CN115661896A

CN115661896A - Dynamic identity confirmation method, system, electronic equipment and storage medium

Info

Publication number: CN115661896A
Application number: CN202211286564.7A
Authority: CN
Inventors: 陈颖
Original assignee: Zhongke Hongtuo Suzhou Intelligent Technology Co ltd
Current assignee: Zhongke Hongtuo Suzhou Intelligent Technology Co ltd
Priority date: 2022-10-20
Filing date: 2022-10-20
Publication date: 2023-01-31

Abstract

The application discloses a dynamic identity confirmation method, a dynamic identity confirmation system, electronic equipment and a storage medium, and relates to the technical field of face recognition. The method comprises the following steps: sending the first face authentication result to a server side for bottom base authentication to obtain a bottom base authentication result, and obtaining and storing an identity recognition threshold interval and a unique identity of a user according to the first face authentication result, the second face authentication result and the bottom base authentication result; judging the identity of the face image according to the full identity recognition threshold interval in the base library and the corresponding unique identity to obtain a first judgment result; performing face authentication on the user for the third time, and sending the face of the user to the server to confirm the identity of the user to obtain a second judgment result; and judging whether the user is legal or not according to the first judgment result and/or the second judgment result. The method and the device can establish the exclusive threshold interval for each user, and prevent illegal entrant personnel from leaving the closed area.

Description

Dynamic identity confirmation method, system, electronic equipment and storage medium

Technical Field

The present application relates to the field of face recognition technologies, and in particular, to a method, a system, an electronic device, and a storage medium for dynamically confirming an identity.

Background

Airport security inspection is a series of security inspection measures for passengers to enter an isolation area after boarding procedures are finished, and essentially ensures aviation security and passenger security. The identification of personnel, including passengers and staff, is a very important ring of security. At present, most airports adopt a mode that a worker checks a person to be detected and an identity document held by the person on site to determine the real identity of the person. However, such a method is not efficient, costly, and poor in passenger experience, but cannot detect and prompt an unauthorized person (an unauthorized person is a person who enters the area without security inspection by an unauthorized method such as crossing the fence).

The security system is called as a safety protection system, the subsystems of the security system comprise a video security monitoring system, an intrusion alarm system, an access control system and the like, and the purpose of maintaining social public safety can be achieved through the combination or the set of a plurality of subsystems. The entrance and exit control system comprises an identity authentication system for performing identity authentication on the entrance and exit personnel and an access control system for controlling the entrance and exit to be opened and closed, the identity of the entrance and exit personnel is authenticated through the identity authentication system, and when the authentication is passed, the access control system opens the entrance and exit for the passage of the personnel passing the identity authentication. The face recognition is based on the fact that the face of a person who performs identity verification is compared with the face collected in advance, when the matching degree is larger than a preset value, the person is considered to pass the identity verification, otherwise, the person is considered not to pass the identity verification, and in order to guarantee the accuracy of the identity verification, the numerical value of the preset value is often set to be large, so that an illegal entrant cannot be dynamically and accurately recognized.

Disclosure of Invention

In order to solve at least one of the problems mentioned in the background art, the present application provides a method, a system, an electronic device, and a storage medium for dynamically confirming an identity, which can establish a dedicated threshold interval for each user to prevent an illegal entrant person from leaving an enclosed area.

The embodiment of the application provides the following specific technical scheme:

in a first aspect, a dynamic identity confirmation method is provided, which is applied to a dynamic identity confirmation system, where the dynamic identity confirmation system includes an entry authentication end, an exit authentication end, a dynamic authentication end of a closed area formed between the entry and the exit, and a service end, and the method includes:

sending the identity information of the user to the server through the entrance identity verification end for identity verification, and if the user passes the identity verification, performing first face authentication on the user through the entrance identity verification end to obtain a first face authentication result;

after a first preset time interval, performing second face authentication on the user through the entrance identity verification end to obtain a second face authentication result;

sending the first face authentication result to the server through the entrance identity verification end for bottom base authentication to obtain a bottom base authentication result, and obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the bottom base authentication result;

capturing a face image in the closed area in real time through the dynamic verification end, sending the face image to the server end for dynamic identity authentication, and judging the identity of the face image according to the whole identity recognition threshold interval in the base and the corresponding unique identity to obtain a first judgment result;

performing face authentication on the user for the third time through the export identity verification end, sending the face of the user to the server end, and confirming the identity of the user according to the total identity recognition threshold interval in the base and the corresponding unique identity to obtain a second judgment result;

and judging whether the user is a legal identity or not by the server side according to the first judgment result and/or the second judgment result.

Further, the first face authentication result includes a first face authentication score, and after the interval of the first preset time, the second face authentication is performed on the user through the entrance identity verification end, and before a second face authentication result is obtained, the method further includes:

judging whether the first face authentication score is larger than a first face comparison threshold value or not;

and if the first face authentication score is smaller than a first face comparison threshold value, the first face authentication result is authentication failure, and the current user is refused to pass through the entrance end.

Further, the sending the first face authentication result to the server through the entrance identity verification end for bottom base authentication to obtain a bottom base authentication result, and obtaining and storing the user's identity recognition threshold interval and unique identity according to the first face authentication result, the second face authentication result and the bottom base authentication result, includes:

sending the first face authentication result to the server through the entrance identity verification end, judging whether the current user is a first user to be put in storage, and matching with the full face of the server bottom base to perform bottom base authentication to obtain a bottom base authentication result;

obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the bottom base authentication result;

the identification threshold interval comprises a minimum identification sub-threshold and a maximum identification sub-threshold.

