CN117671744A

CN117671744A - Fingerprint template updating method across acquisition devices, storage medium and electronic device

Info

Publication number: CN117671744A
Application number: CN202311761240.9A
Authority: CN
Inventors: 杨浩; 么依璇; 王升国
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2023-12-20
Filing date: 2023-12-20
Publication date: 2024-03-08

Abstract

The application discloses a fingerprint feature template updating method crossing acquisition equipment, a storage medium and electronic equipment, comprising the following steps: acquiring current fingerprint characteristics and current acquisition equipment characteristics; matching the current fingerprint feature with a first feature template; the current acquisition equipment features are the same as the first main acquisition equipment features, and if the conditions are met, the first feature template is updated; the current acquisition equipment characteristics are different from the first main acquisition equipment characteristics, and if the current acquisition equipment characteristics are different from the second alternative acquisition equipment characteristics, the current fingerprint characteristics and the current acquisition equipment characteristics are used as a second characteristic template; if the current acquisition equipment characteristics are the same as the second alternative acquisition equipment characteristics, updating the second characteristic template if the conditions are met, and replacing the first characteristic template with the second characteristic template when the accumulated updating times of the second alternative fingerprint characteristics reach N times. By the application of the fingerprint template updating method and device, the updating of the fingerprint template under the cross-collection equipment scene can be effectively realized, and the fingerprint identification accuracy is improved.

Description

Fingerprint template updating method across acquisition devices, storage medium and electronic device

Technical Field

The present disclosure relates to fingerprint identification technologies, and in particular, to a method and apparatus for updating a fingerprint feature template of a cross-collection device, a storage medium, and an electronic device.

Background

With the progress of image processing technology, fingerprint recognition systems are becoming more and more widely used.

In the existing fingerprint identification system, fingerprint input by a user is acquired through acquisition equipment, fingerprint characteristics of corresponding fingerprints are acquired, then the fingerprint characteristics are matched with a plurality of fingerprint characteristic templates in a fingerprint characteristic library, and matching scores are determined so as to find the fingerprint characteristic templates matched with the fingerprint input by the user, so that fingerprint identification is realized; and if the matching score is greater than or equal to the template updating threshold, updating the successfully matched fingerprint feature templates by utilizing the fingerprint features of the fingerprints input by the user, thereby continuously perfecting each fingerprint feature template in the fingerprint library and improving the accuracy of fingerprint identification.

With the widespread use of fingerprint recognition systems, there are more types of capturing devices, such as optical fingerprint capturing devices, capacitive fingerprint capturing devices, and ultrasonic fingerprint capturing devices, and the image size captured by the capturing devices also has a plurality of different optional specifications, such as 160×160, 192×192, 256×288, 256×360, and the like. Accordingly, fingerprint recognition also has the scene of crossing acquisition devices, namely the acquisition device for acquiring the user input fingerprint is different from the acquisition device for acquiring the fingerprint when the fingerprint feature template is generated. The above-mentioned fingerprint template updating mode in the existing fingerprint recognition system is only suitable for updating the fingerprint template of a single acquisition device type and specification, namely the acquisition device for acquiring the user input fingerprint is the same as the acquisition device for fingerprint acquisition when generating the fingerprint template, and for the fingerprint recognition scene crossing the acquisition device, if the above-mentioned updating mode is applied to update the fingerprint template, the accuracy of fingerprint recognition can be seriously reduced.

Disclosure of Invention

The application provides a fingerprint feature template updating method, device, storage medium and electronic equipment of cross-collection equipment, which effectively realize updating of fingerprint templates and improve fingerprint identification accuracy for a fingerprint collection scene of the cross-collection equipment.

In order to achieve the above purpose, the present application adopts the following technical scheme:

a method for updating a fingerprint feature template across collection devices, each candidate fingerprint in a fingerprint feature library comprising a first feature template, the first feature template comprising a primary fingerprint feature and a primary collection device feature, the primary collection device feature being used to mark collection device feature information for fingerprint collection when the primary fingerprint feature is generated, the method comprising:

acquiring current fingerprint characteristics of a user input fingerprint and current acquisition equipment characteristics of the user input fingerprint; the current acquisition equipment features are used for marking the feature information of the acquisition equipment for acquiring the user input fingerprint;

matching the current fingerprint features with first feature templates of candidate fingerprints in the fingerprint feature library, and determining first candidate fingerprints successfully matched;

when the current acquisition equipment characteristics are the same as the first main acquisition equipment characteristics in the first characteristic templates of the first candidate fingerprints, if the template updating conditions are met, updating the first characteristic templates of the first candidate fingerprints by using the current fingerprint characteristics; and/or the number of the groups of groups,

When the current acquisition equipment characteristic is different from the first main acquisition equipment characteristic, if the current acquisition equipment characteristic is different from a second alternative acquisition equipment characteristic in a second characteristic template of the first candidate fingerprint, respectively taking the current fingerprint characteristic and the current acquisition equipment characteristic as a second alternative fingerprint characteristic and a second alternative acquisition equipment characteristic in the second characteristic template of the first candidate fingerprint; and/or if the current acquisition equipment characteristics are the same as the second alternative acquisition equipment characteristics, updating a second characteristic template of the first candidate fingerprint by using the current fingerprint characteristics when a template updating condition is met; or the method further comprises the step of replacing the first characteristic template of the first candidate fingerprint with the second characteristic template of the first candidate fingerprint on the premise that the characteristic of the second candidate acquisition equipment is kept unchanged and the accumulated update times of the second candidate fingerprint is N times;

the second characteristic template of the first candidate fingerprint comprises the second candidate fingerprint and the second candidate acquisition equipment characteristic, and the second candidate acquisition equipment characteristic is used for marking the characteristic information of acquisition equipment for fingerprint acquisition when the second candidate fingerprint characteristic is generated.

Preferably, when the current acquisition device characteristic is different from the first main acquisition device characteristic, the method further comprises: and if the second characteristic template of the first candidate fingerprint is empty, respectively taking the current fingerprint characteristic and the current acquisition equipment characteristic as a second alternative fingerprint characteristic and the second alternative acquisition equipment characteristic in the second characteristic template of the first candidate fingerprint.

Preferably, when the current acquisition device feature is the same as the first main acquisition device feature, the template updating condition used is: the first matching score determined when the current fingerprint feature is matched with the first feature template of the first candidate fingerprint is greater than or equal to a first updating threshold; the first updating threshold is an updating threshold corresponding to the first main acquisition equipment characteristic.

Preferably, when the current acquisition device characteristic is the same as the second alternative acquisition device characteristic,

the method further comprises the steps of: matching the current fingerprint feature with the second alternative fingerprint feature, and calculating to obtain a second matching score;

the template updating conditions used are: the second match score is greater than or equal to a second update threshold; wherein the second update threshold is an update threshold corresponding to the second alternative acquisition device feature.

Preferably, the method further comprises: determining and storing update thresholds corresponding to the corresponding acquisition equipment characteristics aiming at various optional acquisition equipment characteristics in advance;

the means for determining the first update threshold includes:

determining a first updating threshold corresponding to the first main acquisition equipment characteristic in the corresponding relation between the stored different acquisition equipment characteristics and the updating threshold;

the means for determining the second update threshold includes:

and determining a second updating threshold corresponding to the second alternative acquisition equipment characteristic in the corresponding relation between the stored different acquisition equipment characteristics and the updating threshold.

