CN109508705B - Dynamic threshold face comparison setting method based on the validity period of ID card - Google Patents

Abstract

The invention relates to a method for setting a dynamic face comparison threshold value based on the validity period of an ID card, which includes obtaining the certificate application time of the ID card; It also includes a witness comparison module. The witness comparison module is also used to compare the obtained ID card photo with the face photo collected on the spot. If the comparison score is greater than the dynamic threshold, it means that it is the same person. If the score after comparison is less than the dynamic threshold, it means that it is not the same person, and further verification is required. The dynamic threshold setting method provided by the present invention solves the occurrence of comparison failure caused by setting a fixed threshold; increasing the pass rate of witness comparison can improve the check-in efficiency of the hotel; and increase the passenger's check-in experience.

Description

Dynamic threshold face comparison setting method based on the validity period of ID card

technical field

The invention belongs to the technical field of face recognition, and in particular relates to a dynamic face comparison threshold setting method based on the validity period of an ID card.

Background technique

The validity period of the ID card is divided into ten years, twenty years, and long-term; in different validity periods, there is often a large gap between the actual photo and the photo on the ID card, especially the photo at the initial stage of the application and the actual photo at the end of the expiration period. The difference between the photos is even greater. The existing human-to-identity comparison of ID cards adopts a unified threshold. This method of using a unified and fixed threshold for comparison will cause the comparison to fail due to the difference between the actual photo and the ID photo on the ID card. situation occurs frequently.

With the large-scale promotion and implementation of face recognition in the hotel industry, the probability of failure of the comparison in the case of the same person with the same certificate has increased significantly. The reason for this is that our ID card is valid for ten years, twenty years, and long-term; During the validity period of the certificate, such as the initial period of the certificate application and the end of the certificate application period, there is a large gap between the actual photo and the photo on the ID card, resulting in the failure of the comparison of the same person and the same certificate;

The environment of the hotel industry is different. Some hotels are dimly lit and some are heavily backlit. Coupled with the gap between the ID card photo and the actual photo, the probability of failure of the same person to pass the same card increases;

The existing fixed threshold applications have the following deficiencies in human identification verification:

1. If the hotel has a large number of occupants, it will increase the waiting time of other passengers, increase the workload of the hotel staff, and cause other waiting passengers to experience a poor check-in experience.

2. There is sometimes a big gap between the photos when people apply for ID cards and the photos on the spot, and the comparison often fails in the case of a unified threshold;

3. When the number of hotel check-ins is compared, if the comparison fails, the passenger will generally swipe the card for the second or third time, which will increase the waiting time of other hotels to a certain extent; , to a certain extent, increase the workload of hotel staff.

SUMMARY OF THE INVENTION

In order to solve the above problems existing in the prior art, the present invention provides a method for setting a dynamic face comparison threshold based on the validity period of an ID card. The present invention dynamically adjusts the human ID comparison threshold according to the difference between the ID card processing time and reality, thereby reducing the number of The comparison failure caused by uniformly setting the threshold value;

The technical scheme adopted in the present invention is: a dynamic face comparison threshold setting method based on the validity period of an ID card,

The time for obtaining the ID card has been issued;

Dynamically adjust the threshold of witness-to-certificate comparison based on the time of obtaining the certificate and the validity period of the ID card.

Further, it also includes a limited period for obtaining an ID card by swiping the ID card of the person being verified.

Further, according to the start time and end time of the limited period, the validity period of the ID card is obtained.

Further, according to the time when the verified person swiped the ID card and the start time of the limited period, the time of obtaining the certificate is calculated.

Further, it also includes a witness comparison module, the witness comparison module is used to obtain the ID card photo and the face photo collected on the spot.

Further, the human-certificate comparison module is also used to compare the obtained ID photo with the face photo collected on the spot.

Further, it also includes a time analysis module and a dynamic threshold adjustment module;

The time analysis module: calculates the valid time of the ID card according to the limited period information of the ID card obtained by the ID card analysis module and the current system time;

Dynamic threshold adjustment module: According to the valid time of the ID card obtained by the time analysis module and the time when the certificate has been issued, the dynamic threshold under the valid time and the time when the certificate has been issued is calculated.