Further, if the base authentication result includes that the current user is the first user to enter the database, the obtaining and storing the identity recognition threshold interval and the unique identity of the user according to the first face authentication result, the second face authentication result and the base authentication result includes:

assigning the minimum identity recognition sub-threshold value in the identity recognition threshold value interval of the current user as a bottom base public minimum threshold value;

assigning the maximum identity recognition sub-threshold value of the identity recognition threshold value interval of the current user to be a second face authentication score obtained according to the first face authentication result and the second face authentication result;

the second face authentication score is used for describing the closeness degree of the first face authentication result and the second face authentication result.

Further, if the base authentication result includes that the current user is not the first user to enter the base, the base authentication is performed by matching with the full human face of the base of the server, so as to obtain a base authentication result, including:

respectively carrying out face matching on the current user and all users of the server side base to obtain a face recognition score of each base user and corresponding identity information of each base user;

judging whether the face recognition scores of each bottom library user are smaller than the minimum identity recognition sub-threshold corresponding to each bottom library user and smaller than the existing minimum identity recognition sub-threshold of the current user;

and if the face identification scores of each user in the bottom library are smaller than the minimum identity identification sub-threshold corresponding to each user in the bottom library and smaller than the existing minimum identity identification sub-threshold of the current user, assigning the minimum identity identification sub-threshold of the current user to be the public minimum threshold of the bottom library, and assigning the maximum identity identification sub-threshold of the current user to be a second face identification score obtained according to the first face identification result and the second face identification result.

Further, if the face recognition score of any one of the users in the base repository is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the base repository, the obtaining of the authentication result in the base repository further comprises:

dynamically adjusting the minimum identity recognition sub-threshold corresponding to the basement user according to the average value of the face recognition score corresponding to the basement user and the maximum identity recognition sub-threshold corresponding to the basement user;

if the face recognition score of any user in the bottom database is greater than or equal to the existing minimum identity recognition sub-threshold of the current user, the method further comprises the following steps:

and dynamically adjusting the minimum identity recognition sub-threshold of the current user according to the face recognition score corresponding to the bottom library user and the average value of the maximum identity recognition sub-threshold of the current user.

Further, the base library authentication further includes:

judging whether the face recognition score of any one bottom library user is greater than or equal to the maximum identity recognition sub-threshold corresponding to the bottom library user;

if the face recognition score of any one of the base users is greater than or equal to the maximum identity recognition sub-threshold corresponding to the base user, the obtaining of the base authentication result further comprises:

and refusing the current user to enter a service end bottom library and refusing the current user to pass through an entrance end.

Further, the first determination result includes at least one of that the face recognition score of only one face image and a user in the basement is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the basement, that the face recognition score of two or more face images and the user in the same basement is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the basement, and that the face recognition score of a face image and a user in any basement is less than the minimum identity recognition sub-threshold corresponding to the user in the basement.

Further, if the first determination result indicates that two or more face images and the face recognition score of the user in the same base bank are greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the base bank, after the first determination result is obtained, the method further includes:

and dynamically adjusting the minimum identity recognition sub-threshold corresponding to the users in the bottom database according to the two or more face images and the face recognition scores of the users in the same bottom database to obtain an adjusted identity recognition threshold interval corresponding to the users in the bottom database.

In a second aspect, a dynamic identity confirmation system is provided, the system including:

the entrance identity verification end is used for sending the identity information of the user to the server end for identity verification of the server end, and if the user passes the identity verification, the entrance identity verification end is also used for carrying out first face authentication on the user to obtain a first face authentication result;

the entrance identity verification end is also used for carrying out secondary face authentication on the user after a first preset time interval to obtain a second face authentication result;

the entrance identity verification end is further used for sending the first face authentication result to the server end for the server end to perform bottom base authentication to obtain a bottom base authentication result, and the server end is used for obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the bottom base authentication result;

the dynamic verification end is used for capturing a face image in a closed area in real time and sending the face image to the server end for the server end to perform dynamic identity authentication, and the server end is used for judging the identity of the face image according to the whole identity recognition threshold interval in the base and the corresponding unique identity to obtain a first judgment result;

the export identity verification end is used for carrying out face authentication on the user for the third time, and sending the face of the user to the server end so that the server end can confirm the identity of the user according to the total identity recognition threshold interval in the base library and the corresponding unique identity to obtain a second judgment result;

the server is further used for judging whether the user is legal or not according to the first judgment result and/or the second judgment result through the server.

In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for dynamically confirming identity when executing the computer program.

In a fourth aspect, a computer-readable storage medium is provided, which stores computer-executable instructions for performing the method for dynamically validating an identity.

The embodiment of the application has the following beneficial effects:

the dynamic identity confirmation method, the dynamic identity confirmation system, the electronic equipment and the storage medium provided by the embodiment of the application can establish an exclusive threshold interval for each user and prevent illegal entrants from leaving a closed area; the method can also support the real-time snapshot of the face image in the closed area, capture the similar face or the illegal invaded face in real time and prevent the similar face or the illegal invaded face from leaving the closed area; meanwhile, the identity recognition threshold interval corresponding to the user can be dynamically adjusted according to different recognition conditions, so that the accuracy of identity verification can be guaranteed, and a legal user or an illegal invasive user can be accurately recognized.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 shows a general flowchart of a dynamic identity confirmation method provided in an embodiment of the present application;

fig. 2 is a schematic diagram illustrating an architecture of a dynamic identity verification system provided in an embodiment of the present application;

FIG. 3 illustrates an exemplary system that can be used to implement the various embodiments described in this application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the present application clearer, 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.

