CN109583264B - Information identification method and device and electronic equipment - Google Patents
Information identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN109583264B CN109583264B CN201710898341.9A CN201710898341A CN109583264B CN 109583264 B CN109583264 B CN 109583264B CN 201710898341 A CN201710898341 A CN 201710898341A CN 109583264 B CN109583264 B CN 109583264B
- Authority
- CN
- China
- Prior art keywords
- identity information
- identified
- preset
- determining
- target biological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000003111 delayed effect Effects 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the application provides an information identification method and device and electronic equipment. The method comprises the following steps: detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image; determining corresponding identity information according to the target biological characteristics in the multi-frame images; and if the identity information has a preset class characteristic use record, the object to be identified is authenticated in a delayed time. The technical scheme provided by the embodiment of the application reduces the risk of identity authentication.
Description
Technical Field
The embodiment of the application relates to the technical field of computer application, in particular to an information identification method and device and electronic equipment.
Background
In the current application fields of attendance checking, entrance guard, monitoring and the like, the requirements of rapidly confirming the identity of people are involved, and at present, the biological characteristics of a human body are generally utilized to carry out identity authentication, such as a human face, a fingerprint, an iris and the like.
However, some biometrics features are easy to forge, for example, a face photo can be used to perform identity authentication instead of a real face, and since the face photo of the same user is identical to the face features of the real face, the system can be fooled, and the authentication is passed. With the development of biometric technology, although it is now possible to distinguish between genuine features and counterfeit features, if it is determined that the features are counterfeit, it is possible to determine that user authentication has failed. However, a certain misjudgment rate still exists, and if the user repeatedly tries to use the fake feature, the probability that the fake feature is determined as the true feature is greatly improved, so that the identity authentication still has a risk.
Disclosure of Invention
The embodiment of the application provides an information identification method and device and electronic equipment, and aims to solve the technical problem that in the prior art, the risk of identity authentication is high.
In a first aspect, an embodiment of the present application provides an information identification method, including:
detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image;
determining corresponding identity information according to the target biological characteristics in the multi-frame images;
and if the identity information has the use record of the preset class characteristics, the object to be identified is authenticated in a delayed mode.
Optionally, the determining, according to the target biological features of the multiple frames of images, corresponding identity information includes:
determining identity information respectively corresponding to the target biological features in the multi-frame images;
judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same;
if yes, executing the step of delaying to authenticate the object to be identified if the identity information has a preset class characteristic use record;
and if not, determining that the authentication of the object to be identified fails.
Optionally, the detecting the multiple frames of images to obtain the target biometric characteristic of the object to be identified in each frame of image includes:
and detecting the multiple frames of RGB images to obtain the target biological characteristics of the object to be identified in each frame of image.
Optionally, if the identity information has a usage record of a predetermined class of features, the time-lapse authenticating the object to be recognized includes:
if the identity information has a preset feature use record, judging whether the target biological features in the multi-frame images have preset features after a preset time;
if not, determining that the object to be identified is successfully authenticated;
and if so, determining that the authentication of the object to be identified fails.
Optionally, the method further comprises:
if the identity information does not have the preset feature use record, judging whether the target biological features in the multi-frame images have the preset feature or not;
if not, determining that the object to be identified is successfully authenticated;
if so, determining that the authentication of the object to be identified fails.
Optionally, the method further comprises:
if the target biological features in any frame of image are the preset features, recording a preset feature use record aiming at the identity information;
and if the target biological characteristics in the multi-frame images are all non-preset characteristics, deleting the preset characteristic usage record corresponding to the identity information.
Optionally, if the identity information has a usage record of a predetermined class of features, the determining whether the target biometric feature in the multi-frame image has the predetermined class of features after a predetermined time period includes:
if the identity information has a preset class feature use record, determining the use times of the preset class feature;
determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset time length is;
and judging whether the target biological features in the multi-frame images have the preset class features after the preset time.
Optionally, the method further comprises:
and if the identity information corresponding to the target biological feature in any frame of image does not exist, determining that the authentication of the object to be identified fails.
In a second aspect, an embodiment of the present application provides an information identification apparatus, including:
the detection module is used for detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image;
the determining module is used for determining corresponding identity information according to the target biological characteristics in the multi-frame images;
and the first authentication module is used for authenticating the object to be identified in a delayed way if the identity information has the usage record of the preset class characteristics.
Optionally, the determining module is specifically configured to determine identity information corresponding to the target biological features in the multiple frames of images; judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same; if yes, triggering the first authentication module; if not, determining that the authentication of the object to be identified fails.
Optionally, the detection module is specifically configured to detect multiple frames of RGB images, and obtain a target biometric feature of an object to be identified in each frame of image.
