CN116311457A - Application capable of adapting to portrait identification of various service terminals - Google Patents
Application capable of adapting to portrait identification of various service terminals Download PDFInfo
- Publication number
- CN116311457A CN116311457A CN202310295575.XA CN202310295575A CN116311457A CN 116311457 A CN116311457 A CN 116311457A CN 202310295575 A CN202310295575 A CN 202310295575A CN 116311457 A CN116311457 A CN 116311457A
- Authority
- CN
- China
- Prior art keywords
- face
- real
- recognition
- server
- registration
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000002372 labelling Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 230000004913 activation Effects 0.000 abstract description 3
- 210000002268 wool Anatomy 0.000 abstract 1
- 238000012795 verification Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 5
- 238000009333 weeding Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000004397 blinking Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000001727 in vivo Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an application of portrait identification which can be adapted to various service terminals, belonging to the technical field of face identification, comprising the following steps: the system comprises a client, a server and a data terminal; the client comprises face recognition interface call and face registration interface call; the server side comprises a face recognition interface and a face registration interface; the data end comprises a registered face image library, a registered face tag library, a face region detection model, a face feature point labeling model and a face comparison model, and the client also comprises real-time video acquisition, real-time face region detection and real-time face region snapshot; compared with the traditional identity authentication mode, the method has the advantages that the method can run on IOS and Android, face information is collected in real time in authentication to carry out living judgment, safety, confidentiality and convenience are achieved, user privacy is effectively protected, business blackout loss of enterprises is reduced, safety is high, phenomena of false registration of users such as wool are reduced, and resource investment such as enterprise updating and activation can be accurately projected to real users.
Description
Technical Field
The invention belongs to the technical field of face recognition, and particularly relates to application of portrait recognition capable of adapting to various service terminals.
Background
Along with the continuous rising of security and protection demands, traditional security and protection face a plurality of challenges such as larger number of recognition targets, stronger mobility, higher requirement on recognition efficiency, more complexity of recognition scenes and the like, and the traditional manner of checking the identity information of the recognition objects through naked eyes cannot meet the requirements on efficiency and accuracy of mass verification of people, vehicles and certificates.
In the internet service, user login verification is the most basic function, but the user experience of the existing verification mode is poor, and a large amount of black production and the risk of weeding exist.
The existing authentication mode has poor user experience. Because 10 or more APP can be registered by one user at present, the passwords of different APP are required to be memorized through a verification mode of inputting the passwords, so that the memory burden of the user is caused; the verification mode of verification code login can not receive the verification code in a delayed way for some reasons.
False information registration risk, and the existing registration mode can lead to the scenes of black product registration false account number, weeding profit and the like.
According to publication No.: the image matching method, device, storage medium and application based on the portrait identification of the CN110728242A comprise the following steps: step 1: detecting whether a face exists in the image, if so, marking the face in the image and outputting the position of the face; step 2: and training the convolutional neural network model for a plurality of times by taking the face image as a training sample, so that the convolutional neural network model can identify the face characteristics in the image.
However, the face recognition model is operated at the client, the model is required to be simple enough, the client can provide the computing resources required by the operation model, most of the computing resources of the mobile phone client can not meet the requirements, and in order to obtain the model which can be operated at the mobile phone client, the manpower is required to be input for technical pre-research.
In the process of user face recognition, a scene of impersonation in the form of pictures and the like exists, so that a certain security hole exists in recognition; therefore, it is necessary to provide a user that can easily complete registration, login authentication without requiring the user to memorize any information or carrying something, and can effectively prevent risks such as false registration, theft, etc.
Disclosure of Invention
The invention aims to provide an application capable of adapting to portrait identification of various service terminals, so as to solve the problems that the conventional portrait identification provided in the background technology requires a user to memorize related information more complicated and has a certain vulnerability risk.
In order to achieve the above purpose, the present invention provides the following technical solutions: an application adaptable to portrait identification of a plurality of service terminals, comprising:
the system comprises a client, a server and a data terminal;
the client comprises face recognition interface call and face registration interface call;
the server comprises a face recognition interface and a face registration interface;
the data end comprises a registered face image library, a registered face label library, a face region detection model, a face feature point labeling model and a face comparison model.
As a preferred implementation manner, the client also comprises real-time video acquisition, real-time face area detection and real-time face area snapshot.
By adopting the scheme, the face information is collected in real time in login authentication to carry out living judgment, and the authority data source verification is matched to protect the user privacy and the business of enterprises.
Custom in vivo monitoring: the face polishing scheme is used for completing living body detection, and is matched with actions such as blinking, mouth opening, head shaking, left and right turning, head lifting and descending, and the like, a plurality of images are randomly grabbed to carry out living body judgment, so that the effective actions and the verification sequence can be customized, and the black yield is prevented from carrying out targeted living body counterfeiting.
The face recognition model operates on the server side, can adapt to IOS and android different application systems, and simultaneously reduces requirements on hardware configuration of the mobile phone of the user.
As a preferred embodiment, the real-time video acquisition includes converting an analog video into a digital video in real time, storing the digital video in a format of a digital video file, converting the digital video into binary digital information through a dedicated analog-digital conversion device, the real-time face area detection includes acquiring an image or video stream containing a face with a camera or a camera, and automatically detecting and tracking the face in the image, so as to perform face recognition on the detected face, and the real-time face area snapshot includes tracking, recognizing and capturing the face.
As a preferred implementation mode, the server side further comprises feature point detection, feature point alignment, face comparison, blink recognition and mouth opening recognition, and the face comparison is carried out by detecting and aligning the features of the face, blink recognition and mouth opening recognition and then the database.
As a preferred implementation mode, the face recognition comprises a face registration stage and an authentication stage, wherein the face registration stage is used for collecting face photos at all angles (middle, left, right, up and down), the uploading server requests registration, the server receives the registration request and then recognizes the face from the face photos, extracts the face characteristics and stores the face characteristics in a database, and the face recognition stage is compared with the characteristics of the newly uploaded photos.
As a preferred implementation mode, the authentication stage comprises that a client is responsible for collecting face pictures, and uploads a request of authentication of a server, the server receives the request and then performs face detection and face feature extraction, and compares the request with face features generated in the registration stage, if the feature distance is lower than a certain threshold value, the authentication is passed, the server can collect effect data of the authentication, and the user model is optimized and evaluated.
Compared with the prior art, the invention has the beneficial effects that:
compared with the traditional identity authentication mode, the application of portrait identification which can be adapted to various service terminals can run on IOS and Android at the same time, and face information is collected in real time in authentication to carry out living judgment, so that the application is safer, more secret and more convenient, and the privacy of users is effectively protected.
The enterprise business blackout loss is reduced, the safety is higher, the phenomena of false registration of users, weeding, and the like are reduced, and the resource investment of enterprises such as new pulling, activation promotion and the like can be more accurately projected to real users.
And the user experience is improved: the face recognition is fast, is not easy to be perceived, and compared with other biological recognition technologies, the face recognition belongs to an automatic recognition technology, and can be recognized for a plurality of times within one second. Compared with password login, short message verification code login is simple to operate, and safety is improved more.
Drawings
FIG. 1 is a schematic diagram of a client architecture of the present invention;
FIG. 2 is a schematic diagram of a server structure according to the present invention;
fig. 3 is a schematic diagram of the data end structure of the present invention.
Description of the embodiments
The invention is further described below with reference to examples.
The following examples are illustrative of the present invention but are not intended to limit the scope of the invention. The conditions in the examples can be further adjusted according to specific conditions, and simple modifications of the method of the invention under the premise of the conception of the invention are all within the scope of the invention as claimed.
Referring to fig. 1-3, the present invention provides an application capable of adapting to portrait identification of various service terminals, including:
the system comprises a client, a server and a data terminal;
the client comprises face recognition interface call and face registration interface call;
the server side comprises a face recognition interface and a face registration interface;
the data end comprises a registered face image library, a registered face label library, a face region detection model, a face feature point labeling model and a face comparison model.
The client also comprises real-time video acquisition, real-time face area detection and real-time face area snapshot.
The real-time video acquisition comprises the steps of converting an analog video into a digital video in real time, storing the digital video in a format of a digital video file, converting the digital video into binary digital information through special analog and digital conversion equipment, acquiring an image or video stream containing a human face by using a camera or a camera, automatically detecting and tracking the human face in the image, further carrying out face recognition on the detected human face, and capturing the real-time human face region, wherein the real-time human face region comprises the steps of tracking, recognizing and capturing the human face.
The face information is collected in real time in login authentication to carry out living body judgment, and authority data source verification is matched to protect user privacy and enterprise business.
The server side further comprises feature point detection, feature point alignment, face comparison, blink recognition and mouth opening recognition, and the face comparison is carried out by detecting and aligning the features of the face, blink recognition and mouth opening recognition and then the database.
The face recognition comprises a face registration stage and an authentication stage, wherein the face registration stage is used for collecting face photos at all angles (middle, left, right, up and down), the uploading server requests registration, the server receives the registration request, then recognizes the face from the face photos, extracts face features and stores the face features in a database, and the face recognition stage is compared with the features of the newly uploaded photos.
Custom in vivo monitoring: the face polishing scheme is used for completing living body detection, and is matched with actions such as blinking, mouth opening, head shaking, left and right turning, head lifting and descending, and the like, a plurality of images are randomly grabbed to carry out living body judgment, so that the effective actions and the verification sequence can be customized, and the black yield is prevented from carrying out targeted living body counterfeiting.
The authentication stage comprises that a client is responsible for collecting face pictures, uploading the face pictures to a server for authentication, carrying out face detection and face feature extraction after the server receives the request, comparing the face detection and the face feature extraction with face features generated in the registration stage, and if the feature distance is lower than a certain threshold value, the authentication is passed, the server can collect authentication effect data, and the user model is optimized and evaluated.
The face recognition model operates on the server side, can adapt to IOS and android different application systems, and simultaneously reduces requirements on hardware configuration of the mobile phone of the user.
By the design, compared with the traditional identity authentication mode, the method can run on IOS and Android at the same time, and human face information is collected in real time in authentication to carry out living judgment, so that the method is safer, more secret and more convenient, and the privacy of users is effectively protected.
The enterprise business blackout loss is reduced, the safety is higher, the phenomena of false registration of users, weeding, and the like are reduced, and the resource investment of enterprises such as new pulling, activation promotion and the like can be more accurately projected to real users.
And the user experience is improved: the face recognition is fast, is not easy to be perceived, and compared with other biological recognition technologies, the face recognition belongs to an automatic recognition technology, and can be recognized for a plurality of times within one second. Compared with password login, short message verification code login is simple to operate, and safety is improved more.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. An application adaptable to portrait identification of a plurality of service terminals, comprising:
the system comprises a client, a server and a data terminal;
the client comprises face recognition interface call and face registration interface call;
the server comprises a face recognition interface and a face registration interface;
the data end comprises a registered face image library, a registered face label library, a face region detection model, a face feature point labeling model and a face comparison model.
2. The application adaptable to portrait identification of a plurality of service terminals of claim 1, wherein: the client also comprises real-time video acquisition, real-time face area detection and real-time face area snapshot.
3. The application adaptable to portrait identification of a plurality of service terminals of claim 2, wherein: the real-time video acquisition comprises the steps of converting an analog video into a digital video in real time, storing the digital video in a format of a digital video file, converting the digital video into binary digital information through special analog and digital conversion equipment, acquiring an image or video stream containing a human face by using a camera or a camera, automatically detecting and tracking the human face in the image, and further carrying out face recognition on the detected human face, wherein the real-time human face region snapshot comprises the steps of tracking, recognizing and capturing the human face.
4. The application adaptable to portrait identification of a plurality of service terminals of claim 1, wherein: the server side further comprises feature point detection, feature point alignment, face comparison, blink recognition and mouth opening recognition, and the face comparison is performed by detecting and aligning the features of the face, blink recognition and mouth opening recognition and then the database.
5. The application adaptable to portrait identification of a plurality of service terminals of claim 1, wherein: the face recognition comprises a face registration stage and an authentication stage, wherein the face registration stage is used for collecting face photos at all angles (middle, left, right, up and down), the uploading server requests registration, the server receives the registration request, then recognizes the face from the face photos, extracts face features and stores the face features in a database, and the face recognition stage is compared with the features of the newly uploaded photos.
6. The application adaptable to portrait identification of a plurality of service terminals of claim 5, wherein: the authentication stage comprises that a client is responsible for collecting face pictures, uploading the face pictures to a server for authentication, carrying out face detection and face feature extraction after the server receives the request, comparing the face detection and the face feature extraction with face features generated in the registration stage, and if the feature distance is lower than a certain threshold value, the authentication is passed, the server can collect authentication effect data, and the user model is optimized and evaluated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310295575.XA CN116311457A (en) | 2023-03-24 | 2023-03-24 | Application capable of adapting to portrait identification of various service terminals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310295575.XA CN116311457A (en) | 2023-03-24 | 2023-03-24 | Application capable of adapting to portrait identification of various service terminals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116311457A true CN116311457A (en) | 2023-06-23 |
Family
ID=86818514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310295575.XA Pending CN116311457A (en) | 2023-03-24 | 2023-03-24 | Application capable of adapting to portrait identification of various service terminals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116311457A (en) |
-
2023
- 2023-03-24 CN CN202310295575.XA patent/CN116311457A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10650261B2 (en) | System and method for identifying re-photographed images | |
| US20240143842A1 (en) | System and method for validating authorship of an electronic signature session | |
| CN107580196B (en) | Video data sharing system and method | |
| CN106850648B (en) | Identity verification method, client and service platform | |
| KR20200006987A (en) | Access control method, access control device, system and storage medium | |
| CN109214276A (en) | A kind of system and method for the target person track following based on face recognition technology | |
| JP2020520511A (en) | Access control method and apparatus, system, electronic device, program and medium | |
| CN105261105A (en) | Safety access control method | |
| CN101826227A (en) | Triple-authentication gate control system and control method | |
| CN102567686A (en) | Security authentication method of application software of mobile terminal based on human body stable characteristics | |
| CN103384234A (en) | Method and system for face identity authentication | |
| US20220046012A1 (en) | Method and System for Verifying the Identity of a User | |
| CN105844247A (en) | Bi-camera cabinet machine and face recognition and second-generation ID card identification system | |
| CN106710032B (en) | Entrance guard opening method and device | |
| WO2023173785A1 (en) | Access permission verification method, device, and system and identity authentication terminal | |
| CN111831995A (en) | Trusted identity authentication method and system based on eID and human body biological information | |
| CN114218543A (en) | Encryption and unlocking system and method based on multi-scene expression recognition | |
| CN202815870U (en) | Certificate photograph and face automatic identification system | |
| CN109981525A (en) | Identity information authentication method, terminal, server and system | |
| CN105184236A (en) | Robot-based face identification system | |
| US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
| CN212160688U (en) | Face recognition integrated front-end device with biological feature privacy protection function | |
| CN106710033B (en) | Entrance guard opening method and device | |
| CN116311457A (en) | Application capable of adapting to portrait identification of various service terminals | |
| CN104915661A (en) | Intelligent dynamic human face encryption recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231030 Address after: No.17, 3rd Floor, Tengda Building, No. 168 Xizhimenwai Street, Haidian District, Beijing, 100080 Applicant after: BEIJING BITE YIPAI INFORMATION TECHNOLOGY Co.,Ltd. Address before: No.10, 3rd Floor, Tengda Building, No. 168 Xizhimenwai Street, Haidian District, Beijing, 100080 Applicant before: Beijing BITAUTO Mdt InfoTech Ltd. |