CN114694227A - Identity authentication continuous optimization method based on face recognition technology - Google Patents
Identity authentication continuous optimization method based on face recognition technology Download PDFInfo
- Publication number
- CN114694227A CN114694227A CN202210347270.4A CN202210347270A CN114694227A CN 114694227 A CN114694227 A CN 114694227A CN 202210347270 A CN202210347270 A CN 202210347270A CN 114694227 A CN114694227 A CN 114694227A
- Authority
- CN
- China
- Prior art keywords
- user
- face
- module
- information
- recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention discloses an identity authentication continuous optimization method based on a face recognition technology, and particularly relates to the technical field of face recognition. According to the invention, by designing the model training module, data acquisition can be carried out on expression information, face information after makeup and photo face information of the user on the basis of safety verification of face recognition verification, and the data acquisition is used as a subsequent face recognition verification basis, so that the acquisition of the face information of the user is greatly enriched, a face model of the user in a face recognition algorithm model library is more precise, and the successful verification probability of the face information of the user in different expression states is greatly increased.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to an identity authentication continuous optimization method based on a face recognition technology.
Background
Identity authentication is also called "authentication" and "authentication", which means that the user identity is confirmed by a certain means. There are many methods for authentication, which can be basically classified into: shared key based authentication, biometric based authentication, and public key encryption algorithm based authentication. The face recognition technology is one of identity verification means based on biological characteristics, is a biological recognition technology for carrying out identity recognition based on face characteristic information of people, and is a series of related technologies, generally called portrait recognition and facial recognition, for collecting images or video streams containing faces by using a camera or a camera, automatically detecting and tracking the faces in the images and further carrying out facial recognition on the detected faces.
The existing face recognition technology is based on a face recognition algorithm, the matching degree of a user can greatly influence the recognition rate, for example, the length change of beard and hair, the change of hair style, whether glasses are worn or not, the facial expression and the like can greatly influence the recognition rate, and under certain special conditions, for example, when the user is in outdoor scenes such as strong weather, low temperature, hot weather and the like, the expression of the user can often be influenced under the conditions and changes unconsciously, the recognition rate can be greatly influenced negatively, the condition of verification failure can often exist, and technical defects exist.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an identity authentication continuous optimization method based on a face recognition technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
an identity authentication continuous optimization method based on a face recognition technology comprises a client and a server, wherein the client comprises a mobile phone terminal, and the mobile phone terminal comprises a camera use authority application module, a mobile phone gallery access authority application module and a camera parameter control module; the server side comprises an application server and a database, wherein the application server provides system service and comprises a face recognition module, an identity authentication module and a model training module; the identity authentication module comprises a face information verification module, an account name verification module, an account password verification module and a fingerprint information identification verification module; the model training module comprises an expression information recognition module, a post-makeup face information recognition module and a photo face information recognition module; the database is used for storing system data and comprises a user database, a permission database, a user photo database and a face recognition algorithm model database.
The invention is further configured to: the camera use permission application module is used for acquiring the use permission of the mobile phone camera shooting function of the user, the mobile phone gallery access permission application module is used for acquiring the collection gallery access and the use permission of the user, and the camera shooting parameter control module is used for automatically adjusting the specific parameters of the camera shooting function of the user.
By adopting the technical scheme: the invention can use the camera of the mobile phone of the user and access the gallery of the user under the permission of the user.
The invention is further configured to: the face recognition module comprises an uploaded picture recognition module and a camera shooting recognition module, and the uploaded picture recognition module can be used for carrying out face feature recognition on a picture uploaded by a user; the camera shooting identification module can identify pictures shot by a camera at the mobile end of the mobile phone in real time.
By adopting the technical scheme: the invention can identify the face information of the photos in the user gallery and the face information of the user.
The invention is further configured to: the face information verification module can identify and verify face information and photo information provided by a user; the account name verification module can perform primary verification on the identity of the user by using the account name; the account password verification module can verify the identity of the user; the fingerprint information identification and verification module can perform identity verification by using the fingerprint information of the user.
By adopting the technical scheme: the identity information of the user can be verified in multiple layers.