Optionally, the first authentication module comprises:
the first judging unit is used for judging whether the target biological characteristics in the multi-frame images have the preset characteristic after a preset time if the preset characteristic use record exists in the identity information;
the first authentication unit is used for determining that the object to be identified fails to be authenticated if the judgment unit has a positive result; and if the judgment unit result is negative, determining that the object to be identified is successfully authenticated.
Optionally, the method further comprises:
the second authentication module is used for judging whether the target biological characteristics in the multi-frame images have the preset characteristic or not if the preset characteristic use record does not exist in the identity information; if so, determining that the authentication of the object to be identified fails; if not, determining that the object to be identified is successfully authenticated.
Optionally, the method further comprises:
the recording module is used for recording a usage record of the preset class of features aiming at the identity information if the target biological features in any frame of image are the preset class of features;
and the deleting module is used for deleting the preset characteristic use record corresponding to the identity information if the target biological characteristics in the multi-frame images are all non-preset characteristics.
Optionally, the first determining unit is specifically configured to: if the identity information has a preset class feature use record, determining the use times of the preset class feature; determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset duration is; and judging whether the target biological characteristics are preset class characteristics after the preset time.
Optionally, the method further comprises:
and the third authentication module is used for determining that the authentication of the object to be identified fails if the identity information corresponding to the target biological feature in any frame of image does not exist.
In a third aspect, an embodiment of the present application provides an electronic device, including a processing component and a memory;
the memory stores one or more computer program instructions for invocation and execution by the processing component;
the processing component is to:
detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image; determining corresponding identity information according to the target biological characteristics in the multi-frame images;
judging whether the identity information has a preset feature use record or not;
and if the identity information has the use record of the preset class characteristics, the object to be identified is authenticated in a delayed mode.
In the embodiment of the application, a plurality of frames of images are detected to obtain the target biological characteristics of the object to be identified in each frame of image; determining corresponding identity information based on the target biological characteristics corresponding to the multi-frame images; if the identity information has the use record of the preset class of features, the object to be recognized is subjected to delay authentication so as to prolong the time of identity authentication of the object to be recognized and increase the time cost for deception of the object to be recognized, so that the risk of identity authentication can be reduced to a certain extent, and the identity authentication of the object to be recognized is performed based on the multi-frame image, so that the misjudgment rate of the identity authentication is reduced, the accuracy of the identity authentication is ensured, and the risk of the identity authentication is further reduced.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart illustrating an embodiment of an information recognition method provided herein;
FIG. 2a is a schematic diagram of an information recognition system in a practical application;
FIG. 2b is a flow chart illustrating a further embodiment of an information recognition method provided herein;
FIG. 3 is a schematic diagram illustrating an embodiment of an information recognition apparatus provided in the present application;
FIG. 4 is a schematic structural diagram of an information recognition apparatus according to another embodiment of the present application;
fig. 5 shows a schematic structural diagram of an embodiment of an electronic device provided in the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
In some of the flows described in the specification and claims of this application and in the above-described figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, the number of operations, e.g., 101, 102, etc., merely being used to distinguish between various operations, and the number itself does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical scheme of the embodiment of the application can be applied to the security fields of attendance checking, entrance guard, monitoring, security protection and the like and used for identity authentication, the object to be identified can be a person, the target biological characteristics can be the inherent physiological characteristics of the human body, and the target biological characteristics can comprise a human face, a fingerprint, an iris and the like. In particular, identity authentication based on face implementation is widely used.
When identity authentication is performed based on biometrics, biometrics of a human body needs to be directly acquired. However, since the biometric features are easily forged, for example, when the biometric features are human faces, the real human faces are the same as the facial features extracted from the human face photos of the real human faces, and therefore, the system is fooled into passing the authentication, and the risk of passing the authentication is brought. There is still a false positive rate, and if repeated attempts are made with the fake features, the probability that the fake features are determined to be true features will be greatly increased, and thus there is still a risk in identity authentication.
In order to reduce the risk of identity authentication, the inventor provides the technical scheme of the application through a series of researches, in the embodiment of the application, firstly, a plurality of frames of images are detected to obtain the target biological characteristics of the object to be identified in each frame of image; based on the target biological characteristics in the multi-frame images, corresponding identity information can be determined; judging whether the identity information has a preset feature use record or not; and if the identity information has a preset class characteristic use record, the object to be identified is authenticated in a delayed time. That is, if the object to be recognized performs identity authentication by using the predetermined class characteristics, the object to be recognized is authenticated in a delayed manner, so that the time for the identity authentication of the object to be recognized is prolonged, the time cost for cheating the object to be recognized is increased, and the risk of the identity authentication can be reduced to a certain extent. And the identity authentication of the object to be identified is carried out based on the multi-frame image, so that the misjudgment rate of the identity authentication is reduced, the accuracy of the identity authentication is ensured, and the risk of the identity authentication is further reduced. Only when the target biological characteristics in the multi-frame images are all non-predetermined characteristics, the object to be identified is determined to be successfully authenticated,
in the embodiment of the present application, the predetermined class of features may be used to represent fake features, and the non-predetermined class of features may represent real features.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a flowchart of an embodiment of an information identification method provided in an embodiment of the present application, where the method may include the following steps:
101: and detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image.