It should be understood that throughout the description and claims of this application, unless the context clearly requires otherwise, the words "comprise", "comprising", and the like, are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including but not limited to".

It will be further understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, the meaning of "a plurality" is two or more unless otherwise specified.

Example one

The application provides a dynamic identity confirmation method, which is applied to a dynamic identity confirmation system, wherein the dynamic identity confirmation system comprises an entrance identity verification end, an exit identity verification end, a dynamic verification end of a closed area formed between an entrance and an exit and a service end, and referring to fig. 1, the method comprises the following steps:

s1, identity information of a user is sent to a server side through an entrance identity verification end for identity verification, if the user passes the identity verification, first face authentication is carried out on the user through the entrance identity verification end, and a first face authentication result is obtained;

s2, after a first preset time interval, performing second face authentication on the user through the entrance identity authentication end to obtain a second face authentication result;

s3, sending the first face authentication result to a server side through an entrance identity verification end for bottom base authentication to obtain a bottom base authentication result, and obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the bottom base authentication result;

s4, capturing the face image in the closed area in real time through a dynamic verification end, sending the face image to a server end for dynamic identity authentication, and judging the identity of the face image according to a full identity recognition threshold interval in a base library and a corresponding unique identity to obtain a first judgment result;

s5, conducting third face authentication on the user through the export identity authentication end, sending the face of the user to the server end, confirming the identity of the user according to the full identity recognition threshold interval in the base and the corresponding unique identity, and obtaining a second judgment result;

and S6, judging whether the user is legal or not through the server according to the first judgment result and/or the second judgment result.

Specifically, taking an airport as an example, the area to be inspected in the airport is a relatively closed space, provided with hard isolation devices such as isolation walls and the like, and provided with an inlet channel and an outlet channel. Illustratively, a self-service verification gate is arranged at an entrance of the enclosed space, namely, the self-service verification gate serves as the entrance identity verification end and is used for verifying tickets and testimonies of airport passengers and establishing and managing a passenger exclusive identity identification threshold interval; a face verification gate machine is arranged at an exit of the closed space, namely, the face verification gate machine is used as the exit identity verification end and is used for carrying out face recognition verification on airport passengers according to a special identity recognition threshold interval, so that the verification of people with similar faces fails and the illegal invasion is prevented from leaving the closed area; one or more camera sensors supporting face verification are arranged in the closed space, face verification of the whole closed space is covered, the faces of all people in the whole closed space can be captured in real time so as to facilitate face recognition, and therefore the exclusive identity recognition threshold interval of a passenger can be dynamically adjusted.

Illustratively, when an airport passenger arrives at a self-service verification gate deployed at an entrance, the entrance self-service verification gate (entrance identity verification end) is used for personal ticket verification, the passenger can send the identity information of the current passenger to a service end in a mode of swiping a certificate (identity card, passport and the like) or scanning a code (two-dimensional code or other verification codes providing identity information), whether the passenger is a valid air ticket (associated with passenger check-in information) is verified through the service end, and if the personal ticket verification fails, the passenger is rejected to pass through the entrance gate. If the testimony ticket passes the verification, the first face authentication is carried out on the passenger user through the entrance identity verification end, the face of the user which is taken by the first snapshot and the certificate photo in the identity information are sent to the face recognition server side to carry out testimony comparison, and a first testimony face authentication result is obtained.

In some embodiments, the first facial authentication result may include a first facial authentication score, based on which, prior to S2, the method further comprises:

101. judging whether the first face authentication score is larger than a first face comparison threshold value or not;

102. and if the first face authentication score is smaller than the first face comparison threshold, the first face authentication result is authentication failure, and the current user is refused to pass through the entrance end.

Specifically, the face recognition server performs one-to-one testimony comparison, if the first face authentication score is smaller than a first face comparison threshold value, the testimony comparison verification fails, and the current user is directly refused to pass through an entrance-end self-service verification gate machine without passing the testimony comparison verification; if the first face authentication score is larger than or equal to the first face comparison threshold, the verification of the witness comparison is successful, and face verification in the subsequent steps can be performed. The first face comparison threshold is a standard value/empirical value preset by the server, and may also be adjusted according to the actual recognition service scene, so that the present invention is not limited herein.