The invention is further configured to: the expression information identification module utilizes a face identification algorithm to increase the face model information of the user, and the face information identification module after makeup utilizes the face identification algorithm to adapt to the makeup habit of the user, so that the data richness of a face identification algorithm model library in a database is increased; the photo face information recognition module is used for recognizing face information of the photos in the image library based on a face recognition algorithm and inputting the recognized photos into a user photo database.
The invention is further configured to: the user database stores user account information, passwords and other user information; the authority database stores the resource and data authority information of the user in the system; the user photo database stores the user and the face photo information of the user; the face recognition algorithm model base stores algorithm models for face detection and recognition.
The invention has the beneficial effects that:
according to the invention, by designing the model training module, the data acquisition can be carried out on the expression information, the face information after makeup and the photo face information of the user on the basis of the safety verification of the face recognition verification, and the data acquisition can be used as the subsequent face recognition verification basis, so that the acquisition of the face information of the user is greatly enriched, the face model of the user in the face recognition algorithm model library is more precise, the successful verification probability of the face information of the user in different expression states is greatly increased, and meanwhile, as the face information in the model library is more precise, the successful verification probability of long-term similar non-users is greatly reduced by comparing the details of the face information;
in the identity authentication module designed by the invention, the face information verification module and the fingerprint information identification verification module are biological information verification means of the user, and the information of the user can be verified more comprehensively by combining an account information verification mode, and the success rate of non-user verification is greatly increased by different matching of different verification means.
Drawings
FIG. 1 is a schematic block diagram of a method for continuously optimizing identity authentication based on a face recognition technology according to the present invention;
FIG. 2 is a schematic block diagram of comparative example 1 of the present invention;
FIG. 3 is a schematic block diagram of comparative example 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example 1
As shown in fig. 1, a continuous optimization method for identity authentication based on a face recognition technology includes a client and a server, where the client includes a mobile phone terminal, the mobile phone terminal includes a camera access permission application module, a mobile phone gallery access permission application module and a camera parameter control module, the camera access permission application module is used to obtain the mobile phone camera function access permission of a user, the mobile phone gallery access permission application module is used to obtain the collected gallery access and use permission of the user, and the camera parameter control module is used to automatically adjust specific parameters of the user camera function, such as automatically closing a filter and a special effect;
the server side comprises an application server and a database, wherein the application server provides system service and comprises a face recognition module, an identity authentication module and a model training module; the face recognition module comprises an uploaded picture recognition module and a camera shooting recognition module, the uploaded picture recognition module can perform face feature recognition on a picture uploaded by a user, picture face recognition is additionally designed, so that the face recognition system can consider the use condition of the damaged face of the user when the face is verified, and the verification system also has safety by matching with fingerprint recognition; the camera shooting identification module can identify pictures shot by a camera at the mobile end of the mobile phone in real time; the identity authentication module comprises a face information verification module, an account name verification module, an account password verification module and a fingerprint information identification verification module, and the face information verification module can identify and verify face information and photo information provided by a user; the account name verification module can perform primary verification on the identity of the user by using the account name; the account password verification module can verify the identity of the user; the fingerprint information identification and verification module can carry out identity verification by utilizing the fingerprint information of a user;
the model training module comprises an expression information recognition module, a face information recognition module after makeup and a photo face information recognition module, wherein the expression information recognition module increases the face model information of a user by using a face recognition algorithm and increases the success rate and the accuracy rate of verification; the photo face information recognition module is used for recognizing face information of the photos in the image library based on a face recognition algorithm and inputting the recognized photos into a user photo database, so that the success rate and the accuracy rate of verification are increased;
the database is used for storing system data and comprises a user database, a permission database, a user photo database and a face recognition algorithm model database; the user database stores user account information, passwords and other user information; the authority database stores the resource and data authority information of the user in the system; the user photo database stores the user and the face photo information of the user; the face recognition algorithm model base stores algorithm models for face detection and recognition.
Example 2
When the invention is used:
1. firstly, establishing an account, then setting an account password, and storing basic account information and account password information in a user database at the moment;
2. inputting face information, wherein the face information is directly stored in a face recognition algorithm model base after being successfully recognized based on a face recognition algorithm;
3. then, inputting fingerprint information, wherein the fingerprint information identification is based on a fingerprint identification algorithm and is stored in a user database after the identification is successful;
4. then uploading the picture, collecting the character characteristic information in the picture by using a face recognition algorithm, and storing the collected data in a user photo database;
5. and verifying the face information of the user at regular time.