Further, the dynamic threshold adjustment adopts the following steps:

The time analysis module calculates the valid time of the ID card according to the limited period information of the ID card obtained by the ID card analysis module and the current system time;

The dynamic threshold adjustment module calculates the valid time and the dynamic threshold under the certificated time according to the valid time of the ID card and the certificated time obtained by the time analysis module.

Further, if the compared score is greater than the dynamic threshold, it means that it is the same person, and if the compared score is less than the dynamic threshold, it means that it is not the same person, and further verification is required.

The adjustment formula of the dynamic threshold is:

dyScore=score/idFacts-(minScore-maxScore)/idInterval where,

idFacts: the reference factor for different years of ID cards; the reference factor for ten years is 1; the reference factor for 20 years is 1.01; the reference factor for 30 years is 1.02;

idInterval: The number of years of the ID card, the value of the ten-year validity period is 2*10 - the processing period of the ID card; the 20-year period is 20*2 - the processing period of the ID card; the long-term value is 30*2 - the processing period of the ID card;

score: fixed score, the fixed score using the algorithm is the threshold value of 68;

minScore: the minimum passing score, the minimum passing score of the algorithm is 68, that is, as long as it is greater than 68 by default, it is considered the threshold of the same person;

maxScore: The maximum score for determining that it is not the same person: the score is 66, that is, as long as the score is less than 66, it is determined that it is not the same person at all.

dyScore: Dynamic threshold.

Due to the adoption of the above technical solutions, it is possible to obtain the already-issued time of the ID card; and dynamically adjust the threshold for the comparison of witnesses and ID cards according to the already-issued time and the validity period of the ID card. Solve the occurrence of the failure of the comparison caused by setting a fixed threshold; increase the pass rate of the witness comparison can improve the check-in efficiency of the hotel; increase the passenger's check-in experience.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a flowchart of a method for setting a dynamic face comparison threshold based on the validity period of an ID card according to an exemplary embodiment;

Fig. 2 is the dynamic threshold value adjustment step of the present invention;

FIG. 3 shows a specific embodiment of a method for setting a dynamic face comparison threshold based on the validity period of an ID card according to an exemplary embodiment.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with some aspects of the invention as recited in the appended claims.

1 is a flow chart of a method for setting a dynamic face comparison threshold based on the validity period of an ID card according to an exemplary embodiment; as shown in FIG. 1 , the present invention provides a dynamic face comparison threshold setting based on the validity period of an ID card method,

The time for obtaining the ID card has been issued;

Dynamically adjust the threshold of witness-to-certificate comparison based on the time of obtaining the certificate and the validity period of the ID card.

The present invention dynamically adjusts the threshold value of the comparison of witnesses according to the difference between the processing time of the ID card and the actual one, thereby reducing the number of comparison failures;

In the present embodiment, the steps of calculating the time for which the certificate has been issued are as follows:

Step 1: By swiping the ID card of the person being verified, the limited period of obtaining the ID card is obtained.

Step 2: Obtain the validity period of the ID card according to the start time and end time of the limited period.

Step 3: According to the time when the verified person swiped the ID card and the start time of the limited period, calculate the time for the certificate to be issued.

As a preferred implementation manner, this embodiment also includes a human-card comparison module, and the human-card comparison module is used to obtain an ID card photo and a face photo collected on-site. In addition, the human-card comparison module is also used to compare the obtained ID photo with the face photo collected on the spot.

As a preferred implementation, this example also includes a time analysis module and a dynamic threshold adjustment module; the time analysis module obtains the current system time according to the limited period information of the ID card obtained by the ID card analysis module and the current system time.

Calculate the valid time of the ID card for 20 years, such as: (2037-2017=20) and the time when the ID card has been issued:

Among them, the validity time = the end time of the validity period of the ID card - the start time of the validity period of the ID card, such as: 2037-2017 = 20

The time when the certificate has been issued = system time - the start time of the validity period of the ID card, such as: 2018-2017 = 1

Dynamic threshold adjustment module: According to the valid time of the ID card obtained by the time analysis module and the time when the certificate has been issued, the dynamic threshold under the valid time and the time when the certificate has been issued is calculated.

