CN105979363A - Identity identification method and device - Google Patents
Identity identification method and device Download PDFInfo
- Publication number
- CN105979363A CN105979363A CN201510757889.2A CN201510757889A CN105979363A CN 105979363 A CN105979363 A CN 105979363A CN 201510757889 A CN201510757889 A CN 201510757889A CN 105979363 A CN105979363 A CN 105979363A
- Authority
- CN
- China
- Prior art keywords
- face
- picture data
- identification
- far
- face picture
- 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
Classifications
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
- H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
Abstract
The embodiment of the invention provides an identity identification method and device. The method comprises: obtaining the picture data of each frame shot by the camera of an intelligent television through an identity identification service interface; respectively detecting the picture data of each frame, and generating the face picture data and the face identification; uploading the face picture data to a far-end server for identification, and determining an identity identification result; and determining the user identity corresponding to the face identification according to the identity identification result. According to the embodiment of the invention, the identity identification method and device obtain picture data through the identity identification service interface of the intelligent television and perform face identification of the obtained picture data so as to allow the intelligent television to satisfy the requirements for the face identification and identity identification service and reduce the workload of the development of application programs with no need for integrating a face identification module by using the application programs of the intelligent television.
Description
Technical field
The present invention relates to multimedia data processing field, particularly relate to a kind of personal identification method and a kind of identity recognition device.
Background technology
Intelligent television is to comply with television set " high Qinghua ", " networking ", the trend of " intelligent " and a kind of intelligent multimedia terminal of occurring, possess from the Internet, the multiple channel such as video equipment, computer obtains programme content, the function that content consumer needed most by integrated operation interface easy to use is clearly represented on giant-screen.Compared with the application platform of traditional tv, intelligent television can realize the various application services such as web search, Web TV, video request program (VOD), digital music, Internet news, network video telephone.
Along with the development of intelligent interaction TV, in order to improve the experience effect of user, on intelligent television, generally it is mounted with photographic head, such that it is able to use intelligent television to take pictures and record a video.Wherein, the photograph that photographic head photographs may be used for identifying the identity information of user.
At present, the upper level applications being arranged in intelligent television can use the photograph identification user identity that intelligent television photographs.But, intelligent television can not support user identity identification, and Face datection function.Therefore, each upper level applications of intelligent television needs integrated face recognition module, just can be based on photograph identification identity.Specifically, after each upper level applications receives photograph, the yuv data of this photograph is transferred to respective algorithm layer and detects respectively, thus identify identity information.
The developer of each upper level applications have employed different solutions, and the recognizer of employing is uneven so that the complete disunity of recognition result of each upper level applications, causes the recognition result can not multiplexing.
Obviously, existing intelligent television can not support Face datection function, needs the integrated face recognition module of application program, while increasing the workload of application program, adds the operating pressure of intelligent television, and adds the workload of exploitation application program.
Summary of the invention
Embodiment of the present invention technical problem to be solved is to provide a kind of personal identification method so that intelligent television supports face identification functions, while reducing the operating pressure of intelligent television, reduces the workload of exploitation application program.
Accordingly, the embodiment of the present invention additionally provides a kind of identity recognition device, in order to ensure realization and the application of said method.
In order to solve the problems referred to above, the embodiment of the invention discloses a kind of personal identification method, including:
By identification service interface, obtain each frame image data captured by photographic head of intelligent television；
Every frame image data is detected respectively, generates face picture data and face mark；
Described face picture data being uploaded to far-end server be identified, determine one's identity recognition result；
The user identity that described face mark is corresponding is determined according to described identification result.
Accordingly, the embodiment of the invention also discloses identity recognition device, including:
Image data acquisition module, for by identification service interface, obtaining each frame image data captured by photographic head of intelligent television；
Detection module, for detecting every frame image data respectively, generates face picture data and face mark；
Identification module, is identified for described face picture data are uploaded to far-end server, and determine one's identity recognition result；
User identity determines module, for determining, according to described identification result, the user identity that described face mark is corresponding.
Compared with prior art, the embodiment of the present invention includes advantages below:
The embodiment of the present invention can obtain image data by the identification service interface of intelligent television, the image data got is carried out recognition of face, make intelligent television can meet recognition of face, the demand of identity detection service, it is not necessary to the integrated face recognition module of application program of intelligent television.
The embodiment of the present invention while reducing the operating pressure of intelligent television, can reduce the workload of application program, and reduces the workload of exploitation application program.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in describing below is some embodiments of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of steps of a kind of personal identification method embodiment of the present invention；
Fig. 2 is the flow chart of steps of the another kind of personal identification method embodiment of the present invention；
Fig. 3 is the step schematic diagram that a kind of intelligent television of the present invention carries out identification execution to user；
Fig. 4 is the structured flowchart of a kind of identity recognition device embodiment of the present invention；
Fig. 5 is the structured flowchart of a kind of identity recognition device preferred embodiment of the application.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under not making creative work premise, broadly fall into the scope of protection of the invention.
Intelligent television, is to have full open model platform, is equipped with operating system, and user, while appreciating general television content, can install and uninstall types of applications software, the new tv product persistently expanding function and upgrading voluntarily.Intelligent television constantly can bring to user and be different from, and uses individualized experience wired digital teleset (Set Top Box), abundant
At present, intelligent TV set incorporates camera module, can photograph image data by photographic head.But, do not provide identification service interface due to intelligent television, it is impossible to carrying out recognition of face by the image data captured by photographic head, therefore intelligent television does not support user identity identification, and Face datection function.