Example 3
When face information is regularly collected:
1. firstly, account password information is verified, so that the identity of a user is preliminarily verified;
2. verifying the fingerprint information of the user so as to further verify the identity of the user;
3. verifying the uploaded photo information, and further verifying the identity of the user by using the memory of the user;
4. identifying and verifying face information, and finally verifying the identity of the user;
5. and different facial expression model data are collected and uploaded, the facial model data of the user are updated, and the data volume in the facial recognition algorithm model library is enriched.
Example 4
When the user needs to change the access authority information and accesses the authority database:
1. firstly, fingerprint information of a user is verified, and based on the importance of a permission database, the fingerprint information of the user needs to be verified firstly;
2. then, the face feature information is verified, and the accuracy of identity verification is improved by identifying and verifying the face information of the user;
3. the account password verification window is skipped out periodically, the verification flexibility is improved, the verification safety is improved by an elastic verification mode, and the periodic time can be set by a user.
Example 5
When a user needs to change or check the data of the user database and accesses the user database:
1. verifying the face information, and setting the verified face information as a necessary starting condition based on the importance of the user database and the demand of the user during checking;
2. the fingerprint verification window is jumped out periodically, when a user who is not a user uses the face information of the user to perform unlocking identification, the user can be blocked, and the periodic time can be set by the user;
3. and (3) jumping out of the account password verification window regularly, blocking a user who is not the user when unlocking and identifying the user by using the face information of the user, wherein the regular time can be set by the user.
Example 6
The model training module of the invention is used for improving the accuracy and efficiency of the invention for identifying the face information of the user, and during training:
1. collecting face information of three different expressions, storing the face information into a face recognition algorithm model base, wherein the three expression types are different expression types and are used as basic comparison models;
2. identifying and matching the collected face information based on a face identification algorithm, wherein the identified comparison models are the face information models of the three different expressions collected in the method;
3. performing face recognition verification once every three times of recognition failure, and avoiding inserting non-user face information in the recognition process;
4. carrying out photo face information identification once every time the identification is successful until the identification is failed, then carrying out face identification verification once, storing the face information after the identification is successful into a face identification algorithm model base to be used as a subsequent identification basic comparison data model, and enriching a photo database of a user by the photo face information identification after the face identification is successful to be also used as subsequent identification basic comparison data;
5. based on the fact that the face information of the user cannot exist together with the normal face information during makeup, face information recognition after makeup is independent of expression information recognition and photo face information recognition;
6. based on the fact that the face information after makeup is different from the normal face information to a certain extent, face recognition verification is conducted once before face information recognition is started after makeup, verification timeliness is set in a fingerprint verification mode after verification, fingerprint verification is used as verification conditions for timeliness setting starting, the probability of the situation that a user does not interfere with training is reduced by combining the face verification mode and the fingerprint verification mode, and therefore the situation that training cannot be started is avoided;
7. based on make-up consuming time and labor, fingerprint identification verification is performed once after face information identification fails after make-up each time, face identification verification is performed once when face identification training is finished after make-up, and the probability that non-user persons have negative influences on the training process and results is reduced by verifying abnormal conditions occurring in the training process.