Illustratively, after a first preset time interval (e.g., 3 seconds, 5 seconds, etc.), performing a second face snapshot on the current user, and performing a second face authentication on the user to obtain a second face authentication result. Before a user enters a service end bottom library, a default exclusive identity recognition threshold interval of the user is formed in advance, firstly, a face snapshot for the first time in a first face authentication result is sent to a service end to carry out bottom library full authentication, then, the final identity recognition threshold interval and the unique identity of the user are obtained through comprehensive processing and judgment according to the first face authentication result, a second face authentication result and a bottom library authentication result, and the final identity recognition threshold interval and the unique identity of the user are stored and warehoused. In the closed space, a camera sensor, namely a dynamic verification end, covering the closed space can be used for capturing a face image in the closed area in real time, the face image is sent to a server for dynamic identity authentication, the identity of the face image is judged according to a full identity recognition threshold interval in a base and a corresponding unique identity, whether the face image is a unique user entering the base of the server is judged, and if the face image is not the unique user, a special identity recognition threshold interval related to the user can be dynamically adjusted; if the result is not hit in the server-side base, the identification of the unknown face image which is not stored is indicated, the unknown face image can be marked as an illegal intrusion object, and an alarm is given to output a first judgment result. Similarly, when the user arrives at the exit, the face identification gate (namely the exit identity verification end) arranged at the exit can be used for carrying out face authentication for the third time, the face of the user is sent to the server for the third time, the identity of the user is confirmed according to the full identity recognition threshold interval in the base and the corresponding unique identity, whether the face verification score for the third time is in the identity recognition threshold interval of a certain user in the base is judged, if yes, the user is identified as the corresponding user, the unique identity and other identity information of the corresponding user are marked to confirm the identity of the user, if not, the user can be marked as an illegal intrusion object, and a second judgment result is output by alarming. Whether an illegal invading object exists in the closed area can be judged according to the first judgment result so as to make a targeted measure in time; and judging whether the user to pass through the outlet is legal or not through the second judgment result, and verifying again to prevent the illegal invasion object from leaving the closed area.

In some embodiments, S3 comprises:

s31, sending a first face authentication result to a server through an entrance identity verification end, judging whether a current user is a first user to be put in a warehouse or not, and matching with the full face of a server bottom warehouse to perform bottom warehouse authentication to obtain a bottom warehouse authentication result;

s32, obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the bottom base authentication result;

the identity recognition threshold interval comprises a minimum identity recognition sub-threshold and a maximum identity recognition sub-threshold.

Specifically, the default dedicated identification threshold interval may be preset to T (T) before the current user enters the service end vault _L ,T _H ) Firstly, whether the current user is the first user is put in a warehouse or not is judged, namely whether data exist in the current base or not is judged.

In some embodiments, if the result of the base library authentication includes that the current user is the first user to be put in the library, S32 includes:

s321, assigning the minimum identity recognition sub-threshold value in the identity recognition threshold value interval of the current user as a public minimum threshold value of a bottom library;

s322, assigning the maximum identity recognition sub-threshold value of the identity recognition threshold value interval of the current user to be a second face authentication score obtained according to the first face authentication result and the second face authentication result;

and the second face authentication score is used for describing the similarity of the first face authentication result and the second face authentication result.

Specifically, the current user is the first user to put in storage, and the minimum identity recognition sub-threshold T in the identity recognition threshold interval of the current user _L Can be set as the public minimum threshold value T of the bottom library _C The common minimum threshold value T _C Can be a standard value/an empirical value, can also be adjusted according to an actual service scene/a face recognition scene, and can preset T _C And was 0.85. And then determining the maximum identity recognition sub-threshold of the user according to the first face authentication result and a second face authentication score obtained from the second face authentication result, so that an identity recognition threshold interval of the user can be formed. For example, if there is no data in the current service-side base, passenger a is the first passenger to enter the enclosed space, and the proximity between the first face authentication result and the second face authentication result of passenger a is 0.95, then passenger a has the exclusive identity threshold interval T _A (T _AL ,T _AH ) Is T _A (0.85,0.95)。

In some embodiments, if the result of the base library authentication includes that the current user is not a first-order user, S31 includes:

s311, respectively carrying out face matching on the current user and all users of the server side base to obtain a face recognition score of each base user and corresponding identity information of each base user;

s312, judging whether the face recognition scores of each user in the bottom database are smaller than the minimum identity recognition sub-threshold corresponding to each user in the bottom database and smaller than the existing minimum identity recognition sub-threshold of the current user;

and S313, if the face recognition scores of each user in the bottom library are smaller than the minimum identity recognition sub-threshold corresponding to each user in the bottom library and smaller than the existing minimum identity recognition sub-threshold of the current user, assigning the minimum identity recognition sub-threshold of the current user as a public minimum threshold of the bottom library, and assigning the maximum identity recognition sub-threshold of the current user as a second face authentication score obtained according to the first face authentication result and the second face authentication result.

Specifically, if the current user is not the first user, there are four cases, that is, the face recognition score of each user in the bottom library is smaller than the minimum identity recognition sub-threshold corresponding to each user in the bottom library and smaller than the existing minimum identity recognition sub-threshold of the current user, the face recognition score of any user in the bottom library is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the bottom library, the face recognition score of any user in the bottom library is greater than or equal to the existing minimum identity recognition sub-threshold of the current user, and the face recognition score of any user in the bottom library is greater than or equal to the maximum identity recognition sub-threshold corresponding to the user in the bottom library. And when the face identification score of each bottom library user is smaller than the minimum identity identification sub-threshold corresponding to each bottom library user and smaller than the existing minimum identity identification sub-threshold of the current user, directly assigning the minimum identity identification sub-threshold of the current user as a bottom library public minimum threshold, and assigning the maximum identity identification sub-threshold of the current user as a second face identification score obtained according to the first face identification result and the second face identification result, namely, executing the same scheme with the first-place warehousing user. Illustratively, if passenger B is not in-store by the first user, T _C 0.85, the closeness degree of the first face authentication result and the second face authentication result of the passenger B is 0.97, and the default exclusive identity recognition threshold interval T of the passenger B _B (T _BL ,T _BH ) Is T _B (0.85,0.97). The first snapshot face of the passenger B and the bottom bank face of the passenger A are subjected to face recognition to obtain a score of 0.81, which is lower than the exclusive minimum identity recognition sub-threshold value of 0.85 of the passenger A and lower than the exclusive existing of the passenger BMinimum identity sub-threshold 0.85. Similarly, if the face recognition scores of the passenger B and any other basement user are both less than the exclusive minimum identity recognition sub-threshold of the corresponding basement user and less than 0.85 of the exclusive existing minimum identity recognition sub-threshold of the passenger B, it indicates that the face recognition scores of the passenger B and each basement user are both less than the minimum identity recognition sub-threshold of the corresponding basement user and both less than the own existing minimum identity recognition sub-threshold of the passenger B, and the actual identity recognition threshold interval of the passenger B is T _B (0.85,0.97)。