Preferably, after replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint, the method further comprises: and deleting the second characteristic templates of the first candidate fingerprints before replacement.

Preferably, the updating the first feature template of the first candidate fingerprint by using the current fingerprint feature includes:

and carrying out fusion processing on the current fingerprint characteristic and the first main fingerprint characteristic to generate a new first main fingerprint characteristic, and keeping the characteristic of the first main acquisition equipment unchanged.

Preferably, the updating the second feature template of the first candidate fingerprint by using the current fingerprint feature includes:

and carrying out fusion processing on the current fingerprint characteristic and the second alternative fingerprint characteristic to generate a new second alternative fingerprint characteristic, and keeping the characteristic of the second alternative acquisition equipment unchanged.

Preferably, after the current fingerprint feature and the current acquisition device feature are respectively used as a second alternative fingerprint feature and the second alternative acquisition device feature in a second feature template of the first candidate fingerprint, the method further comprises: setting the accumulated update times of the second alternative fingerprint feature to be 1;

after updating the second feature template of the first candidate fingerprint with the current fingerprint feature, the method further comprises: and adding 1 to the accumulated update times of the second alternative fingerprint features.

Preferably, the method further comprises: performing cross matching training of fingerprint features on the pairwise combination of the multiple acquisition device features in advance, determining matching thresholds corresponding to the pairwise combination, and storing the matching thresholds;

the matching the current fingerprint feature with the first feature template of the candidate fingerprint in the fingerprint feature library comprises the following steps:

Determining a first matching threshold corresponding to a combination of the current acquisition device feature and a first acquisition device feature in a first feature template of the candidate fingerprint;

matching the current fingerprint feature with the first fingerprint feature in the first feature template of each candidate fingerprint, and selecting the largest matching score from all matching scores obtained by matching;

if the maximum matching score is greater than or equal to the first matching threshold, determining that the matching is successful; otherwise, determining that the matching fails.

Preferably, the acquisition device characteristics include the type of acquisition device, the size of the acquired image, and/or the manufacturer of the acquisition device.

Preferably, the fingerprint features in the first feature template and the second feature template are fingerprint features which are generated by extracting features of the input fingerprint and are expressed in a unified format.

A fingerprint recognition apparatus across a collection device, comprising: the device comprises a fingerprint feature storage unit, a feature acquisition unit, a fingerprint feature matching unit, a first feature template updating unit and a second feature template updating unit;

the fingerprint feature storage unit is used for storing a fingerprint feature library; each candidate fingerprint in the fingerprint feature library comprises a first feature template, wherein the first feature template comprises main fingerprint features and main acquisition equipment features, and the main acquisition equipment features are used for marking the feature information of acquisition equipment for fingerprint acquisition when the main fingerprint features are generated;

The characteristic acquisition unit is used for acquiring the current fingerprint characteristics of the user input fingerprint and the current acquisition equipment characteristics of the user input fingerprint; the current acquisition equipment features are used for marking the feature information of the acquisition equipment for acquiring the user input fingerprint;

the fingerprint matching unit is used for matching the current fingerprint characteristics with a first characteristic template of candidate fingerprints in the fingerprint characteristic library, and determining a first candidate fingerprint successfully matched;

the first feature template updating unit is configured to update, when the current acquired device feature is the same as a first main acquired device feature in a first feature template of the first candidate fingerprint, the first feature template of the first candidate fingerprint by using the current fingerprint feature if a template updating condition is satisfied;

the second feature template updating unit is configured to, when the current acquisition device feature is different from the first main acquisition device feature, respectively use the current fingerprint feature and the current acquisition device feature as a second alternative fingerprint feature and the second alternative acquisition device feature in a second feature template of the first candidate fingerprint if the current acquisition device feature is different from the second alternative acquisition device feature in the second feature template of the first candidate fingerprint; and/or if the current acquisition equipment characteristics are the same as the second alternative acquisition equipment characteristics, updating a second characteristic template of the first candidate fingerprint by using the current fingerprint characteristics when a template updating condition is met; or further comprising, if the accumulated update times of the second candidate fingerprint feature reaches N times on the premise that the second candidate acquisition device feature remains unchanged, replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint; the second characteristic template of the first candidate fingerprint comprises a second candidate fingerprint and a second candidate acquisition device characteristic, and the second candidate acquisition device characteristic is used for marking the characteristic information of acquisition devices for fingerprint acquisition when the second candidate fingerprint characteristic is generated.

Preferably, the second feature template updating unit is further configured to, when the current acquisition device feature is different from the first main acquisition device feature, respectively use the current fingerprint feature and the current acquisition device feature as a second alternative fingerprint feature and the second alternative acquisition device feature in the second feature template of the first candidate fingerprint if the second feature template of the first candidate fingerprint is empty.

Preferably, in the first feature template updating unit, when the current acquisition device feature is the same as the first main acquisition device feature, the template updating condition used is: the first matching score determined when the current fingerprint feature is matched with the first feature template of the first candidate fingerprint is greater than or equal to a first updating threshold; the first updating threshold is an updating threshold corresponding to the first main acquisition equipment characteristic.

Preferably, when the current acquisition device feature is the same as the second alternative acquisition device feature, the second feature template updating unit is further configured to match the current fingerprint feature with the second alternative fingerprint feature, and calculate a second matching score;

In the second feature template updating unit, the template updating conditions used are: the second match score is greater than or equal to a second update threshold; wherein the second update threshold is an update threshold corresponding to the second alternative acquisition device feature.

Preferably, the device further comprises an update threshold storage unit, which is used for determining and storing update thresholds corresponding to the corresponding acquisition equipment characteristics aiming at various optional acquisition equipment characteristics in advance;

in the first feature template updating unit, the determining the first updating threshold includes:

determining a first updating threshold corresponding to the first main acquisition equipment characteristic in the corresponding relation between different acquisition equipment characteristics and updating thresholds stored in the updating threshold storage unit;

in the second feature template updating unit, the determining the second updating threshold includes:

Preferably, the second feature template updating unit is further configured to delete the second feature template of the first candidate fingerprint before replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint.

Preferably, in the first feature template updating unit, the updating the first feature template of the first candidate fingerprint by using the current fingerprint feature includes:

Preferably, in the second feature template updating unit, the updating the second feature template of the first candidate fingerprint by using the current fingerprint feature includes:

Preferably, the second feature template updating unit is further configured to set the cumulative update times of the second alternative fingerprint feature to 1 after the current fingerprint feature and the current acquisition device feature are respectively used as a second alternative fingerprint feature and the second alternative acquisition device feature in the second feature template of the first candidate fingerprint; and the method is further used for adding 1 to the accumulated update times of the second candidate fingerprint features after updating the second feature template of the first candidate fingerprint by using the current fingerprint features.

Preferably, the device further comprises a matching threshold storage unit, wherein the matching threshold storage unit is used for carrying out cross matching training of fingerprint features aiming at the pairwise combination of various acquisition equipment features in advance, determining matching thresholds corresponding to the pairwise combination and storing the matching thresholds;

in the fingerprint feature matching unit, the matching the current fingerprint feature with the first feature template of the candidate fingerprint in the fingerprint feature library includes:

determining a first matching threshold corresponding to a combination of the current acquisition device feature and a first acquisition device feature in a first feature template of the candidate fingerprint in the corresponding relation between different acquisition device feature combinations and matching thresholds stored in the matching threshold storage unit;

As can be seen from the above technical solution, in the present application, a first feature template is set for each candidate fingerprint in a cross-collection device fingerprint feature library; in a cross-acquisition device scenario, a second feature template is also set for the candidate fingerprint. The two feature templates comprise fingerprint features and acquisition equipment features, and the acquisition equipment features are used for marking the feature information of acquisition equipment for fingerprint acquisition when corresponding fingerprint features are generated. Based on the above, when fingerprint identification is performed, a first characteristic template is used, when fingerprint characteristic template updating is performed, a second characteristic template is used for updating the fingerprint template for the scene crossing the acquisition equipment, a first characteristic template is used for updating the fingerprint template for the scene of the same acquisition equipment, and after the set condition is met, the second characteristic template can be used for replacing the first characteristic template.