Comparative example 1
As shown in fig. 2, an identity authentication continuous optimization method based on a face recognition technology includes a client and a server, where the client includes a mobile phone terminal, the mobile phone terminal includes a camera usage permission application module, a mobile phone gallery access permission application module and a camera parameter control module, the camera usage permission application module is used to obtain usage permission of a mobile phone camera function of a user, the mobile phone gallery access permission application module is used to obtain collected gallery access and usage permission of the user, and the camera parameter control module is used to automatically adjust specific parameters of the user camera function, such as automatically closing a filter and a special effect;
the server side comprises an application server and a database, wherein the application server provides system service and comprises a face recognition module, an identity authentication module and a model training module; the face recognition module comprises an uploaded picture recognition module and a camera shooting recognition module, the uploaded picture recognition module can perform face feature recognition on a picture uploaded by a user, and picture face recognition is additionally designed, so that the face recognition module can be used when the face of the user is injured in face verification; the camera shooting identification module can identify pictures shot by a camera at the mobile end of the mobile phone in real time; the identity authentication module comprises a face information verification module, an account name verification module and an account password verification module, and the face information verification module can identify and verify face information and photo information provided by a user; the account name verification module can perform primary verification on the identity of the user by using the account name; the account password verification module can verify the identity of the user;
the model training module comprises an expression information recognition module, a face information recognition module after makeup and a photo face information recognition module, wherein the expression information recognition module increases the face model information of a user by using a face recognition algorithm and increases the success rate and the accuracy rate of verification; the photo face information recognition module is used for carrying out face information recognition on the photos in the image library based on a face recognition algorithm, and inputting the photos into a user photo database after recognition, so that the success rate and the accuracy rate of verification are increased;
the database is used for storing system data and comprises a user database, a permission database, a user photo database and a face recognition algorithm model database; the user database stores user account information, passwords and other user information; the authority database stores the resource and data authority information of the user in the system; the user photo database stores the user and the face photo information of the user; the face recognition algorithm model bank stores algorithm models for face detection and recognition.
The design reduces the rigor of user identity authentication and increases the probability of database alteration by non-user.
Comparative example 2
As shown in fig. 3, a continuous optimization method for identity authentication based on a face recognition technology includes a client and a server, where the client includes a mobile phone terminal, the mobile phone terminal includes a camera usage permission application module and a camera parameter control module, the camera usage permission application module is used to obtain usage permission of a mobile phone camera function of a user, the mobile phone gallery access permission application module is used to obtain collection gallery access and usage permission of the user, and the camera parameter control module is used to automatically adjust specific parameters of the camera function of the user, such as automatically closing a filter and a special effect;
the server side comprises an application server and a database, wherein the application server provides system service and comprises a face recognition module, an identity authentication module and a model training module; the face recognition module comprises a camera shooting recognition module which can recognize pictures shot by a camera at a mobile terminal of the mobile phone in real time; the identity authentication module comprises a face information verification module, an account name verification module, an account password verification module and a fingerprint information identification verification module, and the face information verification module can identify and verify face information provided by a user; the account name verification module can perform primary verification on the identity of the user by using the account name; the account password verification module can verify the identity of the user; the fingerprint information identification and verification module can carry out identity verification by utilizing the fingerprint information of a user;
the model training module comprises an expression information recognition module and a face information recognition module after makeup, the expression information recognition module increases the face model information of a user by using a face recognition algorithm and increases the success rate and the accuracy rate of verification, the face information recognition module after makeup adapts to the makeup habit of the user by using the face recognition algorithm, the data richness of a face recognition algorithm model base in a database is increased, and the success rate and the accuracy rate of verification are increased;
the database is used for storing system data and comprises a user database, a permission database and a face recognition algorithm model library; the user database stores user account information, passwords and other user information; the authority database stores the resource and data authority information of the user in the system; the face recognition algorithm model base stores algorithm models for face detection and recognition.
The above design, comparative examples 1 to 6, reduced the user authentication means in abnormal situations.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (6)
1. An identity authentication continuous optimization method based on a face recognition technology is characterized by comprising a client and a server, wherein the client comprises a mobile phone terminal, and the mobile phone terminal comprises a camera use permission application module, a mobile phone gallery access permission application module and a camera parameter control module; the server side comprises an application server and a database, wherein the application server provides system service and comprises a face recognition module, an identity authentication module and a model training module; the identity authentication module comprises a face information verification module, an account name verification module, an account password verification module and a fingerprint information identification verification module; the model training module comprises an expression information recognition module, a post-makeup face information recognition module and a photo face information recognition module; the database is used for storing system data and comprises a user database, a permission database, a user photo database and a face recognition algorithm model database.
2. The identity authentication continuous optimization method based on the face recognition technology as claimed in claim 1, wherein the camera usage permission application module is used for obtaining usage permission of a mobile phone camera shooting function of a user, the mobile phone gallery access permission application module is used for obtaining collection gallery access and usage permission of the user, and the camera shooting parameter control module is used for automatically adjusting specific parameters of the user camera shooting function.