The dynamic threshold is calculated by the function (the valid time of the ID card, the time that the certificate has been issued, the fixed threshold of the algorithm); the fixed threshold of the algorithm is that the algorithm does not consider other factors, and the score is greater than or equal to the same person and less than the threshold. Then it is determined that it is not the fixed score of the same person; the deviation coefficient under this condition is calculated according to the valid time of the ID card and the time when the certificate has been issued, and the dynamic threshold is based on the calculated deviation coefficient and the fixed threshold;

As shown in Figure 2, the dynamic threshold adjustment in this embodiment adopts the following steps:

The time analysis module calculates the valid time of the ID card according to the limited period information of the ID card obtained by the ID card analysis module and the current system time;

The dynamic threshold adjustment module calculates the valid time and the dynamic threshold under the certificated time according to the valid time of the ID card and the certificated time obtained by the time analysis module.

Further, if the compared score is greater than the dynamic threshold, it means that it is the same person, and if the compared score is less than the dynamic threshold, it means that it is not the same person, and further verification is required.

If the score after comparison is greater than the dynamic threshold, it means it is the same person; if the score after comparison is less than the dynamic threshold, it means that it is not the same person, and further verification is required.

The adjustment formula of the dynamic threshold in this embodiment is:

dyScore=score/idFacts-(minScore-maxScore)/idInterval where,

idFacts: the reference factor for different years of ID cards; the reference factor for ten years is 1; the reference factor for 20 years is 1.01; the reference factor for 30 years is 1.02;

idInterval: The number of years of the ID card, the value of the ten-year validity period is 2*10 - the processing period of the ID card; the 20-year period is 20*2 - the processing period of the ID card; the long-term value is 30*2 - the processing period of the ID card;

score: fixed score, the fixed score using the algorithm is the threshold value of 68;

minScore: the minimum passing score, the minimum passing score of the algorithm is 68, that is, as long as it is greater than 68 by default, it is considered the threshold of the same person;

maxScore: The maximum score for determining that it is not the same person: the score is 66, that is, as long as the score is less than 66, it is determined that it is not the same person at all.

dyScore: Dynamic threshold.

FIG. 3 shows a specific embodiment of a method for setting a dynamic face comparison threshold based on the validity period of an ID card according to an exemplary embodiment. As shown in Figure 3, the system part used in the setup scheme is first introduced:

The composition of the system (including at least the following parts): ID card reader device, camera, algorithm interface (person-card comparison module) and network; wherein

ID card reader device: responsible for the collection of ID card information, the collected information includes the text information and image information of the certificate. Camera: Responsible for collecting face photos on site. Algorithm interface: responsible for the comparison of ID photos and face photos. The network is responsible for the transmission of data.

The following is a detailed description of the dynamic witness comparison threshold setting process:

S1. The person being verified swipes the ID card

S2. The validity period of the ID card, such as; 2006.07.18-2026.07.18

S3. Obtain the validity period according to the start time and end time of the validity period, such as twenty years.

S4. According to the current card swiping time and the start time of the validity period, calculate the time of the card application

S5. Calculate the dynamic threshold within the validity period according to the face threshold according to the valid time of S3 and the certified time of S4.

S6. Collect live face photos through the camera

S7. According to the obtained ID photo and the face photo collected on site, call the face comparison interface through http or sdk to compare;

If the score is greater than the dynamic threshold, it means the same person

If the score is less than the dynamic threshold, it means that it is not the same person, and further verification is required.

It should be added that: threshold: whether it is the critical point of the score of the same person: for example, the threshold of the current algorithm is 68 without considering the age of the ID card; if the score is greater than or equal to 68, it is considered to be the same person; if the score is less than 68, it is judged not to be same person;

For example, a person's ID card processing time is 2008, and the deadline is 10; in 2015, the dynamic threshold at this time is:

dyScore=68/1-(68-66)/(2*10-(2015-2008))=67.8. At this time, as long as the score is greater than or equal to 67.8, it is determined to be the same person.