For above-mentioned technical problem, one of core idea of the embodiment of the present invention is, by identification service interface, obtain the image data captured by photographic head, and image data is detected, generate face picture data, then adopt face picture data to be identified, determine user identity, so that intelligent television supports identification and face identification functions, without the integrated face recognition module of application program of intelligent television, while reducing the operating pressure of intelligent television, reduce the workload of exploitation application program.
With reference to Fig. 1, it is shown that the flow chart of steps of a kind of personal identification method embodiment of the present invention, specifically may include steps of:
Step 101, by identification service interface, obtains each frame image data captured by photographic head of intelligent television.
In implementing, intelligent television can be by integrating camera module, it is provided that real-time identity recognition function.Specifically, the photographic head of the camera module of intelligent television can be used to shoot, each frame image data captured by this photographic head can be got by the identification service interface of the ccf layer of intelligent television.
A concrete example as the embodiment of the present invention, when application A PP1 of intelligent television needs that user is carried out identification, by the photographic head being arranged on intelligent television, user can be shot, by calling identification service interface, each frame image data captured by photographic head is transferred to the ccf layer of intelligent television, and yuv data is transferred to the identification service interface of ccf layer by application A PP1 being i.e. equivalent to intelligent television.
It should be noted that a kind of colour coding method that YUV is television system to be used, wherein " Y " represents lightness (Luminance or Luma), namely grey decision-making；That " U " and " V " represents is then colourity (Chrominance or Chroma), and effect is to describe colors of image and saturation, for the color of specified pixel.
Step 103, detects respectively to every frame image data, generates face picture data and face mark.
In embodiments of the present invention, the ccf layer of intelligent television can get image data by identification service interface, then can use preset local algorithm that every frame image data is processed, obtain face location information, according to the facial image in this frame image data of face location information interception, generate face picture data.Facial image can include the facial characteristics of user, face picture data based on Face image synthesis, such as include the central point of face, left eye coordinates, right eye coordinate, left side corners of the mouth coordinate, right side corners of the mouth coordinate, any of which or the characteristic informations of several face feature point such as nose coordinate, interpupillary distance, this is not restricted by the embodiment of the present invention.For same user, its facial characteristics should be identical.Therefore, for same user, every frame image data generates the face picture data of this user can keep consistent, thus can be identified user by face picture data.
It addition, by face picture data analysis, it is also possible to determine that face identifies, in order in the data that the face of the locally stored each user of TV is relevant.Such as, based on the interpupillary distance in face picture data and left eye coordinates, face mark can be generated.Thus using face mark for marking user, the most each user is by unique face mark for marking.Therefore, face mark determines according to face picture data, and for different user, the face mark of its correspondence differs.
It should be noted that face mark can represent with character string or serial number, this is not any limitation as by the embodiment of the present invention.
Described face picture data are uploaded to far-end server and are identified by step 105, and determine one's identity recognition result.
In practice, far-end server pre-sets face recognition algorithms.Intelligent television can be identified by image data is uploaded to far-end server, it is also possible to the face picture data after local algorithm process being uploaded far-end server and is identified, this is not any limitation as by the embodiment of the present invention.
In embodiments of the present invention, it is preferably and face picture data are uploaded far-end server, face picture data can be identified by i.e. far-end server by face recognition algorithms, generates identification result, the identification result generated is sent to intelligent television.Wherein, identification result can include the name of people, sex, age, and one or more information therein such as ethnic, academic, this is not any limitation as by the embodiment of the present application.
In one preferred embodiment of the invention, described face picture data being uploaded to before far-end server is identified, described method can also comprise the following steps:
Step S1: record the frame number of face picture data corresponding to described face mark.
User is shot by photographic head, with continuous acquisition multiframe image data, therefore for same user, can collect the face picture of multiframe.For same user, the number of the face picture of its correspondence, the i.e. frame number of the face picture data that record face mark is corresponding can be recorded.
Step S3: judge whether the frame number of described face picture data reaches preset detection threshold value.
Intelligent television can pre-set inspection threshold value, when the frame number of the face picture data of same face mark correspondence reaches preset inspection threshold value, just face picture data are uploaded to far-end server be identified, be equivalent to, when the frame number of these face picture data reaches to detect threshold value, perform described face picture data are uploaded to the step that far-end server is identified.
Wherein, described described face picture data are uploaded to the step that far-end server is identified, can be to send described face picture data to far-end server, obtain the identification result that face picture data are detected by described far-end server.
Such as, the detection threshold value that intelligent television is arranged is 6 frames, when the frame number of the face picture data that face identifies 00001 correspondence reaches 6 frame, the face picture data of the 6th frame is uploaded to far-end server, i.e. sends the image data of the 6th frame to far-end server.Far-end server can call preset face recognition algorithms and be identified received face picture data, generates identification result, and then identification result feeds back to intelligent television.
Certainly, the face picture data of the 1st frame or other frame can also be uploaded far-end server by Intelligent electric visual organ, it is also possible to the face picture data of all frames corresponding for same face mark are uploaded far-end server, and this is not any limitation as by the embodiment of the present invention.
The embodiment of the present invention can carry out local pretreatment to the image data captured by photographic head, generate face picture data, upload to far-end server by face picture data be identified, thus reduce the volume of transmitted data between intelligent television and far-end server, Internet resources are saved, ensure that the recognition result to same user is unified, improve the efficiency that user is carried out identification.
Step 107, determines, according to described identification result, the user identity that described face mark is corresponding.
Intelligent television can determine, according to identification result, the user identity that face mark is corresponding.User identity can include the information such as adult, old people, child, man, woman, name.Intelligent television can based on a determination that user identity, recommend program for user.Such as, intelligent television determines that the user identity of face mark correspondence is Zhang San, based on program acquired before Zhang San, recommends program for it.Certainly, intelligent television can also user identity based on user be child, recommends children's programs for this user.
In embodiments of the present invention, identification service interface can be passed through, obtain the image data captured by photographic head, and image data is detected, generate face picture data, then gather face picture data to be identified, determine user identity, so that intelligent television supports identification and face identification functions, it is not necessary to the integrated face recognition module of application program of intelligent television, while reducing the operating pressure of intelligent television, reduce the workload of exploitation application program.
When the application program of intelligent television needs that user is carried out identification, yuv data can be uploaded to ccf layer by identification service interface, just can obtain the identity of user, i.e. obtain, by the framework of intelligent television, the identification result that yuv data is detected by far-end server, it is assured that user identity, face is identified by the algorithm that need not application program employing itself, decreases the workload of application program.
In one preferred embodiment of the invention, described method can also comprise the following steps:
Step S5: set up described face mark and the association of identification result and preserve, generating face recognition result table.
Intelligent television can be set up the association of the identification result of face mark and its correspondence and keep, and generates face recognition result table.After intelligent television carries out processing locality to image data, face identifier lookup recognition of face table can be passed through, identify when finding this face in recognition of face table, just can get the identification result that this face mark is corresponding, without face picture data are uploaded to far-end server, further increase the speed that user is identified, and save a large amount of Internet resources and system resource.
Certainly, intelligent TV set can also be pre-created face recognition result table, now face recognition result table can be a empty table, when intelligent television gets the identification result of user, just can preserve by the identification result record of the face mark of user and its correspondence at the face recognition result table being pre-created.The mode of the establishment of recognition of face table is not any limitation as by the embodiment of the present invention.
In one preferred embodiment of the invention, described method can also comprise the following steps:
Step S7: judge whether the frame number of described face picture data exceedes detection threshold value.
Step S9: when the frame number of face picture data exceedes detection threshold value, extract, from described face recognition result table, the identification result that described face mark is corresponding.
Identify for same face, when frame number in face picture data reaches to detect threshold value, it is possible to face picture being uploaded far-end server and is identified, determine one's identity recognition result, then this face mark and identification result can be associated and preserve, generate face recognition result table.When frame number in face picture data exceedes detection threshold value, the most user is identified, the identification result of this user can be extracted from face recognition result table, be equivalent to extract, from this face recognition result table, the identification result that face mark is corresponding.
The embodiment of the present invention is when the frame number of face picture data exceedes detection threshold value, directly can extract, from face recognition result table, the identification result that face mark is corresponding, it is not required to that face picture data are uploaded to far-end server be identified, decrease network request, save internet resource and system resource.
On the basis of said method embodiment, in conjunction with the preferred embodiments of the present invention, as a example by the application program of intelligent television, continue the inventive method embodiment is described.
With reference to Fig. 2, it is shown that the flow chart of steps of the another kind of personal identification method embodiment of the present invention, specifically may include steps of:
Step 201, when receiving the recognition of face request that application program is sent, by calling identification service interface, obtains each frame image data captured by described photographic head.
As a concrete example of the embodiment of the present invention, when user's application program by intelligent television, when obtaining its program interested, application program needs user is carried out identification.Such as, work as user input instruction, when starting a certain application A PP1 of intelligent television, the operation of APP1 response user, user is shot by the photographic head starting intelligent television, the yuv data captured by photographic head is uploaded to the system of intelligent television by the identification service interface of intelligent television, be equivalent to the system of intelligent television when receiving the recognition of face request that application program is sent, when i.e. needing that the user captured by photographic head is carried out identification, identification service interface can be passed through, obtain each frame image data captured by photographic head.
Step 203, detects respectively to every frame image data, generates face picture data and face mark.
In one preferred embodiment of the invention, above-mentioned steps 203 can include following sub-step:
Sub-step 20301, is detected every frame image data by preset Face datection algorithm, determines face picture data.
Sub-step 20303, uses preset face characteristic algorithm to calculate described face picture data, generates face mark.
The preset local algorithm of intelligent television can include Face datection algorithm and face characteristic algorithm, and wherein Face datection algorithm is for detecting the image data captured by photographic head, generates face picture data；Face characteristic algorithm, for calculating face picture data, generates face mark.As a example by photographing 3 people, 3 faces are had in same pictures, in the image data A of same frame, i.e. have recorded the face picture data of 3 users, by Face datection algorithm to image data A process, obtain the face location information of these 3 people, i.e. obtain each facial image position in picture, 3 facial images in image data A are intercepted respectively according to each facial image position in the drawings, generate 3 face picture data, face picture data 1 can be respectively labeled as, face picture data 2, face picture data 3；Face characteristic algorithm can be respectively adopted each face picture data are calculated, be equivalent to facial characteristics based on face process, generation face identifies, face ID such as face picture data 1 correspondence is 0001B, the face ID of face picture data 2 correspondence is 0002B, and the face ID of face picture data 3 correspondence is 0003B.
Step 205, records the frame number of face picture data corresponding to described face mark.
These face picture data can be identified after the frame number of the face picture data of record face mark correspondence by intelligent television according to the frame number of record.Specifically, intelligent television can first judge whether the frame number of record arrives detection threshold value, frame number at record has reached to determine whether whether the frame number of record exceedes detection threshold value when detecting threshold value, the i.e. frame number at record has reached to further determine whether to be identified this user when detecting threshold value, if this user is identified, the identification result of this user can be extracted, it is possible to do not upload face picture data and be identified to far-end server from the face recognition result table previously generated；Being identified without to this user, these face picture data, less than detection threshold value, can be uploaded to far-end server be identified when the frame number of record reach to detect threshold value by the frame number i.e. recorded.Intelligent television can also first judge whether the frame number of record exceedes detection threshold value, judge whether this user to be identified, can determine whether whether the frame number of record reaches to detect threshold value when the frame number of record is less than detection threshold value, when frame number at record reaches to detect threshold value, these face picture data can be uploaded to far-end server and be identified.Those skilled in the art can take any one recognition method to be identified, and this is not any limitation as by the embodiment of the present invention.
In order to make it easy to understand, as a example by whether the certificate first judging record reaches to detect threshold value, the embodiment of the present invention is described.
Step 207, it is judged that whether the frame number of described face picture data reaches preset detection threshold value.
When frame number in face picture data fails to reach to detect threshold value, intelligent television can continue to use local algorithm to detect image data.When the frame number of face picture data reaches to detect threshold value, described face picture data directly can be uploaded to far-end server and be identified by intelligent television, i.e. perform step 211；Can also determine whether whether the frame number of face picture data exceedes judgement detection threshold value, i.e. perform step 209, this is not any limitation as by the embodiment of the present invention.In practice, when preferably the frame number in face picture data reaches to detect threshold value, further determine whether to exceed judgement detection threshold value, thus reduce intelligent television and upload the number of times of face picture data to far-end server, i.e. reduce the number of times sending network request, save Internet resources and system resource.
Step 209, it is judged that whether the frame number of described face picture data exceedes detection threshold value.
Identify for same face, when the frame number of face picture data exceedes detection threshold value, illustrate user have been carried out identification, can find, from face recognition result table, the identification result that this face mark is corresponding, i.e. perform step 215；When the frame number of face picture data is less than when checking threshold value, when i.e. the frame number in face picture data reaches to check threshold value, described face picture data is uploaded to far-end server and is identified, i.e. perform step 211.
Step 211, sends described face picture data to far-end server, obtains the identification result that face picture data are detected by described far-end server.
In order to ensure to transmit the safety of data, intelligent television can also use identification double secret key face picture data to be encrypted, and generates the face picture data of encryption, the face picture data of encryption are sent to far-end server.Identify that key can be set in advance in the ccf layer of intelligent television, it is also possible to being sent to intelligent television by far-end server, this is not any limitation as by the embodiment of the present invention.
In another preferred embodiment of the invention, the described step sending described face picture data to far-end server, can include following sub-step:
Sub-step 21101, obtains from described far-end server and identifies key.
Sub-step 21103, uses face picture data described in described identification double secret key to be encrypted, and generates face encryption image data.
Sub-step 21105, sends described face encryption image data to described far-end server.
Intelligent television is when the frame number of face picture data reaches to detect threshold value, i.e. when needs do Network Recognition request, can send, to this far-end server, the request of identification according to the Internet protocol address (Internet Protocol Address, IP address) of far-end server.After far-end server receives identification request, can generate according to the request of identification and identify key.Far-end server can will identify that key is sent to intelligent television so that intelligent television can be by identifying that double secret key face picture data are encrypted.Accordingly, far-end server can use the face picture data after identifying key pair encryption to be decrypted, and by preset face recognition algorithms, face picture data is carried out identification, generates identification result.
In one preferred embodiment of the invention, the sub-step of described face encryption image data is sent to described far-end server, may further include: add described face encryption image data to preset transmit queue, described transmit queue sends described face encryption image data according to sequencing to far-end server.
When intelligent television needs that face picture data corresponding for multiple faces mark are uploaded to far-end server, i.e. need multiple users are carried out identification, face picture data can be added in preset transmit queue.This transmit queue can send face image data according to the sequencing added or priority to far-end server so that far-end server can carry out identification according to the order sent to face picture data, and identification result is fed back to intelligent television.
Step 213, sets up described face mark and the association of identification result and preserves, generating face recognition result table.
Step 215, extracts, from described face recognition result table, the identification result that described face mark is corresponding.
The identification result of face mark and its correspondence can be saved in face recognition result table after obtaining the identification result that face picture data are detected by far-end server by intelligent television.When needing that same user is carried out identification next time, can be according to face identifier lookup identification result table, the identification result that face mark is corresponding is extracted from this face recognition result table, it is identified without again face picture data being uploaded to far-end server, decrease network request, save substantial amounts of Internet resources.
Step 217, determines, according to described identification result, the user identity that described face mark is corresponding.
Step 219, by calling described identification interface, sends, to described application program, the user identity that described face mark is corresponding.
Intelligent television can pass through identification interface, and user identity determined by general is sent to application program.nullApplication A PP1 and APP2 such as intelligent television carry out identification to same user，Wherein，The ccf layer that by identification interface, the image data YUV1 captured by this user is sent to intelligent television is identified by application A PP1，The ccf layer that by identification interface, the image data YUV2 captured by this user is sent to intelligent television is identified by application A PP2，After the ccf layer of intelligent television gets image data YUV1 and image data YUV1，Respectively image data YUV1 and image data YUV1 is detected，Identical face picture data and face mark can be generated，The face picture data of this user are uploaded far-end server be identified，Determine one's identity recognition result，So that it is determined that the user identity that this ID is corresponding，APP1 and APP2 is fed back to by user identity determined by identification service interface general.
In order to make those skilled in the art be more fully understood that the present invention, below in conjunction with Fig. 3, the embodiment of the present invention is described in detail.
With reference to Fig. 3, show that a kind of intelligent television of the present invention carries out the step schematic diagram of identification execution to user, application A PP1 of intelligent television and APP2 are arranged on the application layer of intelligent television, and image data can be uploaded to the ccf layer (Framework layer) of intelligent television by identification service interface.When starting Face datection, the ccf layer of intelligent television can obtain image data, i.e. calls Startfacedetect function and yuv data is uploaded (being equivalent to Startfacedetect&inputYUV).
At ccf layer, intelligent television can call the Face datection algorithm (Loca_facedetect) of this locality and detect yuv data.After this locality is detected, can carry out the face in YUV picture storing return value is the face array (being equivalent to Cut_face_from_yuv) comprising face ID, i.e. generate face picture data and generate face mark, wherein, face array can be understood as the related data of face picture, and face ID can be understood as face mark.
System service starts when, intelligent television can be pre-created a table, to store face picture data.Such as, one Hash table (hashmap) of system creation, store the related data of face picture.The related data of face picture can include face ID, accessed number of times, the JSON data etc. of return.Wherein, the number of times accessed can represent that the frame number of the face image data corresponding for face ID of face, JSON (JavaScript Object Notation) represent the data interchange format of a kind of lightweight.
For ease of understanding, hereinafter will be described as a example by hashmap, but must not believe that the embodiment of the present invention to be only capable of with Hash table and store face picture data, those skilled in the art can use other data storage method to store face picture data, and the embodiment of the present invention is without being any limitation as this.
Identifying face for the first time when, i.e. when using local algorithm that the first frame image data is processed, the capacity (size) of hashmap can be 0, the all face image datas returned in this YUV picture can be stored in hashmap by the system of intelligent television, stores with face ID for keyword.
Next frame image data comes when, obtain face ID again by local Face datection algorithm.Cyclic query can be passed through, it is judged that whether already present hashmap exists this and obtains face ID (being equivalent to Check_face_stable).If there is, mark the most in a program, and can be the related data of this face ID, take out from hashmap, whether the picture number then looking at this face alreadys more than our predetermined quantity (such as 6), i.e. judges whether face picture frame number corresponding for face ID exceedes preset inspection threshold value.
If the picture number of this face has reached predetermined quantity (such as 6), can start that face picture data are uploaded to far-end server and carry out identification (being equivalent to Start_facedetect_server).Such as, call call back function (i.e. callback function), wherein, callback function is used for returning face ID and the face picture data of this face, i.e. return the two information by callback function, just can get the face picture data of this face ID, send Network Recognition request to far-end server.The data returned by network can obtain this face by the result obtained after server algorithm, wherein, and the information such as face name the most close after may include that the contrast of this face inside this result, sex, age, race.Specifically, Network Recognition request will be sent to far-end server, face picture data will be added in transmit queue, and wait and do far-end network request.Face picture data can be uploaded to far-end server according to the sequencing added and carry out identification detection by queue, after identifying successfully, program can store in the data structure comprising this face ID all return results, be equivalent to set up face mark and the association of identification result and preserve, generate face recognition result table.
Predetermined quantity (being the 7th), then illustrate that this face had done far-end identification if more than, and relevant information has stored in hashmap.Intelligent television can be according to face ID, the data structure comprising this face ID is directly returned by callback function, be equivalent to extract, from face recognition result table, the identification result that face mark is corresponding, and can be ready for identifying with this face of notification frame rack-layer.Intelligent television does not truly do Network Recognition, thus saves a large amount of Internet resources and system resource.
After intelligent television gets the identification result (being equivalent to Get_face_info) of this user from ccf layer, the user identity of this user can be returned to application program (being equivalent to Return to app).
Each application program of intelligent television can obtain the user identity that framework determined face mark is corresponding, the i.e. framework of intelligent television can be with multiplexing for the recognition result that same face identifies, decrease the operating pressure of intelligent television, improve the efficiency to user identity identification.
It should be noted that, for embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of combination of actions, but those skilled in the art should know, the embodiment of the present invention is not limited by described sequence of movement, because according to the embodiment of the present invention, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should know, embodiment described in this description belongs to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
With reference to Fig. 4, it is shown that the structured flowchart of the present invention a kind of identity recognition device embodiment, specifically can include such as lower module:
Image data acquisition module 401, for by identification service interface, obtaining each frame image data captured by photographic head of intelligent television.
Detection module 403, may be used for detecting every frame image data respectively, generates face picture data and face mark.
Identification module 405, may be used for that described face picture data are uploaded to far-end server and is identified, and determine one's identity recognition result.
User identity determines module 407, may be used for determining, according to described identification result, the user identity that described face mark is corresponding.
With reference to Fig. 5, it is shown that the structured flowchart of a kind of identity recognition device preferred embodiment of the application.
Image data acquisition module 501, may be used for, by identification service interface, obtaining each frame image data captured by photographic head of intelligent television.
Detection module 503, may be used for detecting every frame image data respectively, generates face picture data and face mark.
Identification module 509, may be used for that described face picture data are uploaded to far-end server and is identified, and determine one's identity recognition result.
User identity determines module 515, may be used for determining, according to described identification result, the user identity that described face mark is corresponding.
In a preferred embodiment of the present application, described detection module 503 can include following submodule:
Picture detection sub-module 50301, be may be used for being detected every frame image data by preset Face datection algorithm, determines face picture data.
Face mark generates submodule 50303, may be used for using preset face characteristic algorithm to calculate described face picture data, generates face mark.
In a preferred embodiment of the present application, described device can also include with lower module:
Frame number logging modle 505, may be used for recording the frame number of face picture data corresponding to described face mark.
Frame detection module 507, may be used for judging whether the frame number of described face picture data reaches preset detection threshold value, triggers described identification module when the frame number of described face picture data reaches and detects threshold value.
Then identification module 509, can obtain, specifically for sending described face picture data to far-end server, the identification result that face picture data are detected by described far-end server.
In a preferred embodiment of the present application, described identification module 509 can include following submodule:
Key obtains submodule 50901, may be used for obtaining from described far-end server identifying key.
Encryption submodule 50903, may be used for using face picture data described in described identification double secret key to be encrypted, and generates face encryption image data.
Send submodule 50905, may be used for sending described face encryption image data to described far-end server.
In a preferred embodiment of the present application, described transmission submodule 50905, can be specifically for adding described face encryption image data to preset transmit queue, described transmit queue sends described face encryption image data according to sequencing to far-end server.
In a preferred embodiment of the present application, described device can also include:
Result table generation module 511, for setting up described face mark and the association of identification result and preserving, generates face recognition result table.
In a preferred embodiment of the present application, frame detection module 507, may be used for judging whether the frame number of described face picture data exceedes detection threshold value；Described device can also include: extraction module 513, may be used for, when the frame number of face picture data exceedes detection threshold value, extracting, from described face recognition result table, the identification result that described face mark is corresponding.
In a preferred embodiment of the present application, described image data acquisition module 501, may be used for, when receiving the recognition of face request that application program is sent, by calling identification service interface, obtaining each frame image data captured by described photographic head；
Described device can also include:
User identity sending module 517, may be used for by calling described identification interface, sends, to described application program, the user identity that described face mark is corresponding.
For device embodiment, due to itself and embodiment of the method basic simlarity, so describe is fairly simple, relevant part sees the part of embodiment of the method and illustrates.
Each embodiment in this specification all uses the mode gone forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, and between each embodiment, identical similar part sees mutually.
Those skilled in the art are it should be appreciated that the embodiment of the embodiment of the present invention can be provided as method, device or computer program.Therefore, the form of the embodiment in terms of the embodiment of the present invention can use complete hardware embodiment, complete software implementation or combine software and hardware.And, the embodiment of the present invention can use the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The embodiment of the present invention is to describe with reference to method, terminal unit (system) and the flow chart of computer program according to embodiments of the present invention and/or block diagram.It should be understood that can be by the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing terminal equipment so that the instruction performed by the processor of computer or other programmable data processing terminal equipment is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing terminal equipment work in a specific way, the instruction making to be stored in this computer-readable memory produces the manufacture including command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded on computer or other programmable data processing terminal equipment, make to perform sequence of operations step on computer or other programmable terminal equipment to produce computer implemented process, thus the instruction performed on computer or other programmable terminal equipment provides the step of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame for realization.
Although having been described for the preferred embodiment of the embodiment of the present invention, but those skilled in the art once know basic creative concept, then these embodiments can be made other change and amendment.So, claims are intended to be construed to include preferred embodiment and fall into all changes and the amendment of range of embodiment of the invention.
Finally, it can further be stated that, in this article, the relational terms of such as first and second or the like is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires or imply the relation or sequentially that there is any this reality between these entities or operation.And, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include that the process of a series of key element, method, article or terminal unit not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or terminal unit.In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, article or terminal unit.
Above to a kind of personal identification method provided by the present invention and a kind of identity recognition device, it is described in detail, principle and the embodiment of the present invention are set forth by specific case used herein, and the explanation of above example is only intended to help to understand method and the core concept thereof of the present invention；Simultaneously for one of ordinary skill in the art, according to the thought of the present invention, the most all will change, in sum, this specification content should not be construed as limitation of the present invention.
Claims (16)
1. a personal identification method, it is characterised in that described method includes:
By identification service interface, obtain each frame picture number captured by photographic head of intelligent television
According to；
Every frame image data is detected respectively, generates face picture data and face mark；
Described face picture data being uploaded to far-end server be identified, determine one's identity recognition result；
The user identity that described face mark is corresponding is determined according to described identification result.
Method the most according to claim 1, it is characterised in that described every frame image data is divided
Do not detect, generate face picture data and face mark, including:
By preset Face datection algorithm, every frame image data is detected, determine face picture number
According to；
Use preset face characteristic algorithm that described face picture data are calculated, generate face mark
Know.
Method the most according to claim 1, it is characterised in that by described face picture data
Passing to before far-end server is identified, described method also includes:
Record the frame number of face picture data corresponding to described face mark；
Judge whether the frame number of described face picture data reaches preset detection threshold value；
When the frame number of described face picture data reaches to detect threshold value, perform described face picture data
It is uploaded to the step that far-end server is identified；
Described described face picture data are uploaded to far-end server it are identified, including:
Send described face picture data to far-end server, obtain described far-end server to face picture
Data carry out the identification result detected.
Method the most according to claim 3, it is characterised in that also include:
Set up described face mark and the association of identification result and preserve, generating face recognition result
Table.
Method the most according to claim 4, it is characterised in that also include:
Judge whether the frame number of described face picture data exceedes detection threshold value；
When the frame number of face picture data exceedes detection threshold value, extract institute from described face recognition result table
State the identification result that face mark is corresponding.
Method the most according to claim 3, it is characterised in that described to far-end server transmission
Described face picture data, including:
Obtain from described far-end server and identify key；
Use face picture data described in described identification double secret key to be encrypted, generate face encryption picture number
According to；
Described face encryption image data is sent to described far-end server.
Method the most according to claim 6, it is characterised in that send to described far-end server
Described face encryption image data, including:
Adding described face encryption image data to preset transmit queue, described transmit queue is according to elder generation
Rear order sends described face encryption image data to far-end server.
8. according to the arbitrary described method of claim 1 to 7, it is characterised in that described in pass through identity
Identify service interface, obtain each frame image data captured by photographic head of intelligent television, including:
When receiving the recognition of face request that application program is sent, connect by calling identification service
Mouthful, obtain each frame image data captured by described photographic head；
Described method also includes:
By calling described identification interface, send described face mark correspondence to described application program
User identity.
9. an identity recognition device, it is characterised in that described device includes:
Image data acquisition module, for by identification service interface, obtaining the shooting of intelligent television
Each frame image data captured by Tou；
Detection module, for every frame image data is detected respectively, generate face picture data and
Face identifies；
Identification module, is identified for described face picture data are uploaded to far-end server, determines
Identification result；
User identity determines module, for determining described face mark correspondence according to described identification result
User identity.
Device the most according to claim 9, it is characterised in that described detection module includes:
Picture detection sub-module, for examining every frame image data by preset Face datection algorithm
Survey, determine face picture data；
Face mark generates submodule, for using preset face characteristic algorithm to described face picture number
According to calculating, generate face mark.
11. devices according to claim 9, it is characterised in that also include:
Frame number logging modle, for recording the frame number of face picture data corresponding to described face mark；
Frame detection module, for judging whether the frame number of described face picture data reaches preset detection threshold
Value, triggers described identification module when the frame number of described face picture data reaches and detects threshold value；
The most described identification module, for sending described face picture data to far-end server, obtains described
The identification result that face picture data are detected by far-end server.
12. devices according to claim 11, it is characterised in that also include:
Result table generation module, for setting up described face mark and the association of identification result and protecting
Deposit, generate face recognition result table.
13. devices according to claim 12, it is characterised in that
Described frame detection module, is additionally operable to judge whether the frame number of described face picture data exceedes detection threshold
Value；
Described device also includes: extraction module, for exceeding detection threshold when the frame number of face picture data
During value, extract, from described face recognition result table, the identification result that described face mark is corresponding.
14. devices according to claim 11, it is characterised in that described identification module includes:
Key obtains submodule, identifies key for obtaining from described far-end server；
Encryption submodule, is used for using face picture data described in described identification double secret key to be encrypted, raw
Become face encryption image data；
Send submodule, for sending described face encryption image data to described far-end server.
15. devices according to claim 14, it is characterised in that described transmission submodule, tool
Body for adding described face encryption image data to preset transmit queue, described transmit queue according to
Sequencing sends described face encryption image data to far-end server.
16. according to the arbitrary described device of claim 9 to 15, it is characterised in that
Described image data acquisition module, for when receiving the recognition of face request that application program is sent
Time, by calling identification service interface, obtain each frame image data captured by described photographic head；
Described device also includes:
User identity sending module, for by calling described identification interface, to described application program
Send the user identity that described face mark is corresponding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510757889.2A CN105979363A (en) | 2015-11-09 | 2015-11-09 | Identity identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510757889.2A CN105979363A (en) | 2015-11-09 | 2015-11-09 | Identity identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105979363A true CN105979363A (en) | 2016-09-28 |
Family
ID=56988128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510757889.2A Pending CN105979363A (en) | 2015-11-09 | 2015-11-09 | Identity identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105979363A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503691A (en) * | 2016-11-10 | 2017-03-15 | 广州视源电子科技股份有限公司 | A kind of identity mask method of face picture and device |
| CN107977657A (en) * | 2017-12-29 | 2018-05-01 | 佛山市幻云科技有限公司 | Long distance monitoring method, terminal and system |
| CN108596063A (en) * | 2018-04-13 | 2018-09-28 | 唐山新质点科技有限公司 | A kind of face identification method and system |
| CN108764053A (en) * | 2018-04-28 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN109002776A (en) * | 2018-06-29 | 2018-12-14 | 金蝶软件（中国）有限公司 | Face identification method, system, computer equipment and computer readable storage medium |
| CN109151502A (en) * | 2018-10-11 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Identify violation video method, device, terminal and computer readable storage medium |
| CN109191180A (en) * | 2018-08-06 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | The acquisition methods and device of evaluation |
| CN110472077A (en) * | 2019-07-12 | 2019-11-19 | 浙江执御信息技术有限公司 | The preposition method of calibration of Identification of Images, system, medium and electronic equipment |
| CN111723676A (en) * | 2020-05-26 | 2020-09-29 | 北京电信易通信息技术股份有限公司 | Face comparison method and device based on portrait recognition intelligent cutting |
| CN111738185A (en) * | 2020-06-28 | 2020-10-02 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
| CN114529977A (en) * | 2020-11-02 | 2022-05-24 | 青岛海尔多媒体有限公司 | Gesture control method and device for intelligent equipment and intelligent equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077954A1 (en) * | 2005-07-01 | 2008-03-27 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Promotional placement in media works |
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN102646190A (en) * | 2012-03-19 | 2012-08-22 | 腾讯科技（深圳）有限公司 | Authentication method, device and system based on biological characteristics |
| CN103974108A (en) * | 2013-12-20 | 2014-08-06 | 乐视网信息技术（北京）股份有限公司 | Smart television control method and system thereof based on identity authentication |
-
2015
- 2015-11-09 CN CN201510757889.2A patent/CN105979363A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077954A1 (en) * | 2005-07-01 | 2008-03-27 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Promotional placement in media works |
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN102646190A (en) * | 2012-03-19 | 2012-08-22 | 腾讯科技（深圳）有限公司 | Authentication method, device and system based on biological characteristics |
| CN103974108A (en) * | 2013-12-20 | 2014-08-06 | 乐视网信息技术（北京）股份有限公司 | Smart television control method and system thereof based on identity authentication |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503691A (en) * | 2016-11-10 | 2017-03-15 | 广州视源电子科技股份有限公司 | A kind of identity mask method of face picture and device |
| CN106503691B (en) * | 2016-11-10 | 2019-12-20 | 广州视源电子科技股份有限公司 | Identity labeling method and device for face picture |
| CN107977657A (en) * | 2017-12-29 | 2018-05-01 | 佛山市幻云科技有限公司 | Long distance monitoring method, terminal and system |
| CN108596063A (en) * | 2018-04-13 | 2018-09-28 | 唐山新质点科技有限公司 | A kind of face identification method and system |
| CN108764053A (en) * | 2018-04-28 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN109002776A (en) * | 2018-06-29 | 2018-12-14 | 金蝶软件（中国）有限公司 | Face identification method, system, computer equipment and computer readable storage medium |
| CN109191180A (en) * | 2018-08-06 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | The acquisition methods and device of evaluation |
| CN109151502A (en) * | 2018-10-11 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Identify violation video method, device, terminal and computer readable storage medium |
| CN110472077A (en) * | 2019-07-12 | 2019-11-19 | 浙江执御信息技术有限公司 | The preposition method of calibration of Identification of Images, system, medium and electronic equipment |
| CN111723676A (en) * | 2020-05-26 | 2020-09-29 | 北京电信易通信息技术股份有限公司 | Face comparison method and device based on portrait recognition intelligent cutting |
| CN111738185A (en) * | 2020-06-28 | 2020-10-02 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
| CN111738185B (en) * | 2020-06-28 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
| CN114529977A (en) * | 2020-11-02 | 2022-05-24 | 青岛海尔多媒体有限公司 | Gesture control method and device for intelligent equipment and intelligent equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105979363A (en) | Identity identification method and device | |
| US9100630B2 (en) | Object detection metadata | |
| CN104012106B (en) | It is directed at the video of expression different points of view | |
| KR101798011B1 (en) | Video playing method and device | |
| US20160042249A1 (en) | Event-based image classification and scoring | |
| US10692539B2 (en) | Crowdsourced video collaboration | |
| WO2019128568A1 (en) | Content pushing method, apparatus and device | |
| CN107679560B (en) | Data transmission method and device, mobile terminal and computer readable storage medium | |
| WO2020044097A1 (en) | Method and apparatus for implementing location-based service | |
| CN106453572B (en) | Method and system based on Cloud Server synchronous images | |
| TW201508520A (en) | Method, Server and System for Setting Background Image | |
| KR101942211B1 (en) | Cooperative provision of personalized user functions using shared and personal devices | |
| CN104834713A (en) | Method and system for storing and transmitting image data of terminal equipment | |
| CN112954450B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN202998337U (en) | Video program identification system | |
| US9706102B1 (en) | Enhanced images associated with display devices | |
| CN113010740A (en) | Word weight generation method, device, equipment and medium | |
| WO2018028253A1 (en) | Information processing method, apparatus and storage medium | |
| CN106332556B (en) | Method and terminal for transmitting cloud files and cloud server | |
| US20210089738A1 (en) | Image Tag Generation Method, Server, and Terminal Device | |
| US20200092444A1 (en) | Playback method, playback device and computer-readable storage medium | |
| WO2013002960A1 (en) | Spatially organized image collections on mobile devices | |
| US20170171462A1 (en) | Image Collection Method, Information Push Method and Electronic Device, and Mobile Phone | |
| US9699123B2 (en) | Methods, systems, and non-transitory machine-readable medium for incorporating a series of images resident on a user device into an existing web browser session | |
| CN114466145B (en) | Video processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160928 |