In some embodiments, if the face recognition score of any one of the users in the base repository is greater than or equal to the minimum identity sub-threshold of the corresponding user in the base repository, S31 further includes:

s314, dynamically adjusting the minimum identity recognition sub-threshold of the corresponding bottom library user according to the face recognition score of the corresponding bottom library user and the average value of the maximum identity recognition sub-thresholds of the corresponding bottom library user;

if the face recognition score of any base user is greater than or equal to the existing minimum identity recognition sub-threshold of the current user, the step S31 further comprises:

and S315, dynamically adjusting the minimum identity recognition sub-threshold of the current user according to the average value of the face recognition score of the corresponding user in the bottom database and the maximum identity recognition sub-threshold of the current user.

Specifically, if the face recognition score of any one of the users in the base repository is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the base repository, it is assumed that the face recognition score T1 of the current user and the user 1 in the base repository is greater than or equal to the minimum identity recognition sub-threshold T of the user 1 in the base repository _1L Then the user 1 in the basement needs to dynamically adjust the minimum id sub-threshold T _1L Is adjusted to

Meanwhile, if the face recognition score T1 of the current user and the bottom library user 1 is smaller than the existing minimum identity recognition sub-threshold of the current user, the minimum identity recognition sub-threshold of the current user is kept unchanged, otherwise, the minimum identity recognition sub-threshold of the current user is kept unchanged

Finally forming a current user identification threshold interval T (T) _L ,T _H ). Illustratively, passenger B is a passenger that enters the enclosure other than the first passenger, T _C 0.85, the first face authentication result and the second face authentication result of passenger B are close to each other by 0.97, and the default exclusive id threshold interval T of passenger B is set to _B (T _BL ,T _BH ) Is T _B (0.85,0.97). The first snapshot face of the passenger B and the face of the bottom library user A are identified to obtain a score of 0.89, and the exclusive identity identification threshold interval T of the bottom library user A _A (0.85, 0.95), if the minimum ID sub-threshold is greater than the minimum ID sub-threshold exclusive to the basement user A by 0.85, the minimum ID sub-threshold of the basement user A is dynamically adjusted to T _A (0.92,0.95). Meanwhile, if the face recognition score 0.89 is greater than the minimum identity recognition sub-threshold of the passenger B by 0.85, dynamically adjusting the minimum identity recognition sub-threshold of the passenger B, wherein the adjusted identity recognition threshold interval is T _B (0.92,0.97). Assuming that the passenger B and the user C in the basement perform face recognition to obtain a score of 0.89 which is greater than the minimum exclusive identity recognition sub-threshold of the passenger C by 0.85, and the minimum exclusive identity recognition sub-threshold of the passenger C is dynamically adjusted, wherein the adjusted identity recognition threshold interval is T _C (0.92,0.97). Meanwhile, if the score 0.89 is smaller than the minimum identity sub-threshold of the passenger B, which is already 0.92, the minimum identity sub-threshold of the passenger B is not adjusted.

In some embodiments, the base authentication further comprises:

judging whether the face recognition score of any bottom library user is greater than or equal to the maximum identity recognition sub-threshold of the corresponding bottom library user;

if the face recognition score of any one of the base users is greater than or equal to the maximum identity recognition sub-threshold of the corresponding base user, obtaining the base authentication result further comprises:

and refusing the current user to enter the service end bottom library and refusing the current user to pass through the entrance end.

Specifically, if the face recognition scores of the current user and any one of the users in the bottom bank are greater than or equal to the maximum identity recognition sub-threshold of the user in the corresponding bottom bank, the current user is rejected from entering the bottom bank, and the current user can be arranged to go through other channels without entering a closed area, so that the current user or the user in the corresponding bottom bank is prevented from being replaced. For example, assuming that the first snapshot face of the passenger B and the base face identification score of the base user a are 0.98 and greater than 0.95 of the maximum exclusive identity sub-threshold of the base user a, the passenger B and the related information thereof are rejected from entering the server base. Similarly, if the face of the passenger B captured for the first time and the face recognition score of any other user in the bottom bank are greater than or equal to the maximum identity recognition sub-threshold of the corresponding user in the bottom bank, the passenger B is rejected. Meanwhile, the passengers B are refused to pass through the entrance, the passengers B are prevented from entering the closed space, and other user channels can be arranged to be removed, so that the passengers B or other related passengers are prevented from being replaced.

In some embodiments, the first determination result includes at least one of that the face recognition score of only one face image and the user in the same basement is greater than or equal to the minimum identity recognition sub-threshold of the user in the corresponding basement, that the face recognition score of two or more face images and the user in the same basement is greater than or equal to the minimum identity recognition sub-threshold of the user in the corresponding basement, and that the face recognition score of the face image and any user in the basement is less than the minimum identity recognition sub-threshold of the user in the corresponding basement.