Specifically, firstly, acquiring the current fingerprint characteristics of the user input fingerprint and the current acquisition equipment characteristics of the user input fingerprint, wherein the current acquisition equipment characteristics are used for marking the characteristic information of acquisition equipment for acquiring the user input fingerprint; and matching the current fingerprint features with first feature templates of candidate fingerprints in the fingerprint feature library, and determining the first candidate fingerprints successfully matched. After determining the first candidate fingerprint, if the current acquisition equipment characteristic is the same as the first main acquisition equipment characteristic in the first characteristic template of the first candidate fingerprint, belonging to the same acquisition equipment condition, and updating the first characteristic template of the first candidate fingerprint by using the current fingerprint characteristic in the same acquisition equipment mode when the updating condition is met; and/or if the current acquisition device feature is different from the first main acquisition device feature in the first feature template of the first candidate fingerprint, the current acquisition device feature belongs to a cross-acquisition device condition, and in this case, different modes are distinguished for updating: if the current acquisition equipment characteristic is different from the second alternative acquisition equipment characteristic in the second characteristic template of the first candidate fingerprint, the current fingerprint characteristic is compared with the fingerprint characteristic of the second characteristic template and belongs to the cross-acquisition equipment condition, and then the current fingerprint characteristic and the current acquisition equipment characteristic are respectively used as a new second alternative fingerprint characteristic and a second alternative acquisition equipment characteristic so as to record the fingerprint template corresponding to the newly introduced acquisition equipment during the current fingerprint acquisition by using the second characteristic template; and/or if the current acquisition equipment characteristics are the same as the second alternative acquisition equipment characteristics, the condition that the current fingerprint characteristics belong to the same acquisition equipment is described as compared with the fingerprint characteristics of the second characteristic template, and when the update condition is met, the second characteristic template of the first candidate fingerprint is updated by utilizing the current fingerprint characteristics in the same acquisition equipment mode, so that the fingerprint template corresponding to the corresponding acquisition equipment recorded in the second characteristic template is perfected; alternatively, it may further include: after the second feature template of the first candidate fingerprint is updated, if the second candidate fingerprint feature is updated for N times under the premise that the feature of the second candidate acquisition device is kept unchanged, the fact that the fingerprint feature in the second fingerprint template is continuously updated for N times in the same acquisition device mode is indicated, the fingerprint feature is considered to meet the precision requirement of the fingerprint template and can be used as the fingerprint template for fingerprint identification processing, and then the first feature template is replaced by the second feature template for subsequent fingerprint identification processing, so that the fingerprint identification processing based on the fact that the replaced first feature template and the current user fingerprint feature belong to the same acquisition device, namely, the scene of the same acquisition device is converted, and compared with the scene of the cross-acquisition device, the fingerprint identification accuracy can be further improved. In conclusion, through the processing of the method, on one hand, reasonable updating of the template under the cross-collection equipment scene can be realized, the accuracy of the fingerprint template under the cross-collection equipment scene is improved, and the accuracy of fingerprint identification is improved; on the other hand, the template under the cross-collection equipment scene can be updated after a period of time, the cross-collection equipment scene is converted into the same collection equipment scene, and the accuracy of fingerprint identification is improved.

Drawings

FIG. 1 is a basic flow diagram of a method for updating a fingerprint template across collection devices in the present application;

FIG. 2 is a flowchart of a method for updating a fingerprint template according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a basic structure of a fingerprint template updating device of a cross-collection device in the present application;

fig. 4 is a schematic basic structure of an electronic device provided in the present application.

Detailed Description

In order to make the objects, technical means and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings.

First, the fingerprint acquisition device is referred to as an acquisition device in the present application. The same collection device in the present application refers to collection devices having the same characteristics, for example, the types of collection devices and the sizes of the collection images are the same, and not necessarily refer to the same collection device, and the cross-collection devices in the present application refer to collection devices having different characteristics, for example, the types of collection devices or the sizes of the collection images are different, and not only refer to different collection devices.

Under the scene of the same acquisition equipment, the acquisition equipment used for the current fingerprint acquisition of a user is the same as the acquisition equipment used for the fingerprint acquisition when the fingerprint template is generated, and when the fingerprint template is updated, the original fingerprint characteristic template and the new fingerprint characteristic which participate in the updating are both from the acquisition equipment with the same characteristic, so that the two characteristics can be fused conveniently to generate the new fingerprint characteristic template; however, in a cross-collection device scenario, the collection device used for the current fingerprint collection of the user is different from the collection device used for the fingerprint collection when the fingerprint template is generated, that is, the original fingerprint feature template and the new fingerprint feature come from collection devices with different characteristics, if the fingerprint feature template is updated by fusion processing according to the existing mode, the accuracy of the fingerprint feature template is seriously affected, and the accuracy of fingerprint identification is further affected.

Based on the above, the application provides a method for updating the fingerprint template of the cross-collection device, which can be used for updating the fingerprint template in a scene of the cross-collection device.

The fingerprint template updating method of the present application is described below. In the application, a first feature template is set for each candidate fingerprint in a fingerprint feature library, and a second feature template is set for the corresponding candidate fingerprint under a cross-collection device scene. The fingerprint feature template comprises fingerprint features and collecting device features, wherein the fingerprint features are the fingerprint feature templates in the existing fingerprint feature template updating method, and the collecting device features are used for marking characteristic information of collecting devices for collecting fingerprints when the fingerprint feature templates are generated. In order to distinguish the fingerprint features and the acquisition device features in the first feature template and the second feature template, the fingerprint features and the acquisition device features in the first feature template are respectively referred to as main fingerprint features and main acquisition device features, and the fingerprint features and the acquisition device features in the second feature template are respectively referred to as alternative fingerprint features and alternative acquisition device features.

That is, the first feature template includes a main fingerprint feature and a main acquisition device feature, the main acquisition device feature is used for marking the feature information of the acquisition device that performs fingerprint acquisition when generating the main fingerprint feature, and the second feature template includes an alternative fingerprint feature and an alternative acquisition device feature, and the alternative acquisition device feature is used for marking the feature information of the acquisition device that performs fingerprint acquisition when generating the alternative fingerprint feature. The main fingerprint features in the first characteristic template are used for fingerprint identification and fingerprint template updating under the same scene, and the alternative fingerprint features in the second characteristic template are used for fingerprint template updating under the cross-scene.

Fig. 1 is a basic flowchart of a fingerprint template updating method across acquisition devices in the present application. As shown in fig. 1, the method includes:

step 101, acquiring current fingerprint characteristics of a user input fingerprint and current acquisition device characteristics of the user input fingerprint.