Another example: the validity period of an ID card is: 2018.08.13--2038.08.13. Assuming that the card is swiped in 2020, the corresponding dynamic threshold is:

dyScore=68/1.01-(68-66)/(2*20-(2020-2018))=67.2741, at this time, as long as the score is greater than or equal to 67.2741, it is determined to be the same person.

Due to the adoption of the above technical solutions, it is possible to obtain the already-issued time of the ID card; and dynamically adjust the threshold for the comparison of witnesses and ID cards according to the already-issued time and the validity period of the ID card. It is set to solve the occurrence of the comparison failure caused by setting a fixed threshold; increasing the pass rate of the witness comparison can improve the check-in efficiency of the hotel; increase the passenger's check-in experience.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

It can be understood that, the same or similar parts in the above embodiments may refer to each other, and the content not described in detail in some embodiments may refer to the same or similar content in other embodiments.

It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for the purpose of description, and should not be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise specified, the meaning of "plurality" means at least two.

Any description of a process or method in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing a specified logical function or step of the process , and the scope of the preferred embodiments of the invention includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present invention belong.

Those skilled in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although the embodiments of the present invention have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present invention. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (8)

1. The dynamic face comparison threshold setting method based on the validity period of ID card is characterized in that: The time for obtaining the ID card has been issued; Dynamically adjust the threshold of witness-to-certificate comparison according to the time of obtaining the certificate and the validity period of the ID card; among them, the adjustment formula of the dynamic threshold is: dyScore=score/idFacts-(minScore-maxScore)/idInterval where, idFacts: the reference factor for the validity period of the ID card; the reference factor for ten years is 1; the reference factor for 20 years is 1.01; the reference factor for 30 years is 1.02; idInterval: the number of years of the ID card, the value of the ten-year validity period is 2*10-the time for the ID card to be issued; for 20 years, 20*2-the time for the ID card to be issued; for the long-term, it is 30*2-the time for the ID card to be issued; Score: fixed score, the fixed score using the algorithm is 68; minScore: The minimum passing score, the minimum passing score of the algorithm is 68, that is, as long as it is greater than 68 by default, it is considered to be the same person; maxScore: The maximum score for determining that it is not the same person: the score is 66, that is, as long as the score is less than 66, it is determined that it is not the same person at all; dyScore: dynamic threshold. 2. The dynamic face comparison threshold setting method based on the validity period of an ID card according to claim 1, is characterized in that: by swiping the ID card for the person to be checked, the limited term of the ID card is obtained. 3. The dynamic face comparison threshold setting method based on the validity period of the ID card according to claim 2, is characterized in that: obtain the validity period of the ID card according to the start time and the end time of the limited time limit. 4. The dynamic face comparison threshold setting method based on the validity period of the ID card according to claim 3, is characterized in that: according to the time when the person to be checked brushes the ID card and the start time of the limited period, the time for obtaining the certificate is calculated. 5. The method for setting a dynamic face comparison threshold based on the validity period of an ID card according to claim 1, characterized in that: obtaining an ID card photo and a face photo collected on site. 6. The method for setting a dynamic face comparison threshold based on the validity period of an ID card according to claim 5, wherein the obtained ID card photo is compared with the face photo collected on the spot. 7. the dynamic face comparison threshold value setting method based on the validity period of ID card according to any one of claims 1 to 5, is characterized in that: Obtain the limited period information of the ID card and obtain the current system time to calculate the validity period of the ID card; The obtained ID card validity period and the certificate application time are used to calculate the dynamic threshold under the validity period and the certificate application time. 8. the dynamic face comparison threshold value setting method based on the validity period of ID card according to claim 7, is characterized in that: if the score after comparison is greater than the dynamic threshold value then explain is the same person, if the score after comparison is less than dynamic The threshold value indicates that it is not the same person, and further verification is required.

Images