Specifically, if the face recognition score of only one face image and the base user is greater than or equal to the minimum identity recognition sub-threshold of the corresponding base user, that is, it indicates that there is only one exclusive identity recognition threshold interval of the user in the server base and the unique identity is matched with the face image, the user of the matched face image is the base user. Illustratively, passenger A has a threshold interval of T for exclusive identification _A (0.85,0.95). The face image to be captured and the face recognition score of the user in the passenger A base library are 0.91, and the face images to be captured and the face recognition scores of the other face images to be captured are all smaller than 0.85, namely, the owner of the face image with the recognition score of 0.91, namely the passenger A, has a unique identity recognition threshold interval and a corresponding unique identity so as to confirm the identity of the owner.

Specifically, if the face recognition scores of the face image and any one of the base library users are smaller than the minimum identity recognition sub-threshold of the corresponding base library user, that is, the face to be snapshotted is not matched with the corresponding user in the server base library, the face image is recognized as an unfamiliar face image, the face image can be marked as illegal intrusion, the user is judged to be illegal identity, and an alarm or an auxiliary alarm is given without adjusting the identity recognition threshold interval.

In some embodiments, if the first determination result is that there are two or more face images and the face recognition score of the user in the same base bank is greater than or equal to the minimum identity recognition sub-threshold of the user in the corresponding base bank, after obtaining the first determination result, the method further includes:

201. and dynamically adjusting the minimum identity recognition sub-threshold corresponding to the users in the bottom library according to the face images of two or more than two users in the same bottom library and the face recognition scores of the users in the same bottom library to obtain an adjusted identity recognition threshold interval corresponding to the users in the bottom library.

Specifically, if the face recognition scores of two or more face images and the same base user are greater than or equal to the minimum identity recognition sub-threshold of the corresponding base user, it indicates that the snapped passengers with two or more different faces can match the same base user in the server base, that is, the face images are "similar faces". Illustratively, taking two face images taken by snap shots as an example, the face recognition scores of users in the same base library are respectively T ₁ 、T ₂ And T is ₁ <T ₂ The passenger 1 and the passenger 2 are respectively corresponding to each other, and according to the principle that the same face recognition score should be larger than different face recognition scores of different people, the passenger 2 is recognized as the user of the bottom bank, and the passenger 1 is marked as the approximate face of the user of the bottom bank. In order to prevent the passenger 1 from being able to successfully recognize the face through the passenger 2 bank, a unique identification threshold section T (T) corresponding to the passenger 2 is required _L ,T _H ) And performing dynamic adjustment. At this time, if T _H <T ₂ Then, then

If not, then the mobile terminal can be switched to the normal mode,

exemplary, if T ₁ ＝0.87，T ₂ =0.91, passenger a is the user of the identification basement, the identification threshold interval T _A (0.85,0.95)。T _H >T ₂ Then, then

Adjusted identity recognition threshold interval T' _A (0.89，0.95)。

Specifically, when the user arrives at the exit, the third face authentication is required, the full-matching verification is also carried out on the face of the user in the corresponding bottom library, whether or not one and only one face recognition score of the user in the corresponding bottom library falls within the identity recognition threshold interval of the user in the corresponding bottom library is judged, and if yes, the gate of the exit end is opened to allow the current user to pass through; otherwise, the label is "similar to human face" or "illegal intrusion", which is the same as the above-mentioned labeling method and rule, so it is not repeated here, at this time, the exit end gate does not open the door and refuse to release, and sends out alarm or auxiliary alarm to inform the relevant staff to process.

In the embodiment, an exclusive threshold interval can be established for each user, so that illegal entrants are prevented from leaving a closed area; the method can also support the real-time snapshot of the face image in the closed area, capture the similar face or the illegal invaded face in real time and prevent the similar face or the illegal invaded face from leaving the closed area; meanwhile, the identity recognition threshold interval corresponding to the user can be dynamically adjusted according to different recognition conditions, so that the accuracy of identity verification can be guaranteed, and a legal user or an illegal invasive user can be accurately recognized.

It should be noted that the terms "S1", "S2", etc. are used for descriptive purposes only, are not intended to refer specifically to an order or sequential meaning, nor are they intended to limit the present application, but are merely used for convenience in describing the method of the present application and are not to be construed as indicating the order of the steps. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present application.

Example two

Corresponding to the embodiment, the application also provides an identity dynamic confirmation system which comprises an entrance identity verification end, an exit identity verification end, a dynamic verification end of a closed area formed between the entrance and the exit and a server.

The system comprises an entrance identity verification end, a server end and a user identity authentication end, wherein the entrance identity verification end is used for sending identity information of a user to the server end so as to be used for identity verification of the server end, and if the user passes the identity verification, the entrance identity verification end is also used for carrying out first face authentication on the user to obtain a first face authentication result;

and the server is also used for judging whether the user is a legal identity or not according to the first judgment result and/or the second judgment result through the server.

Specifically, referring to fig. 2, the entrance authentication end may be an entrance personal identification ticket authentication gate, the exit authentication end may be an exit face authentication gate, an enclosed space is formed between the entrance personal identification ticket authentication gate and the exit face authentication gate, one or more dynamic authentication ends are disposed in the enclosed space, and each dynamic authentication end includes a dynamic face authentication camera sensor supporting face recognition and is used for performing real-time face snapshot.

Further, the first face authentication result includes a first face authentication score, and the entrance identity verification end is further configured to determine whether the first face authentication score is greater than a first face comparison threshold; and if the first face authentication score is smaller than a first face comparison threshold value, the first face authentication result is authentication failure, and the current user is refused to pass through the entrance end.

Further, the entrance identity verification end is further configured to send the first face authentication result to the server end, and the server end is further configured to determine whether the current user is a first user to enter the library, and perform the library authentication by matching with the full face of the library at the server end to obtain a library authentication result;

the server is further used for obtaining and storing an identity identification threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result and the base authentication result; the identification threshold interval comprises a minimum identification sub-threshold and a maximum identification sub-threshold.

Further, the server is further configured to assign the minimum identity sub-threshold in the identity threshold interval of the current user as a bottom base public minimum threshold; the face recognition module is further configured to assign the maximum identity recognition sub-threshold of the current user identity recognition threshold interval to a second face authentication score obtained according to the first face authentication result and the second face authentication result; the second face authentication score is used for describing the similarity of the first face authentication result and the second face authentication result.

Further, the server is further configured to perform face matching on the current user and all users in the server base, so as to obtain a face recognition score of each base user and corresponding identity information of each base user; the identity recognition score of each user in the bottom database is also used for judging whether the face recognition score of each user in the bottom database is smaller than the minimum identity recognition sub-threshold corresponding to each user in the bottom database and smaller than the existing minimum identity recognition sub-threshold of the current user; if the face identification score of each user in the bottom library is smaller than the minimum identity identification sub-threshold corresponding to each user in the bottom library and smaller than the existing minimum identity identification sub-threshold of the current user, the server is further configured to assign the minimum identity identification sub-threshold of the current user to be the public minimum threshold of the bottom library, and assign the maximum identity identification sub-threshold of the current user to be a second face authentication score obtained according to the first face authentication result and the second face authentication result.

Further, if the face recognition score of any one of the basement users is greater than or equal to the minimum identity recognition sub-threshold corresponding to the basement user, the server is further configured to dynamically adjust the minimum identity recognition sub-threshold corresponding to the basement user according to an average of the face recognition score corresponding to the basement user and the maximum identity recognition sub-threshold corresponding to the basement user; if the face recognition score of any user in the basement is greater than or equal to the existing minimum identity recognition sub-threshold of the current user, the server is further used for dynamically adjusting the minimum identity recognition sub-threshold of the current user according to the face recognition score of the user corresponding to the basement and the average value of the maximum identity recognition sub-threshold of the current user.

Further, the server is further configured to determine whether a face recognition score of any of the users in the vault is greater than or equal to a maximum identity recognition sub-threshold corresponding to the user in the vault;

and if the face recognition score of any one of the bottom library users is greater than or equal to the maximum identity recognition sub-threshold corresponding to the bottom library user, the service end is also used for refusing the current user to enter the service end bottom library and refusing the current user to pass through the entrance end.

Further, the first determination result includes at least one of that the face recognition score of only one face image and one basement user is greater than or equal to the minimum identity recognition sub-threshold corresponding to the basement user, that the face recognition score of two or more face images and the same basement user is greater than or equal to the minimum identity recognition sub-threshold corresponding to the basement user, and that the face recognition score of a face image and any basement user is less than the minimum identity recognition sub-threshold corresponding to the basement user.

Further, if the first determination result indicates that the face recognition scores of two or more face images and the same basement user are greater than or equal to the minimum identity recognition sub-threshold corresponding to the basement user, the server is further configured to dynamically adjust the minimum identity recognition sub-threshold corresponding to the basement user according to the face recognition scores of the two or more face images and the same basement user, so as to obtain an adjusted identity recognition threshold interval corresponding to the basement user.

For the specific limitations of the above-mentioned dynamic identity confirmation system, reference may be made to the relevant limitations in the above-mentioned embodiments of the dynamic identity confirmation method, and therefore, the details are not repeated herein. All or part of the modules in the dynamic identity confirmation device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

EXAMPLE III

Corresponding to the foregoing embodiments, the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the computer program to implement the above dynamic identity verification method.

As shown in fig. 3, in some embodiments, the system can be the electronic device for the method for dynamically confirming identity in any one of the embodiments. In some embodiments, a system may include one or more computer-readable media (e.g., system memory or NVM/storage) having instructions and one or more processors (e.g., processor (s)) coupled with the one or more computer-readable media and configured to execute the instructions to implement modules to perform actions described herein.

For one embodiment, the system control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and/or any suitable device or component in communication with the system control module.

The system control module may include a memory controller module to provide an interface to the system memory. The memory controller module may be a hardware module, a software module, and/or a firmware module.

System memory may be used, for example, to load and store data and/or instructions for the system. For one embodiment, the system memory may comprise any suitable volatile memory, such as suitable DRAM. In some embodiments, the system memory may include a double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).

For one embodiment, the system control module may include one or more input/output (I/O) controllers to provide an interface to the NVM/storage and communication interface(s).

For example, the NVM/storage may be used to store data and/or instructions. The NVM/storage may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drive(s) (HDD (s)), one or more Compact Disc (CD) drive(s), and/or one or more Digital Versatile Disc (DVD) drive (s)).

The NVM/storage may include storage resources that are physically part of the device on which the system is installed, or it may be accessible by the device and not necessarily part of the device. For example, the NVM/storage may be accessible over a network via the communication interface(s).

The communication interface(s) may provide an interface for the system to communicate over one or more networks and/or with any other suitable device. The system may wirelessly communicate with one or more components of the wireless network according to any of one or more wireless network standards and/or protocols.

For one embodiment, at least one of the processor(s) may be packaged together with logic for one or more controllers (e.g., memory controller modules) of the system control module. For one embodiment, at least one of the processor(s) may be packaged together with logic for one or more controllers of a system control module to form a System In Package (SiP). For one embodiment, at least one of the processor(s) may be integrated on the same die with logic for one or more controllers of the system control module. For one embodiment, at least one of the processor(s) may be integrated on the same die with logic of one or more controllers of a system control module to form a system on a chip (SoC).

In various embodiments, the system may be, but is not limited to being: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, the system may have more or fewer components and/or different architectures. For example, in some embodiments, the system includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and speakers.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Those skilled in the art will appreciate that the form in which the computer program instructions reside on a computer-readable medium includes, but is not limited to, source files, executable files, installation package files, and the like, and that the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Computer-readable media herein can be any available computer-readable storage media or communication media that can be accessed by a computer.

Communication media includes media by which communication signals, including, for example, computer readable instructions, data structures, program modules, or other data, are transmitted from one system to another. Communication media may include conductive transmission media such as cables and wires (e.g., fiber optics, coaxial, etc.) and wireless (non-conductive transmission) media capable of propagating energy waves such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied in a modulated data signal, for example, in a wireless medium such as a carrier wave or similar mechanism such as is embodied as part of spread spectrum techniques. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The modulation may be analog, digital or hybrid modulation techniques.

An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or a solution according to the aforementioned embodiments of the present application.

Example four

Corresponding to the above embodiments, the present application further provides a computer-readable storage medium storing computer-executable instructions for executing the method for dynamically confirming the identity.

In the present embodiment, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. For example, computer-readable storage media include, but are not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and non-volatile memory such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, feRAM); and magnetic and optical storage devices (hard disk, tape, CD, DVD); or other now known media or later developed that can store computer-readable information/data for use by a computer system.

While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. An identity dynamic confirmation method is applied to an identity dynamic confirmation system, and is characterized in that the identity dynamic confirmation system comprises an entrance identity verification end, an exit identity verification end, a dynamic verification end of a closed area formed between the entrance and the exit and a service end, and the method comprises the following steps:

after a first preset time interval, performing second face authentication on the user through the entrance identity authentication end to obtain a second face authentication result;

and judging whether the user is legal or not through the server side according to the first judgment result and/or the second judgment result.

2. The dynamic identity verification method according to claim 1, wherein the first face authentication result includes a first face authentication score, and after the interval of the first preset time, the method further includes, before performing a second face authentication on the user through the entry authentication end to obtain a second face authentication result:

3. The dynamic identity confirmation method according to claim 1, wherein the step of sending the first face authentication result to the server through the portal identity verification end for base authentication to obtain a base authentication result, and obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result, and the base authentication result comprises:

4. The dynamic identity confirmation method according to claim 3, wherein if the base authentication result includes that the current user is a leading user and enters a base, the obtaining and storing an identity recognition threshold interval and a unique identity of the user according to the first face authentication result, the second face authentication result, and the base authentication result includes:

assigning the maximum identity recognition sub-threshold value of the identity recognition threshold interval of the current user to be a second face authentication score obtained according to the first face authentication result and the second face authentication result;

5. The dynamic identity authentication method of claim 4, wherein if the base authentication result includes that the current user is not the first user to enter the base, the base authentication is performed by matching with the full face of the base at the server side to obtain a base authentication result, and the method comprises:

if the face recognition scores of each user in the bottom library are smaller than the minimum identity recognition sub-threshold corresponding to each user in the bottom library and smaller than the existing minimum identity recognition sub-threshold of the current user, assigning the minimum identity recognition sub-threshold of the current user as the public minimum threshold of the bottom library, and assigning the maximum identity recognition sub-threshold of the current user as a second face authentication score obtained according to the first face authentication result and the second face authentication result.

6. The dynamic identity authentication method according to claim 5, wherein if the face recognition score of any user in the base repository is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the base repository, the obtaining the authentication result in the base repository further comprises:

if the face recognition score of any base bank user is greater than or equal to the existing minimum identity recognition sub-threshold of the current user, the method further comprises the following steps:

7. The dynamic identity verification method of claim 5, wherein the base authentication further comprises:

8. The dynamic identity verification method according to claim 3, wherein the first determination result includes at least one of a face recognition score of only one face image and a user in the basement being greater than or equal to a minimum identity recognition sub-threshold corresponding to the user in the basement, a face recognition score of two or more face images and the user in the same basement being greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the basement, and a face recognition score of a face image and any user in the basement being less than or equal to the minimum identity recognition sub-threshold corresponding to the user in the basement.

9. The dynamic identity authentication method according to claim 8, wherein if the first determination result indicates that two or more face images exist and the face recognition score of a user in the same basement is greater than or equal to the minimum identity recognition sub-threshold corresponding to the user in the basement, after the first determination result is obtained, the method further comprises:

10. A dynamic identity verification system, the system comprising:

the entrance identity verification end is also used for carrying out second face authentication on the user after a first preset time interval to obtain a second face authentication result;

11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for dynamically validating an identity as claimed in any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium storing computer-executable instructions for performing the method of dynamically validating an identity of any one of claims 1 to 9.