3. The identity authentication continuous optimization method based on the face recognition technology is characterized in that the face recognition module comprises an uploaded picture recognition module and a camera shooting recognition module, and the uploaded picture recognition module can perform face feature recognition on a photo uploaded by a user; the camera shooting identification module can identify pictures shot by a camera at the mobile end of the mobile phone in real time.
4. The identity authentication continuous optimization method based on the face recognition technology as claimed in claim 1, wherein the face information verification module can perform recognition verification on face information and photo information provided by a user; the account name verification module can perform primary verification on the identity of the user by using the account name; the account password verification module can verify the identity of the user; the fingerprint information identification and verification module can perform identity verification by using the fingerprint information of the user.
5. The identity authentication continuous optimization method based on the face recognition technology as claimed in claim 1, wherein the expression information recognition module utilizes a face recognition algorithm to increase the face model information of the user, the face information recognition module after makeup utilizes a face recognition algorithm to adapt to the makeup habit of the user, and the data richness of a face recognition algorithm model library in a database is increased; the photo face information recognition module is used for recognizing face information of the photos in the image library based on a face recognition algorithm and inputting the recognized photos into a user photo database.
6. The identity authentication continuous optimization method based on the face recognition technology as claimed in claim 1, wherein a user database stores user information such as user account information and passwords; the authority database stores the resource and data authority information of the user in the system; the user photo database stores the user and the face photo information of the user; the face recognition algorithm model base stores algorithm models for face detection and recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210347270.4A CN114694227A (en) | 2022-04-01 | 2022-04-01 | Identity authentication continuous optimization method based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210347270.4A CN114694227A (en) | 2022-04-01 | 2022-04-01 | Identity authentication continuous optimization method based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114694227A true CN114694227A (en) | 2022-07-01 |
Family
ID=82140300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210347270.4A Pending CN114694227A (en) | 2022-04-01 | 2022-04-01 | Identity authentication continuous optimization method based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114694227A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240265A (en) * | 2022-09-23 | 2022-10-25 | 深圳市欧瑞博科技股份有限公司 | User intelligent identification method, electronic equipment and storage medium |
-
2022
- 2022-04-01 CN CN202210347270.4A patent/CN114694227A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240265A (en) * | 2022-09-23 | 2022-10-25 | 深圳市欧瑞博科技股份有限公司 | User intelligent identification method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101938033B1 (en) | Biometric authentication in connection with camera-equipped devices | |
| US9122913B2 (en) | Method for logging a user in to a mobile device | |
| CN105261105B (en) | Safety door inhibition method | |
| US9147061B1 (en) | Multi-level authentication | |
| US20170262472A1 (en) | Systems and methods for recognition of faces e.g. from mobile-device-generated images of faces | |
| US20210089635A1 (en) | Biometric identity verification and protection software solution | |
| CN103678984A (en) | Method for achieving user authentication by utilizing camera | |
| KR20170047255A (en) | Identity authentication method and apparatus, terminal and server | |
| US20200134346A1 (en) | Intelligent gallery management for biometrics | |
| CN101494690A (en) | Mobile terminal and unlocking method thereof | |
| CN112330035A (en) | Training method and device of risk prediction model | |
| WO2016188230A1 (en) | Unlocking method and device | |
| CN112199530B (en) | Multi-dimensional face library picture automatic updating method, system, equipment and medium | |
| CN109492555A (en) | Newborn identity identifying method, electronic device and computer readable storage medium | |
| JP2006085268A (en) | Biometrics system and biometrics method | |
| CN114694227A (en) | Identity authentication continuous optimization method based on face recognition technology | |
| Podio | Personal authentication through biometric technologies | |
| CN105897747B (en) | Data storage method and device based on digital biological signature and intelligent equipment | |
| JP4434560B2 (en) | Entrance / exit management system | |
| KR102060563B1 (en) | Method and apparatus for providing authentication using voice and facial data | |
| CN114926878A (en) | Non-monitoring remote face recognition method based on one-object-one-code corresponding scene | |
| CN113112664A (en) | Vertical entrance guard's equipment of face identification | |
| CN112669501A (en) | Access control method, device and computer readable storage medium | |
| WO2024027940A1 (en) | System and method for determining the update of a reference credential | |
| AU2005100275A4 (en) | User authentication appratus using human body movement detection biometrics system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |