CN112491924B - Cross-platform face recognition login method, system and storage medium - Google Patents
Cross-platform face recognition login method, system and storage medium Download PDFInfo
- Publication number
- CN112491924B CN112491924B CN202011450934.7A CN202011450934A CN112491924B CN 112491924 B CN112491924 B CN 112491924B CN 202011450934 A CN202011450934 A CN 202011450934A CN 112491924 B CN112491924 B CN 112491924B
- Authority
- CN
- China
- Prior art keywords
- face recognition
- client
- login
- video
- comparison result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/65—Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/643—Communication protocols
- H04N21/6437—Real-time Transport Protocol [RTP]
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to the field of face recognition, in particular to a cross-platform face recognition login method, a cross-platform face recognition login system and a storage medium. The cross-platform face recognition login method comprises the following steps: the method comprises the steps that a client side obtains real-time video data, codes the real-time video data to obtain a video code, and sends the video code to a face recognition server side; the face recognition server decodes the video code to obtain a video original code stream, compares the video original code stream with data in an image library storing user information to obtain a comparison result, and sends the comparison result to a scheduling main service end; and the scheduling main service end judges whether the client needs to realize the login function according to the comparison result, if so, the logging instruction is scheduled, the logging instruction is used for enabling the client to realize the login, and if not, the logging instruction is not scheduled, and the client does not realize the login. The invention can realize the face recognition login function of the client installed on different platforms.
Description
Technical Field
The invention relates to the field of face recognition, in particular to a cross-platform face recognition login method, a cross-platform face recognition login system and a storage medium.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. A series of related technologies, also commonly called face recognition and face recognition, are used to collect images or video streams containing faces by using a camera or a video camera, automatically detect and track the faces in the images, and then perform face recognition on the detected faces. The face recognition system mainly comprises four components, which are respectively: the method comprises the steps of face image acquisition and detection, face image preprocessing, face image feature extraction, matching and identification.
With the popularization of face recognition technology, more and more devices and types can realize face recognition login functions, and when a same client needs to perform face recognition login on mobile devices on different platforms (IOS, Android, Windows, and the like), how to realize the face recognition login functions of the clients installed on the different platforms becomes more important in order to meet the requirements of the mobile devices on the different platforms for using face recognition login.
Disclosure of Invention
The present invention is directed to overcome at least one of the above-mentioned drawbacks (disadvantages) of the prior art, and provides a cross-platform face recognition login method, system and storage medium, which are used to solve the problem of face recognition login of clients installed on different platforms.
The technical scheme adopted by the invention is to provide a cross-platform face recognition login method, which comprises the following steps: the method comprises the steps that a client side obtains real-time video data, codes the real-time video data to obtain a video code, and sends the video code to a face recognition server side; the face recognition server decodes the video code to obtain a video original code stream, compares the video original code stream with data in an image library storing user information to obtain a comparison result, and sends the comparison result to a scheduling main service end; and the scheduling main service terminal judges whether the client terminal needs to realize the login function according to the comparison result, if so, schedules a login instruction and sends the login instruction to the client terminal to enable the client terminal to realize login, and if not, does not schedule the login instruction or schedules a non-login instruction and sends the non-login instruction to the client terminal to enable the client terminal not to realize login.
Preferably, the client can be installed on the platform of iOS, Android, Windows, and the like. The client should be installed on a hardware device with a camera, such as a mobile phone with a camera, a computer, etc. The client can obtain real-time video data with user information through a camera of the starting device, encode the real-time video data to obtain a video code, and then send the video code to the face recognition server, and the face recognition server decodes the video code to obtain a video original code stream with the user information.
And the face recognition server is stored with an image library, and the image library is stored with the user information of the client and used for comparing with the decoded video original code stream with the user information. If the user information of the user is stored in the image library, the user can successfully match the video original code stream with the user information by indicating that the user registers the account of the client once, the user can log in the client, namely the client needs to realize a login function, the face recognition server sends a comparison result, namely the user information of the user, to the scheduling main service end, the scheduling main service end recognizes the user information of the user and schedules a login instruction to send to the client, and the client logs in the account registered by the user according to the login instruction; if the user information of the user is not stored in the image library, the user cannot be successfully matched with the original video code stream with the user information if the user does not register the account of the client, and the comparison result at this moment is that the user cannot log in the client, and the scheduling main service terminal does not recognize the user information of the user, the login instruction or the instruction which cannot log in cannot be scheduled, so that the client cannot realize the login function.
The cross-platform face recognition login method provided by the invention can realize the cross-platform login function of the client, and brings great convenience to users.
Further, the client is integrated with WebRTC; the method for acquiring the real-time video data from the client and coding the real-time video data to obtain the video code comprises the following steps of: the method comprises the steps that real-time video data are obtained from a client side based on WebRTC and are encoded to obtain video codes, and a WebRTC opening channel sends the video codes to a face recognition server side.
The WebRTC is an open source library, can support a plurality of different platforms, and can help clients installed on different platforms, such as iOS, Android, Windows and the like, to realize a face recognition login function. The client can start the camera of the hardware equipment and acquire real-time video data with user information through the camera starting function of the open source library WebRTC, and the real-time video data is encoded based on the WebRTC to obtain a video code. Preferably, the WebRTC starts a video transmission channel to transmit the video code to the face recognition server network in real time. The method has the advantages that the real-time video data acquisition, encoding and network real-time transmission are realized based on the open source library WebRTC, the development cost can be reduced, and the development efficiency can be improved.
Further, the face recognition server is integrated with WebRTC; the decoding of the video code by the face recognition server specifically comprises the following steps: and the face recognition server calls the WebRTC to decode the received video code to obtain a video original code stream. The open source library WebRTC is used for decoding the video code, so that the development cost is reduced and the development efficiency is improved.
Furthermore, the face recognition service terminal is integrated with a Dlib library, the Dlib library is used for loading the image library, receiving the video original code stream, comparing the video original code stream with data in the image library to obtain a comparison result, and sending the comparison result to the scheduling main service terminal through an interface.
The Dlib library is an open-source face recognition library, and when the Dlib library is initialized, an image library stored in a face recognition server is loaded. And the WebRTC inputs the decoded video original code stream with the user information into a Dlib library, and the Dlib library compares the video original code stream with the user information stored in the image library. If the user information of the user is stored in the image library, the user can successfully match the video original code stream with the user information after the user registers the account of the client, the user can log in the client, namely the client needs to realize a login function, the Dlib library sends a comparison result, namely the user information of the user, to a scheduling main service end through a face comparison interface, the scheduling main service end identifies the user information of the user and schedules a login instruction to send to the client, and the client logs in the account registered by the user according to the login instruction; if the user information of the user is not stored in the image library, the result shows that the user does not register the account number of the client, the user cannot be successfully matched with the original video code stream with the user information, the comparison result at this moment is that the user cannot log in the client, the Dlib library cannot send the user information of the user to the dispatching main service end, and the dispatching main service end does not recognize the user information of the user, and then a login instruction or a command that the dispatching cannot log in cannot be scheduled, so that the client cannot realize a login function.
By comparing the video original code stream with the user information, whether the user registers the account of the client or not can be judged, if the user registers the account, the user can log in the client, and if the user does not register the account, the user cannot log in the client.
The method comprises the steps of comparing an original video code stream with user information based on the existing open-source Dlib library to obtain a comparison result, and can reduce development cost and improve development efficiency.
Further, the comparison result is specifically a face recognition result.
The comparison result is a face recognition result obtained by comparing a video original code stream with user information stored in an image library by a digital library, when the video original code stream is successfully matched with the user information, the face recognition result is the user information of the user, the digital library sends the comparison result, namely the user information of the user to a dispatching main service end through a face comparison interface, the dispatching main service end identifies the user information of the user and dispatches a login instruction to a client, and the client logs in an account registered by the user according to the login instruction; if the video original code stream cannot be successfully matched with the user information, the face recognition result indicates that the user cannot log in the client, the Dlib library cannot send the user information of the user to the scheduling main service end, and the scheduling main service end does not recognize the user information of the user, then a login instruction or a command which cannot log in is scheduled, so that the client cannot realize a login function.
Further, the client specifically implements login as follows: and the client side makes page jump or user prompt after receiving the login instruction. And after receiving the login instruction, the client logs in the account registered by the user to realize the cross-platform login function.
Further, before the real-time video data is obtained from the client and encoded to obtain the video code, the following steps are also performed: and the client starts a face recognition login function.