The multi-frame image may be acquired continuously, or may be acquired periodically in a short time. The acquisition time of the multi-frame images is short, the possibility that the object to be recognized changes is low, and the target biological characteristics in the multi-needle images should be the same theoretically, so that the identity authentication can be performed on the object to be recognized.
In the embodiment of the application, in order to reduce the misjudgment rate of the identity authentication, the identity authentication of the object to be recognized is carried out by adopting the multi-frame image, namely, the multi-frame image is adopted for each identity authentication; alternatively, two consecutive frames of images are possible.
Therefore, the target biological characteristics of the object to be identified in each frame of image can be obtained by detecting each frame of image.
When the target biological feature is a human face, the multi-frame image can be obtained by continuously shooting the object to be recognized. The object to be recognized may specifically refer to a user to be recognized.
102: and determining corresponding identity information according to the target biological characteristics in the multi-frame images.
The registered database can store the identity information corresponding to different target biological characteristics, and the identity information corresponding to the target biological characteristics can be identified by searching the registered database.
When the target biological feature is a human face, the identity information corresponding to the target biological feature is determined to be a process of human face recognition, for example, a feature template may be constructed based on a human face obtained from image detection, the feature template and the identity information corresponding to each feature template are stored in a registered database, the obtained feature template is constructed based on the extracted facial feature, and the identity information corresponding to the feature template may be obtained by searching the registered database.
Optionally, since multiple frames of images correspondingly obtain multiple target biological features, the determining the corresponding identity information according to the target biological features in the multiple frames of images may include:
determining identity information respectively corresponding to the target biological features in the multi-frame images;
judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same;
if yes, go to step 103;
if not, the authentication failure of the object to be identified can be directly determined.
If the identity information corresponding to the target biological feature in any frame of image does not exist, the authentication failure of the object to be identified can be directly determined.
103: and if the identity information has the use record of the preset class characteristics, the object to be identified is authenticated in a delayed mode.
The predetermined type of feature may specifically refer to a counterfeit feature, and the predetermined type of feature usage record is also referred to as a counterfeit feature usage record.
The time-delay authentication of the object to be recognized may be that the object to be recognized is authenticated after a predetermined time period after the current time is counted. The predetermined length of time may be preconfigured or determined based on the number of uses of the predetermined class of features, as will be described in more detail in the following embodiments.
If the identity information corresponding to the target biological characteristics exists, in the embodiment of the application, whether the identity information has the use record of the preset characteristics is judged at first, rather than directly determining that the authentication of the object to be recognized is successful.
Optionally, the determining whether the identity information has the usage record of the predetermined class of features may be determining whether the latest authentication result corresponding to the identity information corresponds to the usage record of the predetermined class of features.
If the identity information has the usage record of the predetermined class of features, the identity information is indicated to have the bad record, the object to be identified uses the predetermined class of features for identity authentication once, and in order to prevent the object to be identified from continuing to use the predetermined class of features, the object to be identified can be authenticated in a delayed mode, so that the authentication time of the object to be identified is increased, the time cost of deception of the object to be identified is increased, and the risk of identity authentication can be reduced to a certain extent. And the identity authentication of the object to be identified is carried out based on the multi-frame image, so that the misjudgment rate of the identity authentication is reduced, the accuracy of the identity authentication is ensured, and the risk of the identity authentication is further reduced.
In this embodiment, authenticating the object to be identified may include: and determining whether the target biological characteristics of the object to be identified are the preset class characteristics or not, and determining whether the object to be identified is successfully authenticated or not based on the determination result.
Therefore, optionally, in some embodiments, if the identity information has a feature usage record of a predetermined class, the time-lapse authenticating the object to be identified may include:
if the identity information has a preset feature use record, judging whether the target biological feature is a preset feature after a preset time;
if so, determining that the authentication of the object to be identified fails;
if not, determining that the object to be identified is successfully authenticated.
Namely, when the object to be identified is authenticated, only when the target biological characteristics in the multi-frame images are all non-predetermined characteristics, the object to be identified is determined to be authenticated successfully. Therefore, the misjudgment rate of the identity authentication can be reduced to a certain extent, the accuracy of the identity authentication is ensured, and the risk of the identity authentication is further reduced.
And if the target biological characteristics in any frame of image are the preset class characteristics, determining that the authentication of the object to be identified fails. That is, as long as the target biological feature in one frame of image is the predetermined class feature, that is, the counterfeit feature, the authentication identification of the object to be identified is confirmed.
The object to be identified is determined to be successfully authenticated, that is, the identity information corresponding to the target biological characteristic is used as the identity information of the object to be identified, so that the object to be identified can be correspondingly processed, for example, in an attendance application scene, after the object to be identified is successfully authenticated, attendance information can be recorded for the object to be identified; in an access control application scene, after the object to be identified is successfully authenticated, the access control can be opened, the object to be identified is released, and the like.
If the target biological features in any frame of image are preset features, recording, and generating preset feature use records aiming at the identity information;
in the prior art, after the identity information corresponding to the target biological feature of the object to be recognized is determined and the target biological feature is the predetermined feature, the authentication failure of the object to be recognized can be directly determined, since the detection operation is always performed, the object to be recognized can repeatedly use the predetermined feature to try, the probability that the predetermined feature is judged to be the real feature is improved, and the object to be recognized is possibly authenticated successfully.
In addition, in the prior art, in application scenarios such as attendance checking, access control or monitoring, two cameras are usually arranged to collect images, that is, an infrared camera and an RGB (red-green-blue) camera, and the infrared camera is mainly used to determine whether the target biological features are predetermined features or not in an infrared sensing manner, and particularly, when the target biological features are human faces, whether the target to be recognized is a real person or a photo is determined, but additional infrared detection equipment is required to be added, which is higher in cost.
Optionally, in some embodiments, if the identity information does not have a feature usage record of a predetermined class, the method may further include:
judging whether the target biological features in the multi-frame images have preset class features or not;
if so, determining that the authentication of the object to be identified fails;
if not, determining that the object to be identified is successfully authenticated.
That is, if the identity information does not have the usage record of the predetermined class of features, the object to be recognized may be directly authenticated, where the authentication process includes determining whether a target biometric feature of the object to be recognized is the predetermined class of features, and determining whether the object to be recognized is successfully authenticated based on a result of the determination.
Since the non-predetermined class of features, that is, the real features, may also be identified as the predetermined class of features, in order to avoid an authentication error, and improve the user experience, optionally, in some embodiments, if the target biometric feature is the non-predetermined class of features, the predetermined class of feature record corresponding to the identity information is deleted. Therefore, when the object to be identified performs identity authentication by using the non-predetermined characteristic next time, delayed authentication can be avoided.
Optionally, in order to further reduce the risk of identity authentication, if the object to be identified is continuously authenticated by using the predetermined class features, the delay time may be increased accordingly.
Therefore, in some embodiments, the determining whether the target biometric characteristic in the multi-frame image is the predetermined type of characteristic after the predetermined time period if the predetermined type of characteristic usage record exists in the identity information may include:
if the identity information has a preset class feature use record, determining the number of times of using the preset class feature;
determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset time length is;
judging whether the target biological characteristics are preset class characteristics or not after a preset time length
The object to be identified can be recorded once when the object to be identified uses the preset characteristic once, the number of times of using the preset characteristic by the object to be identified can be determined according to the number of times of recording, and the larger the number of times of recording, the longer the corresponding preset time length, so as to further increase the time of carrying out identity authentication by the time to be identified, increase the time cost of deception, and further reduce the risk of identity authentication.
The technical scheme in the embodiment of the application can be applied to the application fields of attendance checking, entrance guard and the like, and is certainly also applicable to various different security fields of network security control and the like, such as identity authentication in certificates, security detection and monitoring in important places, identity authentication in smart cards, computer login and the like. To reduce the risk of the user using counterfeit features for authentication,
in an actual application, the object to be recognized in the embodiment of the present application is a user to be recognized, the target biometric feature is a human face, the multi-frame image may be obtained by continuously acquiring with an acquisition terminal, and in the attendance application, the acquisition terminal may be an attendance machine or the like. As shown in fig. 2a, the collection terminal 10 may collect the user 20 to be recognized to obtain a multi-frame image, optionally, two continuous frames of images may be obtained each time, the collection terminal 10 may serve as an independent processing device to perform face detection on the multi-frame image, face recognition and authentication on the object to be recognized, of course, in order to improve performance, the collection terminal 10 may also perform only face detection, send the face of the user to be recognized, which is obtained by detection in each frame of image, to the authentication server 30, the authentication server 30 completes face recognition and identity authentication on the object to be recognized, or of course, the collection terminal 10 may transmit the continuous multi-frame image to the authentication server 30, and the authentication server 30 completes face detection, face recognition and identity authentication on the object to be recognized, and the like.
The following describes the technical scheme of the present application in detail, taking an object to be recognized as a user to be recognized and a target biological feature as a human face as an example. As shown in fig. 2, a flowchart of another embodiment of an information identification method provided in the embodiment of the present application may include the following steps:
201: and carrying out face detection on the collected continuous multi-frame images to obtain the face of the user to be identified in each frame of image.
The technical scheme of the embodiment can be applied to the acquisition terminal or the authentication server, and at the moment, the face detection is performed on the continuous multi-frame image acquired by the acquisition terminal, namely, the face detection is performed on the continuous multi-frame image acquired by the acquisition terminal.
In application scenes such as attendance checking, entrance guard and the like, image acquisition can be carried out all the time, and a camera in an attendance checking machine or entrance guard equipment can be used for carrying out image acquisition on a user to be identified.
The face detection is carried out on the collected multi-frame images, and a plurality of faces can be detected and obtained. That is, the user to be identified may include a plurality of users. The identity authentication can be carried out according to the technical scheme of the application aiming at the face of each user to be identified.
202: and determining corresponding identity information according to the human faces in the multi-frame images.
The identity information corresponding to the face is determined, that is, the face recognition process, and a face feature template may be first constructed based on the face features of the face, and then compared with each face feature template stored in the database to determine the identity information corresponding to the face feature template.
Due to the possibility of face forgery, the determined identity information cannot be directly used as the identity information of the user to be identified.
If the identity information corresponding to the faces in the multi-frame images is the same, step 203 may be executed again, otherwise, it may be directly determined that the authentication of the user to be identified fails.
In addition, if the identity information corresponding to the face in any frame of image does not exist, the authentication failure of the user to be identified can be directly determined.
203: and judging whether the identity information has a forged feature use record, if so, executing step 204, and if not, executing step 211.
In this embodiment, the predetermined class of features refers to forged features, and the non-predetermined class of features refers to real features.
To improve accuracy, it may optionally be determined whether the last recognition result of the identity information corresponds to a forged feature usage record.
204: determining a number of uses of the counterfeit feature based on the counterfeit feature usage record.
205: and determining the preset time length corresponding to the using times.
The more the use times are, the longer the corresponding preset duration is.
Optionally, the number of times of use may refer to the number of times of continuous use of the counterfeit feature, that is, the counterfeit feature is used when identity authentication is performed for multiple times.
206: and after the preset time length, judging whether the face in the multi-frame images has a fake feature, if so, executing step 207 and step 208, and if not, executing step 209 and step 210.
207: and determining that the user to be identified fails to be authenticated.
208: recording a fake feature usage record for the identity information.
209: and determining that the user to be identified is successfully authenticated.
That is, when the faces in the multi-frame images are all real features, it is determined that the authentication of the user to be used is successful. And taking the identity information corresponding to the face as the identity information of the object to be identified.
210: and deleting the forged characteristic use record corresponding to the identity information.
211: and judging whether the human face in the multi-frame image has a fake feature, if so, executing step 207 and step 208, and if not, executing step 209 and step 210.
By the embodiment, the risk brought by the fact that the user uses the fake face such as the photo for identity authentication can be reduced. And each time of identity authentication continuously collects multiple frames of images, the success of identity authentication is determined only when the faces of the continuous multiple frames of images are all real features, and the risk of identity authentication is further reduced.
Fig. 3 is a schematic structural diagram of an embodiment of an information identification apparatus according to an embodiment of the present application, where the apparatus may include:
the detection module 301 is configured to detect multiple frames of images to obtain a target biological characteristic of an object to be identified in each frame of image; the multiple frames of images may be acquired continuously, or may be acquired periodically in a short time.
A determining module 302, configured to determine corresponding identity information according to a target biological feature in the multi-frame image;
a first authentication module 303, configured to delay authentication of the object to be identified if the identity information has a predetermined class feature usage record.
The first authentication module may be specifically configured to perform time-delay authentication on the object to be identified if the last authentication result of the identity information corresponds to a predetermined class of feature usage record.
Optionally, the determining module is specifically configured to determine identity information corresponding to the target biological features in the multiple frames of images; judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same; if yes, triggering the first authentication module; if not, determining that the authentication of the object to be identified fails.
If the identity information corresponding to the target biological characteristics exists, in the embodiment of the application, whether the identity information has the use record of the predetermined characteristics is judged at first, rather than directly determining that the authentication of the object to be identified is successful. If the identity information has the usage record of the predetermined class of features, the identity information is indicated to have the bad record, the object to be identified uses the predetermined class of features for identity authentication once, and in order to prevent the object to be identified from continuing to use the predetermined class of features, the object to be identified can be authenticated in a delayed mode, so that the authentication time of the object to be identified is increased, the time cost of deception of the object to be identified is increased, and the risk of identity authentication can be reduced to a certain extent. And the identity authentication of the object to be identified is carried out based on the multi-frame image, so that the misjudgment rate of the identity authentication is reduced, the accuracy of the identity authentication is ensured, and the risk of the identity authentication is further reduced.