In this step, for the user input fingerprint of this time, a corresponding fingerprint feature is obtained, which is different from other subsequent fingerprint features, and the fingerprint feature of the user input fingerprint is hereinafter referred to as a current fingerprint feature. For the current acquisition equipment for acquiring the user input fingerprint, acquiring the acquisition equipment characteristics of the current acquisition equipment, and referring to the acquisition equipment characteristics as the current acquisition equipment characteristics. The current acquisition device features are used for marking the feature information of the acquisition device for acquiring the user input fingerprint. In the application, the characteristics of the acquisition devices of each acquisition device can be set according to the needs, for example, the types of the acquisition devices, the sizes of the acquired images and/or manufacturers of the acquisition devices can be included, the acquisition devices from different manufacturers can be used for acquiring the images, and the image styles and the structures of the acquired images can be different, so that the acquisition devices also belong to a scene crossing the acquisition devices, and the application does not limit the specific characteristic types of the acquisition devices.

Step 102, matching the current fingerprint feature with a first feature template of the candidate fingerprints in the fingerprint feature library, and determining a first candidate fingerprint successfully matched.

In the present application, the first feature template is used when fingerprint identification is performed, so that the present fingerprint feature is matched with the first feature template of the candidate fingerprint in this step, and the candidate fingerprint successfully matched is determined, which is hereinafter referred to as the first candidate fingerprint. The specific matching method can adopt various existing modes, and under the scene of cross-acquisition equipment, for example, cross-matching strategy can be adopted to carry out matching processing according to various existing modes.

In addition, in the fingerprint template of the application, the fingerprint features included in the fingerprint template are the fingerprint features represented in a unified format after feature extraction is carried out on the input fingerprint, even though the types of the fingerprint collecting devices, the sizes of the collected images and the like are different, the fingerprint features are represented in the same format after feature extraction when stored as the fingerprint features, and the current fingerprint features of the collected fingerprints are represented in the unified format during the fingerprint identification, so that the current fingerprint features of the collected fingerprints can be matched with the fingerprint features in the fingerprint template for the fingerprints collected by different collecting devices.

Step 103, judging whether the current acquisition equipment features are the same as the first main acquisition equipment features in the first feature template of the first candidate fingerprint; if the same, step 104 is performed, and/or if the same, step 105 is performed.

In the application, the main fingerprint feature and the main acquisition device feature in the first feature template of the first candidate fingerprint are respectively referred to as a first main fingerprint feature and a first main acquisition device feature, so as to refer to the first candidate fingerprint which is successfully matched.

If the current acquisition equipment features are the same as the first main acquisition equipment features, the current acquisition equipment for fingerprint acquisition is the same as the acquisition equipment for fingerprint acquisition when the first main fingerprint features are generated, so that the first candidate fingerprint is updated according to the fingerprint template updating mode in the same acquisition equipment scene for the first characteristic template of the first candidate fingerprint belonging to the same acquisition equipment, and step 104 is carried out; if the current acquisition device feature is different from the first main acquisition device feature, it indicates that the current acquisition device for fingerprint acquisition is different from the acquisition device for fingerprint acquisition when generating the first main fingerprint feature, so that the first feature template of the first candidate fingerprint belongs to a scene crossing the acquisition device, and step 105 is performed to update the second feature template of the first candidate fingerprint according to the new mode provided in the application.

And 104, if the template updating condition is met, updating the first feature template of the first candidate fingerprint by utilizing the current fingerprint features.

As described above, the processing in this step is to update the fingerprint template according to the same scene of the acquisition device. Specifically, whether a template updating condition is met is firstly judged, and after the updating condition is confirmed to be met, the first characteristic template of the first candidate fingerprint is updated by utilizing the current fingerprint characteristics. In more detail, when the first feature template is updated, the first main fingerprint feature may be specifically updated, and since the current acquisition device feature is consistent with the first main acquisition device feature, the first main acquisition device feature may not be updated.

Step 105, judging whether the characteristics of the current acquisition equipment are the same as the characteristics of the second alternative acquisition equipment in the second characteristic template of the first candidate fingerprint; if the same, step 107 is performed, and/or if the same, step 106 is performed.

In the application, the candidate fingerprint features and the candidate acquisition device features in the second feature template of the first candidate fingerprint are respectively referred to as a second candidate fingerprint feature and a second candidate acquisition device feature, so that the first candidate fingerprint which is successfully matched is specified. Typically, the first primary acquisition device characteristic and the second alternative acquisition device characteristic are different.

Step 105 is performed to illustrate that the current acquisition device that performs fingerprint acquisition is different from the acquisition device that performs fingerprint acquisition when generating the first main fingerprint feature, that is, the current acquisition device is in a scene of crossing the acquisition device with respect to the first feature template of the first candidate fingerprint, and in this case, the update process is performed with respect to the second feature template of the first candidate fingerprint. Specific processing requires further differentiation between two scenarios: the cross-acquisition device scene and the same acquisition device scene for the second feature template of the first candidate fingerprint.

Specifically, if the current acquisition device features are different from the second alternative acquisition device features, the current acquisition device for fingerprint acquisition is different from the acquisition device for fingerprint acquisition when the second alternative fingerprint features are generated, so that the second feature template of the first candidate fingerprint belongs to a scene crossing the acquisition device, and then step 106 is performed for processing; if the characteristics of the current acquisition equipment are the same as those of the second alternative acquisition equipment, the characteristic of the current acquisition equipment for fingerprint acquisition is the same as that of the acquisition equipment for fingerprint acquisition when the second alternative fingerprint characteristics are generated, so that the second characteristic templates of the first candidate fingerprints belong to the same acquisition equipment scene, and the second characteristic templates of the first candidate fingerprints can be updated according to the fingerprint template updating mode under the same acquisition equipment scene.

And 106, taking the current fingerprint characteristic and the current acquisition device characteristic as a second alternative fingerprint characteristic and a second alternative acquisition device characteristic in a second characteristic template of the first candidate fingerprint respectively.

Execution of step 106 indicates that the current acquisition device characteristics are not the same as the first master acquisition device characteristics and the second alternative acquisition device characteristics, i.e., the first candidate fingerprint does not include the same scene as the current acquisition device in the fingerprint template. Under the condition, the second characteristic template of the first candidate fingerprint is directly replaced by the fingerprint characteristic and the acquisition equipment characteristic acquired by the fingerprint acquisition, and the fingerprint template corresponding to the acquisition equipment newly introduced during the fingerprint acquisition is recorded. In order to implement the cumulative update times of the fingerprint templates under the features of the acquisition device corresponding to the newly introduced acquisition device, the cumulative update times may be set to 1.

Step 107, updating the second feature template of the first candidate fingerprint by using the current fingerprint feature when the template updating condition is satisfied, or further comprising, if the accumulated number of updates of the second candidate fingerprint feature reaches N times on the premise that the feature of the second candidate acquisition device remains unchanged, replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint.

Wherein N is a preset positive integer. Executing step 107, where the current acquisition device feature is the same as the second alternative acquisition device feature, then the second candidate template may be updated according to the same acquisition device scene. Specifically, whether a template updating condition is met is firstly judged, and after the updating condition is confirmed to be met, the second characteristic template of the first candidate fingerprint is updated by utilizing the current fingerprint characteristics. In more detail, when the second characteristic template is updated, the second alternative fingerprint characteristic can be specifically updated, so that the fingerprint template corresponding to the corresponding acquisition equipment recorded in the second characteristic template is perfected; the second alternative acquisition device feature may not be updated because the current acquisition device feature is consistent with the second alternative acquisition device feature.

After the second feature template of the first candidate fingerprint is updated, if the accumulated update times of the second candidate fingerprint feature reaches N times under the premise that the features of the second candidate acquisition device are kept unchanged, which means that the second candidate fingerprint feature is continuously updated for N times according to the scene of the same acquisition device, the fingerprint feature is considered to meet the precision requirement of the fingerprint template and can be used as the fingerprint template for fingerprint identification processing, and then the first feature template of the first candidate fingerprint is replaced by the second feature template of the first candidate fingerprint, and in subsequent fingerprint identification processing, the first feature template after the replacement of the first candidate fingerprint is used. Meanwhile, in order to ensure that the features of the acquisition equipment corresponding to the first feature template and the second feature template are different, the second feature template of the first candidate fingerprint can be deleted.

Thus, the flow of the fingerprint template updating method of the cross-collection device shown in fig. 1 in the application is ended. In the above fingerprint template updating method, a first characteristic template and a second characteristic template are set for candidate fingerprints in a fingerprint library, fingerprint templates under two different acquisition devices are respectively stored, the first characteristic template is a mature fingerprint template which can be used for fingerprint identification, the second characteristic template is used for storing a fingerprint template under another acquisition device which is different from the acquisition device corresponding to the first characteristic template, the updating of fingerprint characteristics in the two characteristic templates follows the updating mode under the same acquisition device scene, and when the acquisition device for the fingerprint acquisition is different from the two acquisition devices corresponding to the first characteristic template and the second characteristic template, the acquired fingerprint characteristics and the acquired device characteristics are stored as new second characteristic templates; and when the number of times of updating the fingerprint features corresponding to the same acquisition equipment feature in the second feature template reaches the requirement, replacing the first feature template by using the second feature template for subsequent fingerprint identification. According to the processing mode, on one hand, updating of the fingerprint template under the cross-collection equipment scene is reasonably realized, and the accuracy of the fingerprint template under the cross-collection equipment scene is improved, so that the accuracy of fingerprint identification is improved; on the other hand, because the collection equipment for fingerprint identification is unchanged in a period of time under the normal condition, the fingerprint template update after a period of time in the mode can enable the currently used collection equipment to be consistent with the collection equipment corresponding to the fingerprint template, and the scene crossing the collection equipment is converted into the scene of the same collection equipment, so that the fingerprint identification accuracy is further improved. In conclusion, the fingerprint template updating method can improve fingerprint identification precision, adaptability and robustness of fingerprint identification processing.

A specific implementation example of a fingerprint template updating method of a cross-acquisition device scene is given by a specific embodiment. In this particular embodiment, it is assumed that the acquisition device characteristics include the type of acquisition device and the size of the acquired image.

Fig. 2 is a schematic flowchart of a method for updating a fingerprint template in an embodiment of the present application. As shown in fig. 2, the method includes:

step 201, acquiring current fingerprint features of a user input fingerprint and current acquisition device features of the user input fingerprint.

The process of this step is the same as that of step 101, and will not be described here again.

Step 202, matching the current fingerprint feature with a first feature template of a candidate fingerprint in a fingerprint feature library, and determining a first candidate fingerprint successfully matched.

In this embodiment, when fingerprint matching is performed, the current fingerprint feature may be matched with the main fingerprint feature in the first feature template of each candidate fingerprint, a matching score is determined, a first candidate fingerprint successfully matched is found based on the matching score, for example, a maximum value of the matching score may be found in the determined matching scores, and when the maximum value of the matching score is greater than or equal to the matching threshold, the matching is determined to be successful. The specific matching process may be performed in various existing manners. If the matching is not successful, ending the process, and updating the fingerprint template is not performed. The matching threshold is usually set in advance, and in order to complete the update process, an update threshold needs to be set in advance in addition to the matching threshold.

Considering that there may be a cross-acquisition device scene and the same acquisition device scene, it is necessary to set matching thresholds used in the corresponding scenes, respectively.

Setting a matching threshold for a scene across acquisition devices may be by way of cross-matching training. Specifically, the cross matching training can be performed in advance corresponding to a plurality of different characteristic combinations of the acquisition equipment, so as to obtain the matching threshold value under the characteristic combinations of the acquisition equipment. For example, for 160 x 160 image size specifications of the optical fingerprint acquisition instrument and 192 x 192 image size specifications of the capacitance fingerprint acquisition instrument, performing cross matching training to obtain matching thresholds corresponding to the characteristic combination of the acquisition device, and so on to obtain matching thresholds corresponding to various optional image size specifications of the optical fingerprint acquisition instrument and various optional image size specifications of the capacitance fingerprint acquisition instrument, where the matching thresholds corresponding to the combinations can be stored, for example, a two-dimensional matrix can be used for storing, rows of the matrix correspond to different image size specifications of the optical fingerprint acquisition instrument, columns of the matrix correspond to different image size specifications of the capacitance fingerprint acquisition instrument, and a certain value of the matrix represents the matching threshold under the combination of a certain image size specification of the optical fingerprint acquisition instrument and a certain image size specification of the capacitance fingerprint acquisition instrument; for other different types of collection device feature combinations, the corresponding matching threshold may also be determined in the manner described above. The matching threshold values under various different characteristic combinations of the acquisition equipment can be obtained as above.

For the scene of the same acquisition device, the update threshold needs to be considered in addition to the determination of the matching threshold. Specifically, the update threshold is used to determine the template update condition, and as described above, the processing of determining the template update condition is required in the present application, and includes two types: the current acquisition device features belong to the same acquisition device scene as compared to the first main acquisition device features, and the current acquisition device features belong to the same acquisition device scene as compared to the second alternative acquisition device features, i.e. the use of the update threshold is essentially involved in the same acquisition device scene. Based on this, in this embodiment, the update threshold and the matching threshold need to be considered for the scene of the same acquisition device. Specifically, the matching threshold may be determined and saved for various optional acquisition device types and acquired image sizes. That is, the matching threshold and the updating threshold are determined and stored for various optional acquisition device features. More specifically, the fingerprint image can be acquired and the fingerprint identification and update can be trained according to a certain acquisition equipment characteristic, so that a matching threshold value and an update threshold value corresponding to the corresponding acquisition equipment characteristic are obtained, and for other various acquisition equipment characteristics, the same way is adopted for training to obtain the corresponding matching threshold value and update, and finally, the matching threshold values and the update threshold values corresponding to all optional acquisition equipment characteristics are obtained.

When preserving the matching threshold in the same collection device scenario, the matching threshold may also be preserved as corresponding to a collection device feature combination, except that the combination is a combination of a collection device feature with itself. In this way, the matching thresholds for the same acquisition device scene may be stored in the same manner as across acquisition device scenes.

And determining matching thresholds corresponding to the various scenes and the characteristic combinations of the acquisition equipment based on the mode. When the current fingerprint feature is matched with a certain candidate fingerprint A, determining a combination B of the current acquisition equipment feature and the main acquisition equipment feature in a first feature template of the candidate fingerprint A, finding a matching threshold corresponding to the combination B in a corresponding relation between a pre-stored acquisition feature combination and a matching threshold and an updating threshold, and determining a first candidate fingerprint successfully matched based on the matching threshold. If the matching is not successful (i.e. the first candidate fingerprint is not found), the process can be ended, and the fingerprint template is not updated in the matching. After the first candidate fingerprint is determined, a matching score determined when the current fingerprint feature is matched with the first main fingerprint feature in the first feature template of the first candidate fingerprint is stored, and the matching score is hereinafter referred to as a first matching score and used for subsequent updating processing.

Step 203, determining whether the current acquisition device feature is the same as the first main acquisition device feature, if so, executing step 204, otherwise, executing step 206.

In this application, the same characteristics of the collection device refer to that the information of each characteristic described by the characteristics of the collection device is the same, and in this embodiment, the characteristics of the collection device include the type of the collection device and the size of the collection image, so that the characteristics of the collection device are the same, that is, the type of the collection device is the same and the size of the collection image is the same.

The processing in this step is the same as that in step 103, and will not be described here again.

Step 204, determining whether the first matching score is greater than or equal to a first updating threshold, if yes, executing step 205, otherwise, ending the fingerprint updating process.

The first update threshold is an update threshold corresponding to a first primary collection device feature. The foregoing detailed description of step 202 refers to that the corresponding update threshold value is stored in advance corresponding to various optional acquisition device features, and in this step, when determining the template update condition, the update threshold value corresponding to the first main acquisition device feature needs to be determined.

In this embodiment, corresponding to the situation that the current acquisition device feature is the same as the first main acquisition device feature, the template updating condition is: the first match score is greater than or equal to a first update threshold. Based on this, if the first matching score is greater than or equal to the first update threshold, the template update condition is satisfied, and step 205 is executed to update the first feature template.

Step 205, updating a first feature template of the first candidate fingerprint with the current fingerprint feature.

The first feature template of the first candidate fingerprint is updated by being divided into an update of the first main fingerprint feature and an update of the first main acquisition device feature. For updating the first main fingerprint feature, an existing fingerprint template updating mode may be adopted, for example, the current fingerprint feature and the first main fingerprint feature are fused to generate a new first main fingerprint feature. The characteristics remain unchanged for the first main acquisition device.

Step 206, determining whether the second feature template of the first candidate fingerprint is empty, if yes, executing step 207, otherwise, executing step 208.

Considering that the second feature template may be empty (i.e. the second feature template has not been set before) when the fingerprint template of the first candidate fingerprint is initially set up, or that the second feature template before the replacement may be deleted after the first feature template is replaced by the second feature template in step 213, the second feature template may also be empty (i.e. the second feature template set before has been deleted), it is preferable to use this step to process whether the second feature template is empty. Specifically, if the second feature template of the first candidate fingerprint is empty, step 207 is executed to directly form the current fingerprint feature and the current acquisition device feature into the second feature template of the first candidate fingerprint; otherwise, step 208 is performed to compare the current acquisition device with the second alternative acquisition device characteristics.

Step 207, taking the current fingerprint feature and the current acquisition device feature as a second alternative fingerprint feature and a second alternative acquisition device feature in a second feature template of the first candidate fingerprint respectively, and setting the accumulated update times of the second alternative fingerprint feature to be 1.

The step is used for initializing a second feature template of the first candidate fingerprint, specifically, taking the current fingerprint feature as a second candidate fingerprint feature and taking the current acquisition device feature as a second candidate acquisition device feature.

In order to realize the replacement of the second feature template to the first feature template, the number of accumulated updating times of the alternative fingerprint features corresponding to the same acquisition equipment features in the second feature template is required to be counted. Based on this, after initializing the second feature template in this step, the cumulative update number of the second alternative fingerprint feature is set to 1, which indicates that the corresponding fingerprint feature update number is 1 corresponding to the second alternative acquisition device feature.

Step 208, determining whether the current acquisition device feature is the same as the second alternative acquisition device feature, if so, executing step 210, otherwise executing step 207.

The step and the subsequent steps are used for updating the second feature templates of the first candidate fingerprints. Firstly, judging whether the current acquisition equipment characteristics are the same as or belong to the cross-acquisition equipment scene compared with the second alternative acquisition equipment characteristics, if the current acquisition equipment characteristics are different from the second alternative acquisition equipment characteristics, determining the scene belonging to the cross-acquisition equipment, executing step 207, and updating by adopting the same processing mode when the second characteristic template is empty. If the current acquisition device feature is the same as the second alternative acquisition device feature, determining a scene belonging to the same acquisition device, executing step 209, and performing update processing according to the update mode of the scene of the same acquisition device.

Step 207, taking the current fingerprint feature and the current acquisition device feature as a new second alternative fingerprint feature and a new second alternative acquisition device feature in a second feature template of the first candidate fingerprint respectively, and setting the accumulated update times of the second alternative fingerprint feature to be 1.

Because the current acquisition equipment characteristic is different from the second alternative acquisition equipment characteristic, corresponding fingerprint characteristics cannot be subjected to fusion processing to achieve updating, in the method, the current fingerprint characteristic and the current acquisition equipment characteristic are directly used as a new second alternative fingerprint characteristic and a new second alternative acquisition equipment characteristic in a second characteristic template of a first candidate fingerprint respectively, so that a new second characteristic template of the first candidate fingerprint is generated, namely, the recording of the fingerprint template corresponding to the newly introduced current acquisition equipment characteristic is started. Since the second alternative acquisition device feature is updated, the accumulated update times of the second alternative fingerprint feature corresponding to the acquisition device feature need to be restarted to count, and the corresponding accumulated update times are set to 1 to represent the corresponding new acquisition device feature, and the accumulated update times of the corresponding fingerprint feature are set to 1.

Step 209, matching the current fingerprint feature with a second alternative fingerprint feature, calculating to obtain a second matching score, and determining a second update threshold corresponding to the second alternative acquisition device feature.

Because the current fingerprint feature is compared with the second alternative fingerprint feature, and belongs to the scene of the same acquisition equipment, according to the updating mode under the corresponding scene, the current fingerprint feature and the second alternative fingerprint feature are matched at first, and a second matching score is obtained through calculation. The specific matching process may be performed in various existing manners, which is not limited in this application.

The update threshold also needs to be determined in the same update manner as in the acquisition device scenario. Specifically, the foregoing detailed description of step 202 refers to the preservation of corresponding update thresholds for various optional acquisition device features, and this step determines an update threshold corresponding to a second alternative acquisition device feature based on the correspondence between the pre-preserved acquisition device features and the update thresholds, hereinafter referred to as a second update threshold.

Step 210, determining whether the second matching score is greater than or equal to the second updating threshold, if yes, executing step 211, otherwise, ending the fingerprint updating process.

In this embodiment, corresponding to the case where the current acquisition device feature is the same as the second alternative acquisition device feature, the template update condition is: the second match score is greater than or equal to a second update threshold. Based on this, if the second matching score is greater than or equal to the second update threshold, the template update condition is satisfied, and step 211 is executed to update the second feature template.

Step 211, updating the second feature template of the first candidate fingerprint by using the current fingerprint feature, and adding 1 to the accumulated update times of the second candidate fingerprint feature.

And when the second characteristic template of the first candidate fingerprint is updated, the second characteristic template is divided into the update of the second candidate fingerprint characteristic and the update of the second candidate acquisition equipment characteristic. For updating the second alternative fingerprint feature, an existing fingerprint template updating mode may be adopted, for example, the current fingerprint feature and the second alternative fingerprint feature are fused to generate a new second alternative fingerprint feature. The characteristics remain unchanged for the second alternative acquisition device.

In order to realize the replacement of the second feature template to the first feature template, the number of accumulated updating times of the alternative fingerprint features corresponding to the same acquisition equipment features in the second feature template is required to be counted. Based on this, after the second alternative fingerprint feature is updated in this step, the accumulated update times of the second alternative fingerprint feature is added by 1, which indicates that the corresponding fingerprint feature is updated 1 more time corresponding to the second alternative acquisition device feature.

Step 212, judging whether the accumulated update times of the second alternative fingerprint feature reaches N, if so, executing step 213, otherwise, ending the fingerprint update flow.

If the accumulated number of updates of the second alternative fingerprint feature reaches N, which indicates that, under the same acquisition device feature, the corresponding fingerprint feature has been continuously updated N times, and the fingerprint feature has reached the accuracy requirement for performing fingerprint identification, step 213 may be performed, where the first feature template is replaced with the second feature template, and the second feature template may be deleted. If the accumulated update times of the second alternative fingerprint feature do not reach N, which means that the corresponding fingerprint feature does not reach the accuracy requirement for fingerprint identification, ending the fingerprint update flow.

In addition, N is a preset positive integer, and the specific value can be set according to experience, so that on one hand, the value of N cannot be too small, otherwise, the accuracy requirement for fingerprint identification cannot be met, the accuracy of fingerprint identification is affected, and on the other hand, the value of N cannot be too large, otherwise, a longer time is required to convert a cross-acquisition equipment scene into the same acquisition equipment scene.

Step 213, replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint, and deleting the second feature template of the first candidate fingerprint before replacement.

Execution of step 213 illustrates that the second alternative fingerprint feature has reached the accuracy requirement for performing fingerprint identification, the second feature template may be used as a new first feature template for subsequent fingerprint identification processing. The consideration of such a process is: the scene that this application relates to striding collection equipment means fingerprint identification's collection equipment has changed, but usually fingerprint collection equipment usually can not frequently change, a period after the change can keep unchanged usually, therefore, through the processing of this step, replace first characteristic template for second characteristic template, then can make the collection equipment that is used for fingerprint identification's fingerprint template corresponds with carry out fingerprint collection's collection equipment unanimous, namely will stride the scene of collection equipment and change into the scene of the same collection equipment, can further improve fingerprint identification's accuracy. After the first feature template of the first candidate fingerprint is replaced by the second feature template of the first candidate fingerprint, the fingerprint features and the acquisition device features in the second feature template are stored in the first feature template, so that the second feature template of the first candidate fingerprint before replacement can be deleted for ensuring that the two feature templates correspond to different acquisition device features, and the replaced first feature template is reserved for fingerprint identification.

In addition, after the processing in step 213 is completed, when fingerprint identification and fingerprint template updating are performed again, the processing may still be performed according to the method of the present application, or the fingerprint identification and fingerprint template updating may also be performed directly by adopting the existing manner under the same acquisition device scene, until the subsequent fingerprint identification and fingerprint template updating are performed again according to the method of the present application after triggering of a button or other preset event.

To this end, in the specific embodiment shown in fig. 2, the flow of the fingerprint template updating method across the collection device ends. By the fingerprint template updating method, the problem of low recognition rate caused by different features of the acquisition equipment in the fingerprint recognition process can be effectively avoided, and the fingerprint recognition precision and the adaptability and the robustness of fingerprint recognition processing can be improved.

The method is a specific implementation of a fingerprint template updating method of the cross-collection device. The application also provides a device for updating the fingerprint template of the cross-collection device, which can be used for implementing the method for updating the fingerprint template of the cross-collection device. Fig. 3 is a schematic diagram of a basic structure of a fingerprint template updating device of a cross-collection device in the present application. As shown in fig. 3, the apparatus includes: the device comprises a fingerprint feature storage unit, a feature acquisition unit, a fingerprint feature matching unit, a first feature template updating unit and a second feature template updating unit.

The fingerprint feature storage unit is used for storing the fingerprint feature library; each candidate fingerprint in the fingerprint feature library comprises a first feature template, wherein the first feature template comprises main fingerprint features and main acquisition equipment features, and the main acquisition equipment features are used for marking the feature information of acquisition equipment for fingerprint acquisition when the main fingerprint features are generated;

the characteristic acquisition unit is used for acquiring the current fingerprint characteristics of the user input fingerprint and the current acquisition equipment characteristics of the user input fingerprint; the current acquisition equipment features are used for marking the feature information of acquisition equipment for acquiring the fingerprint input by the user;

the fingerprint matching unit is used for matching the current fingerprint characteristics with the first characteristic templates of the candidate fingerprints in the fingerprint characteristic library, and determining the first candidate fingerprints successfully matched;

the first characteristic template updating unit is used for updating the first characteristic template of the first candidate fingerprint by utilizing the current fingerprint characteristic if the template updating condition is met when the current acquisition equipment characteristic is the same as the first main acquisition equipment characteristic in the first characteristic template of the first candidate fingerprint;

the second characteristic template updating unit is used for respectively taking the current fingerprint characteristic and the current acquisition equipment characteristic as a second alternative fingerprint characteristic and a second alternative acquisition equipment characteristic in a second characteristic template of the first candidate fingerprint if the current acquisition equipment characteristic is different from the second alternative acquisition equipment characteristic in the second characteristic template of the first candidate fingerprint when the current acquisition equipment characteristic is different from the first main acquisition equipment characteristic; and/or if the current acquisition equipment characteristics are the same as the second alternative acquisition equipment characteristics, updating a second characteristic template of the first candidate fingerprint by utilizing the current fingerprint characteristics when the template updating conditions are met; or further comprising, if the accumulated update times of the second candidate fingerprint feature reaches N times on the premise that the second candidate acquisition device feature remains unchanged, replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint; the second characteristic template of the first candidate fingerprint comprises a second candidate fingerprint and a second candidate acquisition device characteristic, wherein N is a preset positive integer, and the second candidate acquisition device characteristic is used for marking the characteristic information of acquisition devices for acquiring fingerprints when the second candidate fingerprint characteristic is generated.

Optionally, the second feature template updating unit is further configured to, when the current acquisition device feature is different from the first main acquisition device feature, respectively use the current fingerprint feature and the current acquisition device feature as the second alternative fingerprint feature and the second alternative acquisition device feature in the second feature template of the first candidate fingerprint if the second feature template of the first candidate fingerprint is empty.

Optionally, in the first feature template updating unit, when the current acquisition device feature is the same as the first main acquisition device feature, the template updating condition used may be: the first matching score determined when the current fingerprint feature is matched with the first feature template of the first candidate fingerprint is greater than or equal to a first updating threshold; wherein the first update threshold is an update threshold corresponding to a first primary collection device feature.

Optionally, when the current acquisition device feature is the same as the second alternative acquisition device feature, the second feature template updating unit may be further configured to match the current fingerprint feature with the second alternative fingerprint feature, and calculate a second matching score;

in the second feature template updating unit, the template updating condition used may be: the second match score is greater than or equal to a second update threshold; wherein the second update threshold is an update threshold corresponding to a second alternative acquisition device feature.

Optionally, the apparatus may further include an update threshold storage unit, configured to determine, in advance, an update threshold corresponding to each of the optional acquisition device features, and store the update threshold;

in the first feature template updating unit, the determining a first updating threshold may specifically include:

determining a first updating threshold corresponding to the first main acquisition equipment characteristic in the corresponding relation between different acquisition equipment characteristics and the updating threshold stored in the updating threshold storage unit;

in the second feature template updating unit, the determining the second updating threshold may specifically include:

Optionally, the second feature template updating unit may further delete the second feature template of the first candidate fingerprint before replacement after replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint, where the fingerprint features and the acquisition device features of the second feature template are already stored in the first feature template, so as to ensure that the first feature template of the first candidate fingerprint is different from the acquisition device features in the second feature template.

Optionally, in the first feature template updating unit, the process of updating the first feature template of the first candidate fingerprint by using the current fingerprint feature may specifically include:

and carrying out fusion processing by utilizing the current fingerprint characteristics and the first main fingerprint characteristics to generate new first main fingerprint characteristics, and keeping the characteristics of the first main acquisition equipment unchanged.

Optionally, in the second feature template updating unit, the process of updating the second feature template of the first candidate fingerprint by using the current fingerprint feature may specifically include:

and carrying out fusion processing by utilizing the current fingerprint characteristic and the second alternative fingerprint characteristic, generating a new second alternative fingerprint characteristic, and keeping the characteristic of the second alternative acquisition equipment unchanged.

Optionally, the second feature template updating unit may be further configured to set the cumulative update number of the second alternative fingerprint feature to 1 after taking the current fingerprint feature and the current acquisition device feature as the second alternative fingerprint feature and the second alternative acquisition device feature in the second feature template of the first candidate fingerprint, respectively; and may be further configured to increment the cumulative update number of the second candidate fingerprint feature by 1 after updating the second feature template of the first candidate fingerprint with the current fingerprint feature.

Optionally, the device further comprises a matching threshold storage unit, wherein the matching threshold storage unit is used for carrying out cross matching training on fingerprint features in advance for the pairwise combination of the multiple acquisition device features, determining matching thresholds corresponding to the pairwise combination and storing the matching thresholds;

in the fingerprint feature matching unit, the process of matching the current fingerprint feature with the first feature template of the candidate fingerprint in the fingerprint feature library may specifically include:

determining a first matching threshold corresponding to the combination of the first acquisition device features in the first feature template of the current acquisition device features and the candidate fingerprints in the corresponding relation between the different acquisition device feature combinations and the matching threshold stored in the matching threshold storage unit;

if the maximum matching score is greater than or equal to the first matching threshold value, determining that the matching is successful; otherwise, determining that the matching fails.

Alternatively, the capture device characteristics may include the type of capture device, the size of the captured image, and/or the manufacturer of the capture device.

Optionally, the fingerprint features in the first feature template and the second feature template are fingerprint features represented in a unified format generated after feature extraction of the input fingerprint.

The present application also provides a computer readable storage medium storing instructions that, when executed by a processor, can perform the steps in a method of updating a fingerprint template across an acquisition device as described above. In practice, the computer readable medium may be comprised by or separate from the apparatus/device/system of the above embodiments, and may not be incorporated into the apparatus/device/system. Wherein instructions are stored in a computer readable storage medium, which stored instructions, when executed by a processor, can perform the steps in a method of updating a fingerprint template across an acquisition device as described above.

According to embodiments disclosed herein, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: portable computer diskette, hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing, but are not intended to limit the scope of the protection herein. In the embodiments disclosed herein, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

Fig. 4 is a schematic basic structure of an electronic device provided in the present application. As shown in fig. 4, a schematic structural diagram of an electronic device according to an embodiment of the present application is shown, specifically:

the electronic device may include a processor 401 of one or more processing cores, a memory 402 of one or more computer readable storage media, and a computer program stored on the memory and executable on the processor. The method of updating fingerprint templates across acquisition devices may be implemented when executing the program of the memory 402.

Specifically, in practical applications, the electronic device may further include a power supply 403, an input/output unit 404, and other components. Those skilled in the art will appreciate that the configuration of the electronic device shown in fig. 4 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components. Wherein:

the processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of a server and processes data by running or executing software programs and/or modules stored in the memory 402, and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device.

Memory 402 may be used to store software programs and modules, i.e., the computer-readable storage media described above. The processor 401 executes various functional applications and data processing by running software programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required for at least one function, and the like; the storage data area may store data created according to the use of the server, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

The electronic device further comprises a power supply 403 for supplying power to the respective components, which may be logically connected to the processor 401 by a power management system, so that functions of managing charging, discharging, power consumption management, etc. are implemented by the power management system. The power supply 403 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

The electronic device may also include an input output unit 404, which input unit output 404 may be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical signal inputs related to user settings and function control. The input unit output 404 may also be used to display information entered by a user or provided to a user as well as various graphical user interfaces that may be composed of graphics, text, icons, video, and any combination thereof.

The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the invention.

Claims

1. A method for updating a fingerprint feature template across collection devices, wherein each candidate fingerprint in a fingerprint feature library comprises a first feature template, the first feature template comprises a main fingerprint feature and a main collection device feature, the main collection device feature is used for marking feature information of collection devices that collect fingerprints when generating the main fingerprint feature, the method comprises:

2. The method of claim 1, wherein when the current acquisition device characteristic is different from the first master acquisition device characteristic, the method further comprises: and if the second characteristic template of the first candidate fingerprint is empty, respectively taking the current fingerprint characteristic and the current acquisition equipment characteristic as a second alternative fingerprint characteristic and the second alternative acquisition equipment characteristic in the second characteristic template of the first candidate fingerprint.

3. The method of claim 1, wherein when the current acquisition device characteristic is the same as the first master acquisition device characteristic, the template update condition used is: the first matching score determined when the current fingerprint feature is matched with the first feature template of the first candidate fingerprint is greater than or equal to a first updating threshold; the first updating threshold is an updating threshold corresponding to the first main acquisition equipment characteristic.

4. The method of claim 1, wherein, when the current acquisition device characteristic is the same as the second alternative acquisition device characteristic,

5. The method according to claim 3 or 4, characterized in that the method further comprises: determining and storing update thresholds corresponding to the corresponding acquisition equipment characteristics aiming at various optional acquisition equipment characteristics in advance;

the means for determining the first update threshold includes:

the means for determining the second update threshold includes:

6. The method of claim 1, wherein after replacing the first feature template of the first candidate fingerprint with the second feature template of the first candidate fingerprint, the method further comprises: and deleting the second characteristic templates of the first candidate fingerprints before replacement.

7. The method of claim 1, wherein updating the first feature template of the first candidate fingerprint with the current fingerprint feature comprises:

8. The method of claim 1, wherein updating the second feature template of the first candidate fingerprint with the current fingerprint feature comprises:

9. The method according to claim 1 or 2, characterized in that after having the current fingerprint feature and the current acquisition device feature as a second alternative fingerprint feature and the second alternative acquisition device feature in a second feature template of the first candidate fingerprint, respectively, the method further comprises: setting the accumulated update times of the second alternative fingerprint feature to be 1;

10. The method according to claim 1, characterized in that the method further comprises: performing cross matching training of fingerprint features on the pairwise combination of the multiple acquisition device features in advance, determining matching thresholds corresponding to the pairwise combination, and storing the matching thresholds;

11. The method of claim 1, wherein the acquisition device characteristics include a type of acquisition device, a size of an acquisition image, and/or a manufacturer of the acquisition device.

12. The method of claim 1, wherein the fingerprint features in the first feature template and the second feature template are fingerprint features in a unified format generated by feature extraction of an input fingerprint.

13. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of cross-acquisition device fingerprint template updating of any one of claims 1 to 12.

14. An electronic device comprising at least a computer-readable storage medium and a processor;

the processor configured to read executable instructions from the computer readable storage medium and execute the instructions to implement the cross-acquisition device fingerprint template updating method of any one of the preceding claims 1-12.