The invention also provides a multi-platform face recognition login system, which comprises a client, a face recognition server, a scheduling main service end and an image library; the client is used for obtaining real-time video data, coding the real-time video data to obtain a video code and sending the video code to the face recognition server; the face recognition server is used for decoding the video code to obtain a video original code stream, comparing the video original code stream with data stored in an image library to obtain a comparison result, and sending the comparison result to a scheduling main service end; and the scheduling main service end is used for judging whether the client needs to realize the login function according to the comparison result, if so, scheduling the login instruction and sending the login instruction to the client so as to realize the login of the client, and if not, not scheduling the login instruction and not realizing the login of the client.
Further, the client integrates a WebRTC, the face recognition server integrates the WebRTC and a Dlib library, the client is used for coding the obtained real-time video data by calling the WebRTC to obtain a video code, and the face recognition server decodes the video code by calling the WebRTC to obtain a video original code stream and inputs the video original code stream into the Dlib library; and the Dlib library is used for loading an image library, comparing the video original code stream with data stored in the image library to obtain a comparison result and sending the comparison result to a dispatching main service end through an interface.
The cross-platform face recognition login system can realize face recognition login of clients installed on different platforms, so that a user can conveniently and rapidly perform face recognition login on the clients installed on different platforms, such as iOS, Android, Windows and the like. And the existing open source library WebRTC and the Dlib library can be directly called to realize the cross-platform face recognition login function, so that the development cost is reduced, and the development efficiency is improved.
The invention also provides a storage medium for storing a computer program, and the computer program realizes the cross-platform face recognition login method when executed and realizes the face recognition login function of the client installed on different platforms.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention can realize the function of face recognition login of the client on different platforms and bring convenience to users.
2. The invention adopts the prior open source library WebRTC which can support different platforms, solves the problems of acquisition and coding, video code decoding, network transmission and the like of real-time video data, reduces the development cost, improves the development efficiency and realizes the login of clients of different platforms.
3. The invention compares the video original code stream with the user information based on the existing open-source Dlib library to obtain a comparison result, thereby reducing the development cost and improving the development efficiency.
Drawings
Fig. 1 is a first flowchart of a cross-platform face recognition login method according to embodiment 1 of the present invention.
Fig. 2 is a second flowchart of a cross-platform face recognition login method according to embodiment 1 of the present invention.
Fig. 3 is a system diagram of a cross-platform face recognition login system according to embodiment 2 of the present invention.
Detailed Description
The drawings are only for purposes of illustration and are not to be construed as limiting the invention. For a better understanding of the following embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
Example 1
As shown in fig. 1, the present embodiment provides a cross-platform face recognition login method, including:
s1: the method comprises the steps that a client side obtains real-time video data, codes the real-time video data to obtain a video code, and sends the video code to a face recognition server side;
s2: the face recognition server side decodes the video code to obtain a video original code stream;
s3: the face recognition server compares the original video code stream with data in an image library storing user information to obtain a comparison result, and sends the comparison result to a scheduling main service end;
s4: and the scheduling main service terminal judges whether the client terminal needs to realize the login function according to the comparison result, if so, schedules a login instruction and sends the login instruction to the client terminal to enable the client terminal to realize login, and if not, does not schedule the login instruction or schedules a non-login instruction to be sent to the client terminal to enable the client terminal not to realize login.
The client side realizes the operation of logging in or not according to the received instruction, such as a login instruction or a non-login instruction, scheduled by the scheduling main service side.
Further, S1 is preceded by performing S0, S0: and the client starts a face recognition login function.
Preferably, the client can be installed on the platform of iOS, Android, Windows, and the like. The client should be installed on a hardware device with a camera, such as a mobile phone with a camera, a computer, etc. The client can obtain real-time video data with user information through a camera of the starting device, encode the real-time video data to obtain a video code, and then send the video code to the face recognition server, and the face recognition server decodes the video code to obtain a video original code stream with the user information.
And the face recognition server is stored with an image library, and the image library is stored with the user information of the client and used for comparing with the decoded video original code stream with the user information. If the user information of the user is stored in the image library, the user can successfully match the video original code stream with the user information by indicating that the user registers the account of the client once, the user can log in the client, namely the client needs to realize a login function, the face recognition server sends a comparison result, namely the user information of the user, to the scheduling main service end, the scheduling main service end recognizes the user information of the user and schedules a login instruction to send to the client, and the client logs in the account registered by the user according to the login instruction; if the user information of the user is not stored in the image library, the user cannot be successfully matched with the original video code stream with the user information if the user does not register the client account, and the comparison result at this moment is that the user cannot log in the client, and the scheduling main service terminal does not recognize the user information of the user, the login instruction or the instruction which cannot log in cannot be scheduled, so that the client cannot realize the login function.
By comparing the video original code stream with the user information, whether the user registers the account of the client or not can be judged, if the user registers the account, the user can log in the client, and if the user does not register the account, the user cannot log in the client.
The cross-platform face recognition login method provided by the embodiment can realize the face recognition login function of the client on different platforms, and brings great convenience to users.
Further, the client is integrated with WebRTC; the method for acquiring the real-time video data from the client and coding the real-time video data to obtain the video code comprises the following steps of: the method comprises the steps that real-time video data are obtained from a client side based on WebRTC and are encoded to obtain video codes, and a WebRTC opening channel sends the video codes to a face recognition server side.
WebRTC is an open source library and can support a number of different platforms, such as iOS, Android, Windows, etc. The client can start the camera of the hardware equipment and acquire real-time video data with user information through the camera starting function of the open source library WebRTC, and the real-time video data is encoded based on the WebRTC to obtain a video code. Preferably, the WebRTC starts a video transmission channel to transmit the video code to the face recognition server network in real time. The method has the advantages that the real-time video data acquisition, encoding and network real-time transmission are realized based on the open source library WebRTC, the development cost can be reduced, and the development efficiency can be improved.
Further, the face recognition server is integrated with WebRTC; the decoding of the video code by the face recognition server specifically comprises the following steps: and the face recognition server calls the WebRTC to decode the received video code to obtain a video original code stream. The open source library WebRTC is used for decoding the video code, so that the development cost is reduced and the development efficiency is improved.
Furthermore, the face recognition service terminal is integrated with a Dlib library, the Dlib library is used for loading the image library, receiving the video original code stream, comparing the video original code stream with data in the image library to obtain a comparison result, and sending the comparison result to the scheduling main service terminal through an interface.
The Dlib library is an open-source face recognition library, and when the Dlib library is initialized, an image library stored in a face recognition server is loaded. And the WebRTC inputs the decoded video original code stream with the user information into a Dlib library, and the Dlib library compares the video original code stream with the user information stored in the image library. If the user information of the user is stored in the image library, the user can successfully match the video original code stream with the user information after the user registers the account of the client, the user can log in the client, namely the client needs to realize a login function, the Dlib library sends a comparison result, namely the user information of the user, to a scheduling main service end through a face comparison interface, the scheduling main service end identifies the user information of the user and schedules a login instruction to send to the client, and the client logs in the account registered by the user according to the login instruction; if the user information of the user is not stored in the image library, the user cannot be successfully matched with the original video code stream with the user information if the user does not register the account number of the client, the comparison result at this moment is that the user cannot log in the client, the Dlib library cannot send the user information of the user to the dispatching main service end, and the dispatching main service end does not identify the user information of the user, the login instruction cannot be dispatched, so that the client cannot realize the login function.
The method comprises the steps of comparing an original video code stream with user information based on the existing open-source Dlib library to obtain a comparison result, and can reduce development cost and improve development efficiency.
Further, the comparison result is specifically a face recognition result.
The comparison result is a face recognition result obtained by comparing a video original code stream with user information stored in an image library by a digital library, when the video original code stream is successfully matched with the user information, the face recognition result is the user information of the user, the digital library sends the comparison result, namely the user information of the user to a dispatching main service end through a face comparison interface, the dispatching main service end identifies the user information of the user and dispatches a login instruction to a client, and the client logs in an account registered by the user according to the login instruction; if the video original code stream cannot be successfully matched with the user information, the face recognition result indicates that the user cannot log in the client, the Dlib library cannot send the user information of the user to the scheduling main service end, and the scheduling main service end does not recognize the user information of the user, then a login instruction or a command which cannot log in is scheduled, so that the client cannot realize a login function.
Further, the client specifically implements login as follows: and the client side makes page jump or user prompt after receiving the login instruction. And after receiving the login instruction, the client logs in the account registered by the user to realize the cross-platform login function.
As a specific and preferred implementation manner of this embodiment, a WebRTC is integrated on a client, a WebRTC and a Dlib library are integrated on a face recognition server, and the face recognition server includes an image library storing user information, as shown in fig. 2, the cross-platform face recognition login method includes the following steps:
a0: the client starts a face recognition login function, initializes the Dlib library and loads the image library;
a1: the client acquires real-time video data based on the WebRTC camera opening function.
A2: the client encodes real-time video data based on WebRTC to obtain a video code, and sends the video code to the face recognition server.
A3: and the face recognition server decodes the video code based on WebRTC to obtain a video original code stream, and sends the video original code stream to a Dlib library.
A4: and the face recognition server compares the original video code stream with data in an image library in which user information is stored on the basis of the Dlib library to obtain a comparison result.
A5: and the Dlib library sends the comparison result to a scheduling main service end through an interface.
If the user information of the user is stored in the image library, the user can successfully match the video original code stream with the user information by registering the account number of the client once, the user can log in the client, namely the client needs to realize a login function, and the Dlib library sends a comparison result, namely the user information of the user, to a scheduling main service end through a face comparison interface;
if the user information of the user is not stored in the image library, the user cannot be successfully matched with the original video code stream with the user information if the user does not register the account number of the client, and the comparison result is that the user cannot log in the client.
A6: and the scheduling main service terminal judges whether the client terminal needs to realize the login function according to the comparison result, if so, schedules a login instruction and sends the login instruction to the client terminal to enable the client terminal to realize login, and if not, does not schedule the login instruction or schedules a non-login instruction to be sent to the client terminal to enable the client terminal not to realize login.
When the client needs to realize the login function, the scheduling main service terminal identifies the user information of the user and schedules a login instruction to send to the client, and the client logs in the account registered by the user according to the login instruction;
when the client does not need to realize the login function, the Dlib library cannot send the user information of the user to the scheduling main service end, and the scheduling main service end cannot schedule the login instruction or the instruction which cannot be logged in if the user information of the user is not identified, so that the client cannot realize the login function.
The client side realizes the operation of logging in or not according to the received instruction, such as a login instruction or a non-login instruction, which is scheduled by the scheduling main service side.
The method comprises the steps of obtaining real-time video data based on the existing open source library WebRTC, coding and decoding the real-time video data to obtain a video original code stream, comparing the video original code stream with user information stored in an image library based on a Dlib library to obtain a comparison result, realizing a cross-platform face recognition login function of a client, reducing development cost, improving development efficiency, and realizing face recognition login without developing a corresponding function library by self.
Example 2
As shown in fig. 3, the present embodiment provides a cross-platform face recognition login system, which includes a client, a face recognition server, a scheduling main server, and an image library; the client is used for obtaining real-time video data, coding the real-time video data to obtain a video code and sending the video code to the face recognition server; the face recognition server is used for decoding the video code to obtain a video original code stream, comparing the video original code stream with data stored in an image library to obtain a comparison result, and sending the comparison result to a scheduling main service end; and the scheduling main service end is used for judging whether the client needs to realize the login function according to the comparison result, if so, scheduling the login instruction and sending the login instruction to the client so as to enable the client to realize login, and if not, not scheduling the login instruction or scheduling not to send the login instruction to the client so as to enable the client not to realize login.
And the client executes login or non-login operation according to the received instruction scheduled by the scheduling main service terminal.
Further, the client integrates a WebRTC, the face recognition server integrates the WebRTC and a Dlib library, the client is used for coding the obtained real-time video data by calling the WebRTC to obtain a video code, and the face recognition server decodes the video code by calling the WebRTC to obtain a video original code stream and inputs the video original code stream into the Dlib library; and the Dlib library is used for loading an image library, comparing the video original code stream with data stored in the image library to obtain a comparison result and sending the comparison result to a dispatching main service end through an interface.
The cross-platform face recognition login system can realize face recognition login of clients of different platforms such as iOS, Android, Windows and the like. And the existing open source library WebRTC and the Dlib library can be directly called to realize the cross-platform face recognition login function, so that the development cost is reduced, and the development efficiency is improved.
Example 3
The present embodiment provides a storage medium storing a computer program, and the computer program, when executed, implements the cross-platform face recognition login method according to embodiment 1.
The cross-platform face recognition login method is realized through the computer program on the storage medium, so that a user can conveniently and quickly log in clients on different platforms through face recognition.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific embodiments of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention claims should be included in the protection scope of the present invention claims.
Claims (6)
1. A cross-platform face recognition login method is characterized by comprising the following steps:
the method comprises the steps that a client side obtains real-time video data, codes the real-time video data to obtain a video code, and sends the video code to a face recognition server side;
the face recognition server decodes the video code to obtain a video original code stream, compares the video original code stream with data in an image library storing user information to obtain a comparison result, and sends the comparison result to a scheduling main service end;
the scheduling main service terminal judges whether the client terminal needs to realize the login function according to the comparison result, if so, the logging instruction is scheduled and sent to the client terminal so as to enable the client terminal to realize the login, and if not, the logging instruction is not scheduled or the non-logging instruction is scheduled and sent to the client terminal so as to enable the client terminal not to realize the login;
the client side is provided with integrated WebRTC;
the method comprises the following steps that the client side obtains real-time video data and encodes the real-time video data to obtain a video code, and the step of sending the video code to the face recognition server side specifically comprises the following steps: the method comprises the steps that real-time video data are obtained from a client side based on WebRTC and are encoded to obtain video codes, and a WebRTC opening channel sends the video codes to a face recognition server side;
the face recognition server is integrated with WebRTC;
the decoding of the video code by the face recognition server specifically comprises the following steps: the face recognition server calls WebRTC to decode the received video code to obtain a video original code stream;
the face recognition server integrates a Dlib library, the Dlib library is used for loading the image library, receiving the original video code stream, comparing the original video code stream with data in the image library to obtain a comparison result, and sending the comparison result to a scheduling main service end through an interface.
2. The cross-platform face recognition login method according to claim 1, wherein the comparison result is specifically a face recognition result.
3. The cross-platform face recognition login method according to claim 1, wherein the client side specifically implements login as: and the client side makes page jump or user prompt after receiving the login instruction.
4. The cross-platform face recognition login method according to any one of claims 1 to 3, wherein before the obtaining of the real-time video data from the client and the encoding thereof to obtain the video code, further performing: and the client starts a face recognition login function.
5. A cross-platform face recognition login system is characterized by comprising a client, a face recognition server, a scheduling main server and an image library;
the client is used for obtaining real-time video data, coding the real-time video data to obtain a video code and sending the video code to the face recognition server;
the face recognition server is used for decoding the video code to obtain a video original code stream, comparing the video original code stream with data stored in an image library to obtain a comparison result, and sending the comparison result to a scheduling main service end;
the scheduling main service end is used for judging whether the client needs to realize the login function according to the comparison result, if so, scheduling the login instruction and sending the login instruction to the client so as to enable the client to realize login, and if not, not scheduling the login instruction or scheduling not to send the login instruction to the client so as to enable the client not to realize login;
the client is integrated with WebRTC, the face recognition server is integrated with WebRTC and a Dlib library, the client is used for coding the obtained real-time video data by calling the WebRTC to obtain a video code, and the face recognition server is used for decoding the video code by calling the WebRTC to obtain a video original code stream and inputting the video original code stream into the Dlib library; and the Dlib library is used for loading an image library, comparing the video original code stream with data stored in the image library to obtain a comparison result and sending the comparison result to a dispatching main service end through an interface.
6. A storage medium storing a computer program which, when executed, implements a cross-platform face recognition login method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011450934.7A CN112491924B (en) | 2020-12-09 | 2020-12-09 | Cross-platform face recognition login method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011450934.7A CN112491924B (en) | 2020-12-09 | 2020-12-09 | Cross-platform face recognition login method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112491924A CN112491924A (en) | 2021-03-12 |
| CN112491924B true CN112491924B (en) | 2022-03-22 |
Family
ID=74941753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011450934.7A Active CN112491924B (en) | 2020-12-09 | 2020-12-09 | Cross-platform face recognition login method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112491924B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105530453A (en) * | 2015-12-29 | 2016-04-27 | 苏州科达科技股份有限公司 | Video data sending method and device and video data receiving method and device for WebRTC |
| CN106886697A (en) * | 2015-12-15 | 2017-06-23 | ***通信集团公司 | Authentication method, authentication platform, user terminal and Verification System |
| CN108777692A (en) * | 2018-06-25 | 2018-11-09 | 北京蜂盒科技有限公司 | Method, apparatus, electronic equipment, login service device and the medium that user logs in |
| CN108985036A (en) * | 2018-06-25 | 2018-12-11 | 北京蜂盒科技有限公司 | Method, apparatus, electronic equipment, login service device and the medium that user logs in |
| CN109151387A (en) * | 2018-08-27 | 2019-01-04 | 杭州当虹科技股份有限公司 | A kind of dollying head recognition of face low latency solution based on webRTC |
| CN109218670A (en) * | 2018-09-14 | 2019-01-15 | 广州高清视信数码科技股份有限公司 | A kind of smart home security monitoring system and method based on WebRTC |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9270822B2 (en) * | 2012-08-14 | 2016-02-23 | Avaya Inc. | Protecting privacy of a customer and an agent using face recognition in a video contact center environment |
| CN106228628B (en) * | 2016-07-15 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Check-in system, method and device based on face recognition |
-
2020
- 2020-12-09 CN CN202011450934.7A patent/CN112491924B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886697A (en) * | 2015-12-15 | 2017-06-23 | ***通信集团公司 | Authentication method, authentication platform, user terminal and Verification System |
| CN105530453A (en) * | 2015-12-29 | 2016-04-27 | 苏州科达科技股份有限公司 | Video data sending method and device and video data receiving method and device for WebRTC |
| CN108777692A (en) * | 2018-06-25 | 2018-11-09 | 北京蜂盒科技有限公司 | Method, apparatus, electronic equipment, login service device and the medium that user logs in |
| CN108985036A (en) * | 2018-06-25 | 2018-12-11 | 北京蜂盒科技有限公司 | Method, apparatus, electronic equipment, login service device and the medium that user logs in |
| CN109151387A (en) * | 2018-08-27 | 2019-01-04 | 杭州当虹科技股份有限公司 | A kind of dollying head recognition of face low latency solution based on webRTC |
| CN109218670A (en) * | 2018-09-14 | 2019-01-15 | 广州高清视信数码科技股份有限公司 | A kind of smart home security monitoring system and method based on WebRTC |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112491924A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110176256B (en) | Recording file format conversion method and device, computer equipment and storage medium | |
| CN110730274B (en) | Voice packet capture analysis method, system, mobile terminal and storage medium | |
| CN112637428A (en) | Invalid call judgment method and device, computer equipment and storage medium | |
| CN113395523B (en) | Image decoding method, device, equipment and storage medium based on parallel threads | |
| CN114419527B (en) | Data processing method, equipment and computer readable storage medium | |
| CN111063006A (en) | Image-based literary work generation method, device, equipment and storage medium | |
| CN112491924B (en) | Cross-platform face recognition login method, system and storage medium | |
| CN116668691A (en) | Picture compression transmission method and device and terminal equipment | |
| CN115774762A (en) | Instant messaging information processing method, device, equipment and storage medium | |
| CN108401070B (en) | Mobile phone and unbinding reminding method | |
| CN112133306B (en) | Response method and device based on express delivery user and computer equipment | |
| CN110765869B (en) | Lip language living body detection method, system and computer equipment for collecting data by channels | |
| EP1860647B1 (en) | Robust speaker recognition | |
| CN111541864B (en) | Digital retina software defined camera method and system | |
| CN112511706A (en) | Voice stream obtaining method and system suitable for non-invasive bypass telephone | |
| CN112165594A (en) | Service handling method and device based on video communication and computer equipment | |
| CN111081247A (en) | Method for speech recognition, terminal, server and computer-readable storage medium | |
| CN112151069A (en) | Voice data processing method and device, computer equipment and storage medium | |
| CN110868615B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN113298074B (en) | Image recognition method and device, computer readable storage medium and processor | |
| CN116647727B (en) | Screen recording information collection method, device, equipment and storage medium | |
| CN117880562A (en) | Data processing method, device, equipment and storage medium | |
| CN116366862A (en) | Video file compression method and system based on Redis message | |
| CN112565254B (en) | Data transmission method, device, equipment and computer readable storage medium | |
| US11871068B1 (en) | Techniques for detecting non-synchronization between audio and video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240418 Address after: Room 303, 3rd Floor, No. 27, Changlin 801, Xisanqi, Haidian District, Beijing, 100000 Patentee after: Beijing Gengtu Technology Co.,Ltd. Country or region after: China Address before: 233 Kezhu Road, Guangzhou hi tech Industrial Development Zone, Guangdong 510670 Patentee before: VTRON GROUP Co.,Ltd. Country or region before: China |