Optionally, the detection module is specifically configured to detect multiple frames of RGB images, and obtain a target biometric feature of an object to be identified in each frame of image.
According to the embodiment of the application, the identity authentication of the object to be recognized can be realized only by using the RGB image, and the equipment cost is reduced.
As another embodiment, as shown in fig. 4, the difference from the embodiment shown in fig. 3 is that the first authentication module 303 may include:
a first judging unit 401, configured to judge, after a predetermined time period, whether a target biometric feature in the multiple frames of images is a predetermined type of feature if the identity information has a predetermined type of feature use record;
a first authentication unit 402, configured to determine that the object to be identified fails to be authenticated if the result of the determination unit is yes; and if the judgment unit has a negative result, determining that the object to be identified is successfully authenticated.
Wherein, the device can also include:
a recording module 304, configured to record a predetermined class feature usage record for the identity information if the target biometric feature in any frame of image is a predetermined class feature;
optionally, as shown in fig. 4, the apparatus may further include:
a second authentication module 305, configured to determine whether the target biometric characteristic in the multi-frame image is a predetermined class characteristic if the identity information does not have a predetermined class characteristic usage record; if so, determining that the authentication of the object to be identified fails; if not, determining that the object to be identified is successfully authenticated.
In the embodiment of the present application, the predetermined type of feature may specifically refer to a forged feature, and the predetermined type of feature usage record is also referred to as a forged feature usage record. Since the true features may also be identified as the predetermined class of features, in order to avoid authentication errors, the user experience is improved, optionally, in some embodiments, the apparatus may further include:
and a deleting module 306, configured to delete the predetermined class-specific usage record corresponding to the identity information if the target biological features in the multiple frames of images are all non-predetermined class features.
Further, in some embodiments, the apparatus may further comprise:
and the third authentication module is used for determining that the authentication of the object to be identified fails if the identity information corresponding to the target biological feature in any frame of image does not exist.
Optionally, in order to further reduce the risk of identity authentication, if the object to be identified is continuously authenticated using the predetermined class of features, the delay time may be increased accordingly.
Therefore, in some embodiments, the first determining unit 401 may specifically be configured to: if the identity information has a usage record of the predetermined class of features, determining the number of times of using the predetermined class of features; determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset time length is; and judging whether the target biological characteristics are preset class characteristics or not after the preset time.
The method comprises the steps that the preset class characteristics are used once by an object to be identified, recording is carried out once, the times of using the preset class characteristics by the object to be identified can be determined according to the recording times, the more the recording times are, the longer the corresponding preset time length is, the time for carrying out identity authentication by the object to be identified is further increased, the time cost of deception of the object to be identified is increased, and the risk of identity authentication is further reduced.
In addition, in a practical application, the target biological feature may be a human face;
the detection module may be specifically configured to: and carrying out face detection on the multi-frame images to obtain the face of the object to be identified in each frame of image. By adopting the technical scheme of the embodiment of the application, the risk caused by the fact that the user uses the face of the preset class such as the photo to carry out identity authentication can be reduced.
The information identification apparatus shown in fig. 3 or fig. 4 may be configured to execute the information identification method shown in the embodiment shown in fig. 1 or fig. 2, and the implementation principle and the technical effect are not described again. The specific manner in which each module and unit of the information identification apparatus in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.
In one possible design, the information identification apparatus in the embodiment shown in fig. 3 or fig. 4 may be implemented as an electronic device, and in practical applications, the electronic device may be implemented as a attendance machine, an access control system, a monitoring device, or an authentication server connected to the attendance machine, the access control system, or the monitoring device, or the like.
As shown in fig. 5, the electronic device may include a processing component 501 and a memory 502;
the memory 502 stores one or more computer program instructions for invocation and execution by the processing component;
the processing component 501 is configured to:
detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image; determining corresponding identity information according to the target biological characteristics in the multi-frame images;
judging whether the identity information has a preset feature use record or not;
and if the identity information has a preset class characteristic use record, the object to be identified is authenticated in a delayed time.
Optionally, the processing component 501 may be configured to execute the information identification method according to any of the above embodiments.
The processing component 501 may include one or more processors executing computer instructions to perform all or part of the steps of the method described above. Of course, the processing elements may also be implemented as one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic components configured to perform the above-described methods.
The memory 502 may be configured to store various types of data to support operations at the electronic device. The memory may be implemented by any type or combination of volatile and non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
Of course, the electronic device may of course also comprise other components, such as input/output interfaces, communication components, etc.
The input/output interface provides an interface between the processing component and a peripheral interface module, which may be an output device, an input device, etc.
The communication component is configured to facilitate wired or wireless communication between the electronic device and other devices.
In addition, the electronic device may further include a capture component to capture the image. The processing component is used for specifically carrying out face detection on the multi-frame image acquired by the acquisition component so as to acquire the target biological characteristics of the object to be identified. The multi-frame images can be acquired by the acquisition component continuously.
An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a computer, the information identification method in the embodiment shown in fig. 1 or fig. 2 may be implemented.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (17)
1. An information recognition method, comprising:
detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image;
determining corresponding identity information according to the target biological characteristics in the multi-frame images;
and if the identity information has the use record of the preset class characteristics, the object to be identified is authenticated in a delayed mode.
2. The method according to claim 1, wherein the determining the corresponding identity information according to the target biological characteristics of the multi-frame images comprises:
determining identity information respectively corresponding to the target biological features in the multi-frame images;
judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same;
if yes, executing the step of delaying to authenticate the object to be identified if the identity information has the usage record of the predetermined class of characteristics;
and if not, determining that the authentication of the object to be identified fails.
3. The method according to claim 1, wherein the detecting the plurality of frames of images to obtain the target biological feature of the object to be identified in each frame of image comprises:
and detecting the multiple frames of RGB images to obtain the target biological characteristics of the object to be identified in each frame of image.
4. The method according to claim 1, wherein the delaying the authentication of the object to be identified if the identity information has a feature usage record of a predetermined class comprises:
if the identity information has a preset feature use record, judging whether the target biological features in the multi-frame images have preset features after a preset time;
if not, determining that the object to be identified is successfully authenticated;
and if so, determining that the authentication of the object to be identified fails.
5. The method of claim 1, further comprising:
if the identity information does not have the preset feature use record, judging whether the target biological features in the multi-frame images have the preset feature or not;
if not, determining that the object to be identified is successfully authenticated;
and if so, determining that the authentication of the object to be identified fails.
6. The method of claim 4 or 5, further comprising:
if the target biological features in any frame of image are the preset features, recording a preset feature use record aiming at the identity information;
and if the target biological characteristics in the multi-frame images are all non-preset characteristics, deleting the preset characteristic usage record corresponding to the identity information.
7. The method according to claim 4, wherein the determining whether the predetermined class of features exist in the target biometric features in the multi-frame image after a predetermined time period if the predetermined class of feature usage record exists in the identity information comprises:
if the identity information has a preset class feature use record, determining the use times of the preset class feature;
determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset time length is;
and judging whether the target biological features in the multi-frame images have the preset class features after the preset time.
8. The method of claim 1, further comprising:
and if the identity information corresponding to the target biological features in any frame of image does not exist, determining that the authentication of the object to be identified fails.
9. An information recognition apparatus, characterized by comprising:
the detection module is used for detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image;
the determining module is used for determining corresponding identity information according to the target biological characteristics in the multi-frame images;
and the first authentication module is used for delaying the authentication of the object to be identified if the identity information has a preset class characteristic use record.
10. The apparatus according to claim 9, wherein the determining module is specifically configured to determine identity information corresponding to the target biometrics in the multiple frames of images; judging whether the identity information respectively corresponding to the target biological features in the multi-frame images is the same; if yes, triggering the first authentication module; if not, determining that the authentication of the object to be identified fails.
11. The apparatus according to claim 9, wherein the detection module is specifically configured to detect multiple frames of RGB images, and obtain a target biometric feature of the object to be recognized in each frame of image.
12. The apparatus of claim 9, wherein the first authentication module comprises:
the first judging unit is used for judging whether the target biological characteristics in the multi-frame images have the preset characteristic after a preset time if the preset characteristic use record exists in the identity information;
the first authentication unit is used for determining that the object to be identified fails to be authenticated if the judgment unit has a positive result; and if the judgment unit result is negative, determining that the object to be identified is successfully authenticated.
13. The apparatus of claim 9, further comprising:
the second authentication module is used for judging whether the target biological characteristics in the multi-frame images have the preset characteristic or not if the preset characteristic use record does not exist in the identity information; if so, determining that the authentication of the object to be identified fails; if not, determining that the object to be identified is successfully authenticated.
14. The apparatus of claim 12 or 13, further comprising:
the recording module is used for recording a usage record of the preset class of features aiming at the identity information if the target biological features in any frame of image are the preset class of features;
and the deleting module is used for deleting the preset feature use record corresponding to the identity information if the target biological features in the multi-frame image are all non-preset features.
15. The apparatus according to claim 12, wherein the first determining unit is specifically configured to: if the identity information has a usage record of the predetermined class of features, determining the number of times of using the predetermined class of features; determining corresponding preset time length based on the using times; the more the use times are, the longer the corresponding preset time length is; and judging whether the target biological characteristics are preset class characteristics after the preset time.
16. The apparatus of claim 9, further comprising:
and the third authentication module is used for determining that the authentication of the object to be identified fails if the identity information corresponding to the target biological feature in any frame of image does not exist.
17. An electronic device comprising a processing component and a memory;
the memory stores one or more computer program instructions for invocation and execution by the processing component;
the processing component is to:
detecting the multi-frame images to obtain the target biological characteristics of the object to be identified in each frame of image; determining corresponding identity information according to the target biological features in the multi-frame images;
judging whether the identity information has a preset feature use record or not;
and if the identity information has a preset class characteristic use record, the object to be identified is authenticated in a delayed time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898341.9A CN109583264B (en) | 2017-09-28 | 2017-09-28 | Information identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710898341.9A CN109583264B (en) | 2017-09-28 | 2017-09-28 | Information identification method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109583264A CN109583264A (en) | 2019-04-05 |
| CN109583264B true CN109583264B (en) | 2023-01-17 |
Family
ID=65912786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710898341.9A Active CN109583264B (en) | 2017-09-28 | 2017-09-28 | Information identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583264B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110046597B (en) * | 2019-04-19 | 2025-01-21 | 努比亚技术有限公司 | Face recognition method, mobile terminal and computer readable storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4762805B2 (en) * | 2006-06-29 | 2011-08-31 | 富士通株式会社 | Biometric authentication method and biometric authentication system |
| JP5061322B2 (en) * | 2006-08-21 | 2012-10-31 | 富士通株式会社 | Unauthorized registration prevention device, unauthorized registration prevention method, unauthorized registration prevention program, computer-readable recording medium recording the unauthorized registration prevention program, and unauthorized registration prevention system |
| JP5018035B2 (en) * | 2006-11-20 | 2012-09-05 | ソニー株式会社 | Verification device, verification method and verification program |
| CN102916968B (en) * | 2012-10-29 | 2016-01-27 | 北京天诚盛业科技有限公司 | Identity identifying method, authentication server and identification authentication system |
| CN103186772A (en) * | 2013-01-30 | 2013-07-03 | 上海交大高新技术股份有限公司 | Face recognition system and method based on cluster framework |
| CN103434484B (en) * | 2013-08-20 | 2016-04-27 | 安科智慧城市技术（中国）有限公司 | Vehicle-mounted identification authenticate device, mobile terminal, intelligent vehicle key control system and method |
| JP6202983B2 (en) * | 2013-10-22 | 2017-09-27 | 株式会社東芝 | Identification system |
-
2017
- 2017-09-28 CN CN201710898341.9A patent/CN109583264B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109583264A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106599772B (en) | Living body verification method and device and identity authentication method and device | |
| WO2019091012A1 (en) | Security check method based on facial recognition, application server, and computer readable storage medium | |
| JP5710748B2 (en) | Biometric authentication system | |
| CN109886697A (en) | Method, apparatus and electronic equipment are determined based on the other operation of expression group | |
| WO2019023606A1 (en) | System and method for identifying re-photographed images | |
| US10403076B2 (en) | Method for securing and verifying a document | |
| HK1221831A1 (en) | Method and device for identity authentication | |
| CN109756458B (en) | Identity authentication method and system | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| US20220046012A1 (en) | Method and System for Verifying the Identity of a User | |
| CN109598251A (en) | Testimony of a witness checking method, device, equipment and system and storage medium | |
| CN113780212A (en) | User identity verification method, device, equipment and storage medium | |
| CN109558773B (en) | Information identification method and device and electronic equipment | |
| CN110929244A (en) | Digital identity identification method, device, equipment and storage medium | |
| Surantha et al. | Lightweight face recognition-based portable attendance system with liveness detection | |
| CN111126098A (en) | Certificate image acquisition method, device, equipment and storage medium | |
| CN105427480B (en) | A kind of automatic teller machine based on graphical analysis | |
| CN112183167B (en) | Attendance checking method, authentication method, living body detection method, device and equipment | |
| CN113627387B (en) | Parallel identity authentication method, device, equipment and medium based on face recognition | |
| CN109583264B (en) | Information identification method and device and electronic equipment | |
| CN105897747B (en) | Data storage method and device based on digital biological signature and intelligent equipment | |
| US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
| US20120219192A1 (en) | Method of controlling a session at a self-service terminal, and a self-service terminal | |
| CN114821845B (en) | Card punching method and device | |
| CN114511891B (en) | Face recognition processing method, device, terminal and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |