WO2019051799A1 - 图像处理方法、装置、移动终端、服务器和存储介质 - Google Patents

图像处理方法、装置、移动终端、服务器和存储介质 Download PDF

Info

Publication number
WO2019051799A1
WO2019051799A1 PCT/CN2017/101942 CN2017101942W WO2019051799A1 WO 2019051799 A1 WO2019051799 A1 WO 2019051799A1 CN 2017101942 W CN2017101942 W CN 2017101942W WO 2019051799 A1 WO2019051799 A1 WO 2019051799A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
face
information
clustering
mobile terminal
Prior art date
Application number
PCT/CN2017/101942
Other languages
English (en)
French (fr)
Inventor
柯秀华
曹威
王俊
Original Assignee
广东欧珀移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 广东欧珀移动通信有限公司 filed Critical 广东欧珀移动通信有限公司
Priority to PCT/CN2017/101942 priority Critical patent/WO2019051799A1/zh
Publication of WO2019051799A1 publication Critical patent/WO2019051799A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60Network 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 
    • H04N21/65Transmission of management data between client and server
    • H04N21/654Transmission by server directed to the client
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60Network 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 
    • H04N21/65Transmission of management data between client and server
    • H04N21/658Transmission by the client directed to the server

Definitions

  • the present application relates to the field of computer technologies, and in particular, to an image processing method and apparatus, a mobile terminal, a server, and a storage medium.
  • image classification in smart mobile terminals may include grouping images according to face, location, and time. Grouping the images in the smart mobile terminal enables the user to view the images in the smart mobile terminal, and the manner in which the user views the images in the smart mobile terminal is more convenient and faster.
  • an image processing method for processing images.
  • An image processing method comprising:
  • the mobile terminal When receiving the first clustering request, the mobile terminal clusters the first facial image set to obtain first clustering information;
  • the server Receiving, by the server, the second clustering information, where the second clustering information is clustering information of the second facial image set uploaded by the server to the mobile terminal;
  • An image processing apparatus is applied to a mobile terminal, including:
  • a first clustering module configured to: when receiving the first clustering request, the mobile terminal pairs the first face image Collecting clusters to obtain first cluster information;
  • a receiving module configured to receive second cluster information sent by the server, where the second clustering information is clustering information of the second facial image set uploaded by the server to the mobile terminal;
  • An obtaining module configured to obtain a comparison result between the first cluster information and the second cluster information
  • an update module configured to update at least one of the first cluster information and the second cluster information according to the type of the comparison result.
  • a mobile terminal comprising a memory and a processor, the memory storing computer readable instructions, the instructions being executed by the processor to cause the processor to perform an image processing method as described above.
  • One or more non-transitory computer readable storage medium comprising computer readable instructions, when said computer readable instructions are executed by one or more processors, causing said one or more processors to perform as described above Image processing method.
  • An image processing method comprising:
  • An image processing apparatus is applied to a server, including:
  • a second clustering module configured to: when receiving a second clustering request uploaded by the mobile terminal, clustering the second facial image set uploaded by the mobile terminal to obtain second clustering information;
  • a sending module configured to send the second cluster information to the mobile terminal
  • a receiving module configured to receive updated second cluster information uploaded by the mobile terminal
  • a replacement module configured to replace the second cluster information with the updated second cluster information.
  • a server includes a memory and a processor, the memory storing computer readable instructions that, when executed by the processor, cause the processor to perform an image processing method as described above.
  • One or more non-transitory computer readable storage medium comprising computer readable instructions, when said computer readable instructions are executed by one or more processors, causing said one or more processors to perform as described above Image processing method.
  • FIG. 1 is a schematic diagram of an application environment of an image processing method in an embodiment
  • FIG. 2 is a sequence diagram of interaction between a mobile terminal and a first server and a second server in an embodiment
  • FIG. 3 is a flow chart of an image processing method in an embodiment
  • Figure 5 is a flow chart of an image processing method in another embodiment
  • FIG. 6 is a flow chart of an image processing method in another embodiment
  • FIG. 7 is a flow chart of an image processing method in another embodiment
  • Figure 9 is a block diagram showing the structure of an image processing apparatus in an embodiment
  • Figure 10 is a block diagram showing the structure of an image processing apparatus in another embodiment
  • Figure 11 is a block diagram showing the structure of an image processing apparatus in another embodiment
  • Figure 12 is a block diagram showing the structure of an image processing apparatus in another embodiment
  • Figure 13 is a block diagram showing the structure of an image processing apparatus in another embodiment
  • Figure 14 is a block diagram showing the structure of an image processing apparatus in another embodiment
  • 15 is a block diagram showing a part of a structure of a mobile phone related to a mobile terminal provided by an embodiment of the present application;
  • Figure 16 is a schematic diagram showing the internal structure of a server in an embodiment.
  • first, second and the like may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.
  • first clustering module may be referred to as a second clustering module without departing from the scope of the present application, and similarly, the second clustering module may be referred to as a first clustering module. Both the first clustering module and the second clustering module are clustering modules, but not the same clustering module.
  • FIG. 1 is a schematic diagram of an application environment of an image processing method in an embodiment.
  • the application environment includes a first mobile terminal 110, a second mobile terminal 120, a first server 130, and a second server 140.
  • An image is stored in the first mobile terminal 110, and the image may be stored in the first mobile terminal 110 or may be stored in the first mobile terminal 110 with a built-in SD (Secure Digital Memory Card) card.
  • the first mobile terminal 110 can identify the face image included in the image, extract the face feature information in the face image, and cluster the face image according to the face feature information.
  • the first mobile terminal 110 may also upload the face image to the first server 130.
  • the first server 130 may extract the face feature information in the face image, and send the extracted face feature information to the second server 140.
  • the second server 140 may cluster the face feature information and transmit the cluster information to the first mobile terminal 110.
  • the first mobile terminal 110 may compare the cluster information of the same face image by the first mobile terminal 110 and the second server 140, and update the first according to the comparison result. Cluster information of the same face image by the mobile terminal 110 or clustering information of the same face image by the second server 140.
  • the first mobile terminal 110 may further cluster the un-uploaded face images in the first mobile terminal 110 according to the cluster information sent by the second server 140.
  • the second mobile terminal 120 has the same function as the first mobile terminal 110, and the second mobile terminal 120 can cluster the face images in the second mobile terminal 120.
  • the second mobile terminal 120 may upload the face image to the first server 130.
  • the first server 130 may recognize the face feature information in the face image and upload the face feature information to the second server 140.
  • the second server 140 may cluster the face feature information and return the cluster information to the second mobile terminal 120.
  • the second mobile terminal 120 may compare the cluster information of the same face image by the second mobile terminal 120 and the second server 140, and update the first according to the comparison result.
  • the clustering information of the same face image by the mobile terminal 110 or the clustering information of the same face image by the second server 140 may further cluster the un-uploaded face images in the second mobile terminal 120 according to the cluster information sent by the second server 140.
  • the face image uploaded by the first mobile terminal 110 or the second mobile terminal 120 to the first server 130 may be a face image stored in the memory, or may be a face image stored in the built-in SD card, or may be a memory and a built-in SD.
  • the first server 130 may be a single server, or may be a first server cluster composed of a plurality of first servers 130, or one of the first server clusters; the second server 140 may be a single server. It may also be a second server cluster composed of a plurality of second servers 140, or a server in a second server cluster.
  • the first mobile terminal 110 and the second mobile terminal 120 may be two mobile terminals belonging to the same account, or may be two mobile terminals belonging to different accounts.
  • the first server 130 may merge the face images uploaded by the first mobile terminal 110 and the second mobile terminal 120.
  • the first server 130 may also send the merged face image to the first mobile terminal 110 and the second mobile terminal 120 to synchronize the data of the first mobile terminal 110 and the second mobile terminal 120.
  • the first mobile terminal 110 and the second mobile terminal 120 may send a second clustering request to the second server 140, and the second server 140 may generate a clustering request queue according to the order in which the second clustering request is received.
  • the second server 140 detects that the cluster request queue includes the plurality of second cluster requests sent by the first mobile terminal 110, the plurality of second cluster requests may be combined into one second cluster request.
  • the second clustering request may combine the plurality of second clustering requests into one second clustering request.
  • the second server 140 detects that the cluster request queue includes the second clustering request uploaded by the first mobile terminal 110 and the second clustering request uploaded by the second mobile terminal 120, the second clustering request may be combined. Request for a second cluster.
  • the first mobile terminal 110 and the second mobile terminal 120 may upload a second clustering request to the second server 140.
  • the second server 140 may generate a clustering request queue according to the order in which the second clustering request is received, and cluster the facial feature information corresponding to the second clustering information according to the order of the clustering request queue.
  • the first server 130 and the second server 140 can be the same server.
  • the first mobile terminal 110 or the second mobile terminal 120 may upload the face image to the server, and the server may extract the face feature information in the face image and cluster the extracted face feature information.
  • the server may return the clustering information to the first mobile terminal 110 or the second mobile terminal 120.
  • the server may generate a clustering request queue according to the received second clustering request sequence, and merge the plurality of second clustering requests uploaded by the same terminal into one second clustering request, and respectively separate multiple mobile terminals of the same account.
  • the uploaded second cluster request is merged into one second cluster request.
  • FIG. 2 is a sequence diagram of interaction between a mobile terminal and a first server and a second server in an embodiment. As shown in FIG. 2, the process of the mobile terminal 210 interacting with the first server 220 and the second server 230 includes:
  • the mobile terminal 210 Upon receiving the first clustering request, the mobile terminal 210 clusters the first face image set to obtain the first clustering information.
  • the first cluster image set in the mobile terminal 210 may be clustered to obtain the first clustering information.
  • the first face image set includes a face image stored in the memory of the mobile terminal 210 and a face image stored in a SD (Secure Digital Memory Card) card built into the mobile terminal 210.
  • the clustering of the first face image set by the mobile terminal 210 includes: the mobile terminal 210 extracts the face feature information of the face image in the first face image set according to the feature recognition model, and performs similarity matching on the face feature information according to the Match result to the first
  • the face images in a face image collection are clustered.
  • the mobile terminal 210 uploads the second face image set to the first server 220.
  • the first face image set includes a second face image set
  • the second face image set is a face image stored in the memory of the mobile terminal 210.
  • the mobile terminal 210 may upload the second face image set to the first server 220.
  • the mobile terminal 210 acquires the face image of the second server 230 that has been clustered in the second face image set and the face image of the user group, and the second server 230
  • the mobile terminal 210 uploads the corresponding tag information, so that the second server 230 does not need to re-cluster the clustered face image.
  • the mobile terminal 210 uploads the user group information corresponding to the face image, so that the second server 230 and the mobile terminal 210 match the grouping of the face image.
  • the first server 220 extracts face feature information of the face image in the second face image set.
  • the first server 220 may extract face feature information of the face image in the second face image set according to the feature recognition model.
  • the feature recognition model in the first server 220 may be the same as or different from the feature recognition model in the second server 230.
  • the first server 220 transmits the face feature information to the second server 230.
  • the mobile terminal 210 transmits a second clustering request to the second server 230.
  • the mobile terminal 210 may send a second clustering request to the second server 230, so that the second server 230 clusters the facial feature information corresponding to the second facial image set.
  • the server may receive the second clustering request uploaded by the multiple mobile terminals 210, and the server may generate a clustering request queue according to the order of receiving the second clustering request, in the order of the second clustering request in the clustering request queue.
  • the face image collection is clustered.
  • the second server 230 may merge multiple second clustering requests uploaded by the same mobile terminal 210 into one second clustering request, and the second server 230 may also upload multiple second aggregations of multiple mobile terminals 210 of the same account.
  • the class request is merged into a second cluster request.
  • the second server 230 clusters the face feature information to obtain the second cluster information.
  • the second server 230 performs similarity matching on the face feature information, and clusters the face feature information according to the matching result.
  • the second server 230 transmits the second cluster information to the mobile terminal 210.
  • the mobile terminal 210 replaces the first cluster information with the second cluster information.
  • the mobile terminal 210 clusters the face images other than the second face image set in the first face image set according to the second cluster information.
  • the mobile terminal 210 uploads the first cluster information to the second server 230, and the first cluster information is used to replace the second cluster information.
  • the mobile terminal 210 may compare the first cluster information with the second cluster information, and update the first cluster information or the second cluster information according to the comparison result.
  • the mobile terminal 210 may further cluster the face images other than the second face image set in the first face image set according to the second cluster information.
  • FIG. 3 is a flow chart of an image processing method in one embodiment. As shown in FIG. 3, an image processing method is applied to a mobile terminal, including:
  • Step 302 When receiving the first clustering request, the mobile terminal clusters the first facial image set to obtain first clustering information.
  • the mobile terminal can perform face recognition on the stored image and recognize the face image included in the stored image.
  • the mobile terminal further extracts face feature information in the face image according to the feature recognition model, and clusters the face image according to the face feature information.
  • the above first clustering request is a request to cluster a face image stored in the mobile terminal.
  • the first face image set is a face image stored in the mobile terminal, and includes a face image stored in the memory of the mobile terminal and a face image stored in the built-in SD card of the mobile terminal. After receiving the first clustering request, the mobile terminal may cluster the face images stored in the mobile terminal.
  • the condition for triggering the first clustering request may include one or more of the following:
  • the mobile terminal receives the second clustering information sent by the server, and triggers the first clustering request when detecting that the second facial image set corresponding to the second clustering information is smaller than the first facial image set.
  • a feature recognition model is stored in the mobile terminal.
  • the mobile terminal may compare the version number of the current feature recognition model in the mobile terminal with the version number of the feature recognition model sent by the server, if the current feature identification of the mobile terminal The version number of the model is lower than the version number of the feature recognition model sent by the server, and the mobile terminal updates the feature recognition model.
  • the mobile terminal may re-extract the face feature information of the face image in the first face image set according to the updated feature recognition model, and select the person in the first face image set according to the face feature information.
  • the face image clustering obtains the first cluster information.
  • the stored face feature information in the first face image set may be converted into the face feature information corresponding to the updated feature recognition model.
  • the mobile terminal performs feature recognition only on the face image in which the face feature information is not stored in the first face image set, and acquires the face feature information.
  • the mobile terminal further clusters the first face image set according to the face feature information corresponding to the face image in the first face image set to obtain the first cluster information.
  • An image update list is stored in the mobile terminal.
  • the mobile terminal stores the face image of the added face image or the change information in the image update list. .
  • the mobile terminal detects that the image update list is not empty, triggering the first clustering request. After receiving the first clustering request, the mobile terminal extracts facial feature information for the facial image in the image update list, and clusters the facial image in the image update list according to the facial feature information.
  • the mobile terminal may search for the second face image set corresponding to the second cluster information.
  • the mobile terminal can detect whether the face image in the second face image set is the same as the face image in the first face image set, and when detecting that the face image in the first face image set is more than the second face image set
  • the first cluster request is triggered when the face image is displayed.
  • the mobile terminal uses the face image other than the second face image set in the first face image set as the third face image set.
  • the mobile terminal extracts face feature information of the face image in the third face image set, and the mobile terminal may set the face feature information of the face image in the third face image set and the face image in the second face image set
  • the face feature information is similarly matched.
  • the face image in the third face image set is divided into the group corresponding to the face image in the second face image set.
  • the packet corresponding to the face image in the second face image set is obtained by the mobile terminal according to the second cluster information.
  • the first threshold may be a preset value of the mobile terminal, a preset value of the server, or a value manually input by the user.
  • the mobile terminal may also check Determine if the current condition meets the preset condition. If it is detected that the current condition meets the preset condition, the mobile terminal clusters the first face image set to obtain the first cluster information.
  • Checking whether the current condition meets the preset conditions includes:
  • the preset time and the preset duration in the foregoing preset conditions may be preset values of the mobile terminal, may also be preset values of the server, or may be values manually input by the user.
  • the BatteryManager in the mobile terminal can broadcast battery information through the intent, including the state of charge of the battery, the charging current, and the like. When the state of charge changes, the BatteryManager sends a system broadcast, and the mobile terminal can receive the system broadcast through the broadcast receiver, and determine the current battery state of the mobile terminal according to the broadcast content of the system.
  • Step 304 Receive second cluster information sent by the server, where the second cluster information is clustering information of the second face image set uploaded by the server to the mobile terminal.
  • the mobile terminal may upload the second face image set to the server, and send a second clustering request to the server, so that the server clusters the second face image set.
  • the second face image set may be a face image included in a memory storage image in the mobile terminal.
  • the server may extract the facial feature information of the facial image in the second facial image set according to the feature recognition model.
  • the server further performs similarity matching on the face feature information of the face image in the second face image set, and divides the portrait feature information whose similarity exceeds the second threshold into the same group.
  • the second threshold may be a preset value of the mobile terminal, a preset value of the server, or a value manually input by the user.
  • the server may return the clustering information of the second facial image set to the mobile terminal, that is, the server may send the second clustering information to the mobile terminal.
  • the feature recognition models in the mobile terminal and the server may be the same or different.
  • the mobile terminal After receiving the second cluster information, the mobile terminal detects that the current second face image set is different from the second face image set of the last upload server of the mobile terminal, and the mobile terminal discards and receives the second gather. Class information.
  • Step 306 Acquire a comparison result between the first cluster information and the second cluster information, and update at least one of the first cluster information and the second cluster information according to the type of the comparison result.
  • the mobile terminal may compare the first cluster information with the second cluster information. Comparing the first cluster information with the second cluster information includes:
  • the mobile terminal may select to update the first cluster information, the second cluster information, the first cluster information, and the second cluster information according to the comparison result.
  • the image processing method in the embodiment of the present application compares the clustering information of the face image of the mobile terminal with the clustering information of the server to the face image, and selects to update the first cluster information or the second group according to the comparison result.
  • the class information, or the first cluster information and the second cluster information are simultaneously updated, so that the clustering information of the face image by the mobile terminal and the clustering information of the server face image can be synchronized.
  • the mobile terminal selects and updates different cluster information according to different comparison results, so that the manner in which the mobile terminal saves the cluster information is more diverse and intelligent.
  • the first cluster information includes a first image identification; the second cluster information includes a second image identification. Updating the first cluster information according to the type of the comparison result in step 306 includes:
  • An image identifier is a string used to uniquely identify an image, and can be numbers, letters, symbols, and the like.
  • the first image identifier is an image identifier of a face image in the first face image set in the mobile terminal.
  • the second image identifier is an image identifier of the face image in the second face image set received by the server.
  • the mobile terminal may acquire the first image identification set and the second image identification set, and identify the first image The collection is compared to the second set of image identifiers.
  • the face image in the first face image set can be compared with the face image in the second face image set by comparing the first image identification set with the second image identification set. And if the first image identification set includes the second image identification set, and the first image identification set is not equal to the second image identification set, updating the first cluster information. That is, when it is detected that the first face image set includes all face images in the second face image set, and other face images are included, the mobile terminal may update the first cluster information.
  • the updating, by the mobile terminal, the first cluster information includes:
  • the mobile terminal acquires clustering information of the second face image set in the first clustering information, and the mobile terminal replaces the clustering information of the second terminal image set by the mobile terminal with the second clustering information sent by the server.
  • the mobile terminal uses the face image other than the second face image set in the first face image set as the third face image set.
  • the mobile terminal extracts face feature information of the face image in the third face image set, and the mobile terminal may set the face feature information of the face image in the third face image set and the face image in the second face image set
  • the face feature information is similarly matched.
  • the similarity exceeds the first threshold, the face image in the third face image set is divided into the group corresponding to the face image in the second face image set.
  • the first threshold may be a preset value of the mobile terminal, a preset value of the server, or a value manually input by the user.
  • the clustering information of the server to the face image may be replaced by the clustering information of the mobile terminal to the same face image. And clustering other face images in the mobile terminal according to the clustering result of the server on the face image. Based on the clustering results of the server, the stability of the data is improved, and the accuracy of image clustering is also improved.
  • the first cluster information includes a first face identifier; and the second cluster information includes a second face identifier.
  • Updating the first cluster information according to the type of the comparison result in step 306 includes: acquiring a first face identifier and a second face identifier of the same image, where the second face identifier is more than the first face identifier A human face identifies a face, and replaces the first cluster information with the second cluster information of the same image.
  • a face logo is a string used to uniquely identify a face, including numbers, letters, and symbols.
  • the first face identifier is a set of face identifiers included in a face image in the first face set.
  • the second face identifier is a set of face identifiers included in a face image in the second cluster information sent by the server.
  • the mobile terminal may acquire the first face identifier and the second face identifier of the same image, and compare the first face identifier with the second face identifier. When the face in the second face identifier is more than the face in the first face identifier, the first cluster information is replaced with the second cluster information of the same image.
  • the face identified by the same face image server is more than the face recognized by the mobile terminal, and the face recognized by the server is taken as the standard, and the mobile terminal replaces the mobile terminal with the second cluster information of the image by the server.
  • the first clustering information of the image is more than the face recognized by the mobile terminal, and the face recognized by the server is taken as the standard, and the mobile terminal replaces the mobile terminal with the second cluster information of the image by the server.
  • the first clustering information of the image is more than the face recognized by the mobile terminal, and the face recognized by the server is taken as the standard
  • the image processing method in the embodiment of the present application can detect whether the face recognized by the server and the mobile terminal for the same image is consistent. If it is detected that the face recognized by the same image server is more than the face recognized by the mobile terminal, the server recognizes the face as the standard, and the clustering information of the image is replaced by the server with the clustering information of the image by the mobile terminal. Because the amount of image data processed by the server is large and the number of recognized face images is more, the number of faces recognized by the server is taken as the standard, which improves the accuracy of face recognition.
  • updating the second cluster information according to the type of the comparison result in step 306 includes: when the face in the first face identifier is more than the face in the second face identifier, and the first face identifier is more The generated face has a user group identifier, and the first cluster information of the same image is uploaded to the server, and the first cluster information is used to replace the second cluster information of the same image.
  • the user group identifier is a character string used to mark the user's manual grouping information, including numbers, letters, symbols, and the like.
  • the mobile terminal can obtain the first face identifier and the second face identifier of the same image. When it is detected that the face in the first face identifier is more than the face in the second face identifier, the first face identifier can be detected. Whether the face is out of the user group identifier. That is, when the mobile terminal detects that the face recognized by the same face image mobile terminal is more than the face recognized by the server, it is detected whether the excess face recognized by the mobile terminal carries the user group identifier.
  • Detecting whether the face of the first face identifier has a user group identifier detecting whether the image corresponding to the extra face has a user group identifier, and if the image carries a user group identifier, detecting whether the user group identifier is Corresponds to an extra face.
  • the user face identifier and the extra face include: the user manually groups the images corresponding to the plurality of faces, and the group is a group that clusters the extra faces.
  • the mobile terminal recognizes the face A, the face B, and the face C included in the image 1.
  • the server recognizes the face A and the face B included in the image 1, and the face C is recognized in the face recognized by the mobile terminal.
  • the mobile terminal detects whether the user manually groups the image 1. If the user manually groups the image 1, it detects whether the user divides the image 1 into the group C of the face C. If the user divides the image 1 into the group C of the face C, the extra is Face C has a user grouping identifier.
  • the mobile terminal When it is detected that the extra face in the first face identifier has a user group identifier, the mobile terminal uploads the first cluster information of the same image to the server according to the user operation. After receiving the first clustering information, the server may replace the second clustering information of the same image by receiving the first clustering information.
  • the user when it is detected that the server and the mobile terminal identify that the same face is inconsistent, and the mobile terminal recognizes more faces than the server-identified face, the user is detected whether the user recognizes the mobile terminal.
  • the faces were manually grouped. If the user manually groups more than ten times of the mobile terminal, the manual grouping of the user is retained, and the clustering information of the image of the mobile terminal is uploaded to the server.
  • the server replaces the clustering information of the image by the mobile terminal with the clustering information of the server on the same image to ensure data synchronization. Retaining the user's manual grouping in the above method increases user stickiness.
  • updating the first cluster information according to the type of the comparison result in step 306 includes: when the face in the first face identifier is more than the face in the second face identifier, and the first face identifier is more The outgoing face does not carry the user grouping identifier, and the first clustering information is replaced with the second clustering information of the same image.
  • the mobile terminal After the first face identifier and the second face identifier of the same image are acquired by the mobile terminal, if the face in the first face identifier is more than the face in the second face identifier, and the first face identifier is more The face of the face does not carry the user group identifier, and the clustering information of the image is replaced by the server to replace the clustering information of the mobile terminal with the same image. That is, for the same face image, the mobile terminal recognizes more faces than the server-identified face, and the mobile terminal recognizes that the extra face does not carry the user group identifier, and the face recognized by the server is used as the standard.
  • the server clusters the image information to replace the clustering of the same image by the mobile terminal. information.
  • the mobile terminal acquires the first face identifier and the second face identifier of the same image, where the face in the first face identifier is more than the face in the second face identifier, and the first face identifier
  • the mobile terminal may hide the extra face recognized by the mobile terminal and re-cluster the same image. That is, for the same face image, the mobile terminal recognizes more faces than the server-identified face, and the mobile terminal recognizes that the extra face does not carry the user group identifier, and the mobile terminal may add more of the same image.
  • the face state is changed to hidden, that is, the mobile terminal no longer extracts the face feature information of the above-mentioned face.
  • the mobile terminal performs feature extraction on the same image to obtain facial feature information, and similarly matches the facial feature information of the same image with the facial feature information of the clustered image, and performs the same image according to the similarity result. Clustering.
  • the user when it is detected that the server and the mobile terminal identify that the same face is inconsistent, and the mobile terminal recognizes more faces than the server-identified face, the user is detected whether the user recognizes the mobile terminal.
  • the faces were manually grouped. If the user does not manually group the faces of the mobile terminal by ten times, the face recognized by the server shall prevail. Because the amount of face data recognized by the server is large and the amount of data is stable, the accuracy of face image recognition is improved based on the face recognized by the server.
  • updating the second cluster information according to the type of the comparison result in step 306 includes: when the second face identifier is unmanned, uploading the first cluster information of the same image to the server, the first cluster information The second cluster information used to replace the same image.
  • the mobile terminal After acquiring the first face identifier and the second face identifier of the same image, the mobile terminal detects the face in the first face identifier and the unmanned face in the second face identifier, and then the first image of the same image
  • the face logo is subject to change. That is, for the same face image, if the mobile terminal recognizes the face and the server does not recognize the face, the face recognized by the mobile terminal for the same image is retained.
  • the mobile terminal may upload the first clustering information of the image to the server, and the server replaces the second clustering information of the same image according to the received first information.
  • the image processing method in the embodiment of the present application detects that the mobile terminal of the same image is recognized.
  • the mobile terminal retains the face of the image. Avoid data errors caused by server failures and recognition of face errors.
  • the accuracy of image face recognition is improved.
  • the first clustering information comprises a first grouping identifier; the second clustering information comprises a second grouping identifier. Updating at least one of the first cluster information and the second cluster information according to the type of the comparison result in step 306 includes:
  • Step 402 Acquire a first group identifier and a second group identifier of the same image.
  • the first group identifier is different from the second group identifier, obtain a first time corresponding to the first group identifier and a second time corresponding to the second group identifier. time.
  • the group identifier is a character string for identifying the group in which the face image is located, including numbers, letters, symbols, and the like.
  • the first group identifier is a group identifier of the image by the mobile terminal
  • the second group identifier is a group identifier of the image by the server.
  • the first packet identifier may be compared with the second group identifier.
  • the first time corresponding to the first group identifier and the second time corresponding to the second group identifier may be acquired.
  • the first time indicates a time when the image information of the same image in the mobile terminal is last updated.
  • the second time indicates the time when the image information of the same image in the server was last updated.
  • Step 404 When the first time is later than the second time, the first cluster information of the same image is uploaded to the server, and the first cluster information is used to replace the second cluster information of the same image.
  • the grouping of the same image of the mobile terminal shall prevail.
  • the mobile terminal uploads the first cluster information of the same image to the server, and the server replaces the second cluster information of the same image according to the received first cluster information.
  • Step 406 When the second time is later than the first time, the first cluster information is replaced with the second cluster information of the same image.
  • the mobile terminal stores the clustering information of the server on the image, that is, the second terminal of the same image of the mobile terminal
  • the cluster information replaces the first cluster information.
  • two mobile terminals A and B belonging to the same account upload image 2 to the server, wherein the image information update time of image 2 in mobile terminal A is 18:00 on September 4, 2017, and image 2 in mobile terminal B.
  • the image information update time is 17:00 on September 3, 2017, the server stores the image 2 uploaded by the mobile terminal, and transmits the cluster information of the image 2 to the mobile terminal A and the mobile terminal B.
  • the mobile terminal B detects that the packet identification of the image 2 by the mobile terminal B and the server is inconsistent, and the image information update time corresponding to the image 2 sent by the server is later than the image information update time corresponding to the image 2 in the mobile terminal B, then the mobile terminal B
  • the storage server clusters information for image 2.
  • the group corresponding to the image with the image information update time is taken as the standard.
  • the multi-end can perform clustering according to the image after updating the image information in time, thereby ensuring consistency of data processing and avoiding data disorder caused by inconsistency of multi-end data.
  • the mobile terminal clusters the first facial image set to obtain the first clustering information, including:
  • Step 502 When it is detected that the image update list is not empty, acquire the first face feature information of the face image in the image update list.
  • the mobile terminal stores an image update list.
  • the mobile terminal adds an image or image information update
  • the mobile terminal marks the updated image and the image information updated image in the image update list.
  • the above image information update includes: recognizing a face change in the image, changing the image group, and the like.
  • the mobile terminal detects that there is an image in the image update list
  • the first face feature information of the face image in the image update list may be acquired according to the feature recognition model.
  • the recognition of the face in the image is increased, the facial feature information of the added face is added correspondingly when the first facial feature information is acquired.
  • the face recognition is reduced in the image, the facial feature information of the reduced face is deleted correspondingly when the first face feature information is acquired.
  • Step 504 Perform similarity matching between the first facial feature information and the second facial feature information, where the second facial feature information is facial feature information of the clustered facial image of the mobile terminal.
  • Step 506 When the similarity exceeds the preset threshold, the first facial feature information is divided into the group corresponding to the second facial feature information.
  • the mobile terminal may similarly match the first facial feature information with the facial feature information of the human face that has been clustered by the mobile terminal.
  • the first facial feature information may be divided into the group corresponding to the second facial feature information, and the preset threshold may be a preset value of the mobile terminal, or may be a preset value of the server. , can also be manually entered values for the user.
  • the updated image is re-clustered, and the clustering information corresponding to the image is updated in time when the image information is updated, thereby ensuring timely processing of the image. Sex.
  • the image processing method further includes at least one of the following cases:
  • Timing sends a second clustering request to the server.
  • the mobile terminal may send a second clustering request to the server, and the server may cluster the second facial image set uploaded by the mobile terminal according to the second clustering request.
  • the mobile terminal may send a second clustering request to the server according to a preset time interval, and the mobile terminal may also periodically send a second clustering request to the server.
  • the mobile terminal may further send a second clustering request to the server according to the triggering request sent by the server.
  • the mobile terminal After receiving the triggering request sent by the server, the mobile terminal may detect the current second facial image set of the mobile terminal and the last uploading server of the mobile terminal. Is the second face image collection the same? If they are different, it indicates that the face image in the second face image set in the mobile terminal changes, re-uploads the second face image set, and sends a second clustering request to the server.
  • the mobile terminal can send the second clustering request to the server under different conditions, which ensures the real-time clustering of the image in the mobile terminal by the server, and ensures that the mobile terminal is only specific.
  • the second clustering request is sent to the server under the condition. Timing is sent and sent at a preset time interval to avoid sending the second cluster to the server at a high frequency, which reduces the power consumption of the mobile terminal. Sending the second clustering request in the charging state, to avoid sending the second clustering request when the mobile terminal is low, increasing the power consumption of the mobile terminal, causing the mobile terminal to lose power quickly. The situation has increased user stickiness.
  • the image processing method further includes:
  • Step 602 When receiving the face image sent by the server, detecting whether the same face image is stored in the mobile terminal.
  • the server may merge the face images uploaded by the plurality of mobile terminals of the same account, and compare the merged face image set with the second face image set uploaded by each mobile terminal.
  • the server may separately send the face images other than the second face image set in the merged face image set to the corresponding mobile terminal. After receiving the face image sent by the server, the mobile terminal can detect whether the same face image exists in the mobile terminal.
  • Step 604 when the mobile terminal does not store the same face image, store the face image sent by the server.
  • Step 606 When the mobile terminal stores the same face image, it is detected whether the image information of the same face image is the same; when the image information of the same face image is different, the face image with a later image operation time is stored.
  • the mobile terminal stores the face image sent by the server. If the mobile terminal has a face image sent by the server, it is detected whether the image information of the face image sent by the server is the same as the image information of the same image in the mobile terminal. If they are not the same, the face image whose image operation time is late is stored. That is, if the image operation time of the face image in the mobile terminal is late, the face image sent by the server is not saved, and the mobile terminal may upload the face image to the server, so that the server stores the face image with the image operation time later. If the image of the face image sent by the server is operated at a later time, the same face image in the mobile terminal is replaced with the face image sent by the server.
  • the image processing method in the embodiment of the present application when image synchronization is implemented in multiple ends, the image with the latest image operation time is stored. When multi-end data synchronization is ensured, the image data is also updated in time, which improves the stability and real-time of the data.
  • FIG. 7 is a flow chart of an image processing method in another embodiment. As shown in FIG. 7, an image processing method is applied to a server, including:
  • Step 702 When receiving the second clustering request uploaded by the mobile terminal, clustering the second facial image set uploaded by the mobile terminal to obtain the second clustering information.
  • the server can receive the second face image set uploaded by the mobile terminal.
  • the second facial image set may be a set of facial images stored in the memory by the mobile terminal.
  • the server may cluster the second facial image set to obtain the second clustering information.
  • the clustering of the second face image set by the server includes: the server extracting face feature information of the face image in the second face image set according to the feature recognition model.
  • the server further performs similarity matching on the face feature information of the face image in the second face image set, and divides the portrait feature information whose similarity exceeds the second threshold into the same group.
  • the second threshold may be a preset value of the mobile terminal, a preset value of the server, or a value manually input by the user.
  • Step 704 Send second cluster information to the mobile terminal.
  • the server may return the clustering information of the second facial image set to the mobile terminal, that is, the server may send the second clustering information to the mobile terminal.
  • Step 706 Receive updated second cluster information uploaded by the mobile terminal, and replace the second cluster information with the updated second cluster information.
  • the server may further receive the updated second cluster information uploaded by the mobile terminal, and the server may search for the original second cluster information corresponding to the updated second cluster information, and replace the original second cluster with the updated second cluster information. Class information.
  • the server may cluster the face images uploaded by the mobile terminal.
  • the server may further receive clustering information of the updated face image uploaded by the mobile terminal, and replace the original clustering information with the clustering information of the updated face image.
  • the image is clustered by the server to ensure the accuracy of face image recognition.
  • the cluster information is updated to ensure the consistency of multi-end data and improve the stability of the data.
  • the image processing method further includes:
  • the server may merge the second face image sets uploaded by the plurality of mobile terminals of the same account, and compare the merged face image sets with the second face image sets uploaded by the respective mobile terminals.
  • the server may separately send the face images other than the second face image set in the merged face image set to the corresponding mobile terminal.
  • the image processing method in the embodiment of the present invention can realize synchronization of image data between multiple mobile terminals of the same account, thereby ensuring consistency of multi-end data and improving data stability.
  • the image processing method further includes: receiving a second face image set uploaded by the plurality of mobile terminals of the same account, and the same image in the second face image set uploaded by the plurality of mobile terminals of the same account.
  • the image information is different, the same image whose image operation time is the latest is stored.
  • the server may receive the second face image set uploaded by the plurality of mobile terminals of the same account, and merge the second face image sets uploaded by the plurality of mobile terminals of the same account. If the mobile terminal detects that the image information of the same image uploaded by the plurality of mobile terminals of the same account is different, the server searches for the latest one of the image operation moments in the plurality of same images and stores them.
  • the server when the server receives the same image uploaded by multiple mobile terminals of the same account, if it is detected that the image information of the same image uploaded by the multiple mobile terminals is inconsistent, the server stores the latest image of the image operation time. The real-time nature of the data is guaranteed.
  • the image processing method further includes:
  • the server may receive the second clustering request uploaded by the plurality of mobile terminals, and generate a clustering request queue according to the order in which the second clustering request is received. When the server detects the presence of the same in the cluster request queue A plurality of second clustering requests uploaded by the mobile terminal may combine multiple clustering requests uploaded by the same terminal into one second clustering request.
  • the server merges multiple second clustering requests uploaded by the same mobile terminal into one second clustering request, thereby avoiding multiple second clustering requests, multiple triggering image clustering, wasting server resources.
  • the situation reduces server power consumption and increases the processing speed of the server.
  • the image processing method further includes:
  • Step 802 When multiple clustering requests uploaded by multiple mobile terminals including the same account in the clustering request queue are detected, multiple second clustering requests uploaded by multiple mobile terminals of the same account are combined into one Two clustering requests.
  • Step 804 Acquire a second facial image set corresponding to multiple mobile terminals of the same account.
  • Step 806 Clustering a second face image set corresponding to multiple mobile terminals of the same account to obtain second cluster information.
  • Step 808 Send second cluster information to multiple mobile terminals of the same account.
  • the server may also detect whether multiple second cluster requests uploaded by multiple mobile terminals of the same account in the cluster request queue, and if so, merge multiple second cluster requests uploaded by multiple mobile terminals of the same account into A second clustering request.
  • the server may also merge the second face image sets uploaded by the plurality of mobile terminals of the same account. After the plurality of second clustering requests uploaded by the plurality of mobile terminals of the same account are merged into one second clustering request, the second facial image set uploaded by the plurality of mobile terminals of the same account may be acquired and merged.
  • the second clustering information is sent to the mobile terminal that uploaded the second clustering request among the plurality of mobile terminals of the same account.
  • the server may also send the second cluster information to each of the plurality of mobile terminals of the same account.
  • the server may combine the second clustering requests uploaded by the multiple mobile terminals of the same account into one, and avoid multiple clustering requests to trigger the server to cluster the face images multiple times, thereby saving the image processing method.
  • Server resources improve the speed of image processing in the server.
  • each step in the flowchart of the image processing method in each of the above embodiments is in accordance with an indication of an arrow Displayed in sequence, but these steps are not necessarily performed in the order indicated by the arrows. Except as explicitly stated herein, the execution of these steps is not strictly limited, and may be performed in other sequences. Moreover, at least some of the steps in the flowchart of the image processing method in each of the above real-time examples may include a plurality of sub-steps or stages, which are not necessarily performed at the same time, but may be executed at different times. The order of execution is not necessarily performed sequentially, but may be performed alternately or alternately with at least a portion of other steps or sub-steps or stages of other steps.
  • FIG. 9 is a block diagram showing the structure of an image processing apparatus in an embodiment.
  • an image processing apparatus running on a mobile terminal, includes:
  • the first clustering module 902 is configured to: when receiving the first clustering request, the mobile terminal clusters the first facial image set to obtain first clustering information.
  • the receiving module 904 is configured to receive second cluster information sent by the server, where the second clustering information is clustering information of the second facial image set uploaded by the server to the mobile terminal.
  • the obtaining module 906 is configured to obtain a comparison result between the first cluster information and the second cluster information.
  • the updating module 908 is configured to update at least one of the first cluster information and the second cluster information according to the type of the comparison result.
  • the first cluster information includes a first image identification; the second cluster information includes a second image identification.
  • the update module 908 is further configured to obtain the first image identifier set and the second image identifier set; when the first image identifier set includes the second image identifier set, and the first image identifier set is not equal to the second image identifier set, according to the second aggregation The class information re-clusters the first face image set to obtain the updated first cluster information.
  • the first cluster information includes a first face identifier; the second cluster information includes a second face identifier; the update module 908 is further configured to acquire a first face identifier and a second face of the same image.
  • the identifier is that when the face in the second face identifier is more than the face in the first face identifier, the first cluster information is replaced by the second cluster information of the same image.
  • the update module 908 is further configured to: when the face in the first face identifier is more than the face in the second face identifier, and the face in the first face identifier has a user group identifier, Will be the same
  • the first clustering information uploading server of the image the first clustering information is used to replace the second clustering information of the same image.
  • the update module 908 is further configured to upload the first cluster information of the same image to the server when the second face identifier is unmanned, and the first cluster information is used to replace the second cluster of the same image. information.
  • the first clustering information comprises a first grouping identifier; the second clustering information comprises a second grouping identifier.
  • the update module 908 is further configured to acquire the first group identifier and the second group identifier of the same image, and when the first group identifier is different from the second group identifier, obtain the first time corresponding to the first group identifier and the second group identifier. a second time; when the first time is later than the second time, the first cluster information of the same image is uploaded to the server, and the first cluster information is used to replace the second cluster information of the same image; when the second time is later than At the first moment, the first cluster information is replaced with the second cluster information of the same image.
  • the first clustering module 902 is further configured to: when detecting that the image update list is not empty, acquiring first face feature information of the face image in the image update list; The face feature information is similarly matched, and the second face feature information is face feature information of the cluster face image of the mobile terminal; when the similarity exceeds a preset threshold, the first face feature information is divided into the second face feature information. The group corresponding to the face feature information.
  • FIG. 10 is a block diagram showing the structure of an image processing apparatus in another embodiment.
  • the image processing apparatus described above includes a first clustering module 1002, a receiving module 1004, an obtaining module 1006, an updating module 1008, and a second transmitting module 1010.
  • the first clustering module 1002, the receiving module 1004, the obtaining module 1006, and the updating module 1008 have the same functions as the corresponding modules in FIG. 9.
  • the second sending module 1010 is configured to send a second clustering request to the server according to a preset time interval.
  • the second sending module 1010 is further configured to periodically send a second clustering request to the server.
  • the second sending module 1010 is further configured to receive a trigger request sent by the server, and detect that the current second face image set of the mobile terminal is different from the second face image set of the last uploading server of the mobile terminal, and send the second aggregation to the server. Class request.
  • FIG. 11 is a block diagram showing the structure of an image processing apparatus in another embodiment.
  • the image processing apparatus includes a first clustering module 1102, a receiving module 1104, an obtaining module 1106, an updating module 1108, a detecting module 1110, and a first storage module 1112.
  • the first clustering module 1102, the receiving module 1104, the obtaining module 1106, and the updating module 1108 have the same functions as the corresponding modules in FIG.
  • the detecting module 1110 is configured to detect whether the same face image is stored in the mobile terminal when receiving the face image sent by the server.
  • the first storage module 1112 is configured to store a face image sent by the server when the mobile terminal does not store the same face image.
  • the first storage module 1112 is further configured to: when the mobile terminal stores the same face image, detecting whether the image information of the same face image is the same; when the image information of the same face image is different, storing the face image with a later image operation time .
  • FIG. 12 is a block diagram showing the structure of an image processing apparatus in another embodiment.
  • an image processing apparatus running on a server, includes:
  • the second clustering module 1202 is configured to: when receiving the second clustering request uploaded by the mobile terminal, clustering the second facial image set uploaded by the mobile terminal to obtain the second clustering information.
  • the first sending module 1204 is configured to send second cluster information to the mobile terminal.
  • the receiving module 1206 is configured to receive the updated second cluster information uploaded by the mobile terminal.
  • the replacement module 1208 is configured to replace the second cluster information with the updated second cluster information.
  • FIG. 13 is a block diagram showing the structure of an image processing apparatus in another embodiment.
  • an image processing apparatus includes a second clustering module 1302, a first transmitting module 1304, a receiving module 1306, a replacement module 1308, a merging module 1310, and a comparison module 1312.
  • the second clustering module 1302, the first sending module 1304, the receiving module 1306, and the replacing module 1308 have the same functions as the corresponding modules in FIG.
  • the merging module 1310 is configured to combine the second face image set uploaded by the plurality of mobile terminals when the plurality of mobile terminals of the same account are received, and merge the second face image sets uploaded by the plurality of mobile terminals;
  • the comparison module 1312 is configured to compare the merged face image set with the second face image set uploaded by each of the plurality of mobile terminals.
  • the first sending module 1304 is further configured to separately send the face image in the merged face image set to each of the plurality of mobile terminals according to the comparison result.
  • the merging module 1310 is further configured to generate a clustering request queue according to the order in which the second clustering request is received; when detecting that the clustering request queue includes multiple second clustering requests uploaded by the same mobile terminal, The plurality of second clustering requests uploaded by the same mobile terminal are combined into one second clustering request.
  • the merging module 1310 is further configured to: when detecting multiple second clustering requests uploaded by multiple mobile terminals including the same account in the clustering request queue, uploading multiple mobile terminals of the same account
  • the second clustering request is merged into one second clustering request.
  • the second clustering module 1302 is further configured to acquire a second facial image set corresponding to the plurality of mobile terminals of the same account; and cluster the second facial image set corresponding to the plurality of mobile terminals of the same account to obtain the second clustering information.
  • the first sending module 1304 is further configured to separately send the second cluster information to multiple mobile terminals of the same account.
  • FIG. 14 is a block diagram showing the structure of an image processing apparatus in another embodiment.
  • an image processing apparatus includes a second clustering module 1402, a first transmitting module 1404, a receiving module 1406, a replacement module 1408, and a storage module 1410.
  • the second clustering module 1402, the first sending module 1404, the receiving module 1406, and the replacing module 1408 have the same functions as the corresponding modules in FIG.
  • the receiving module 1406 is further configured to receive a second facial image set uploaded by multiple mobile terminals of the same account.
  • the storage module 1410 is configured to store the same image with the latest image operation time when the image information of the same image in the second face image set uploaded by the plurality of mobile terminals of the same account is different.
  • the various modules in the image processing apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof.
  • the network interface may be an Ethernet card or a wireless network card.
  • the above modules may be embedded in the hardware in the processor or in the memory in the server, or may be stored in the memory in the server, so that the processor calls the corresponding operations of the above modules.
  • module is intended to mean a computer-related entity, which may be hardware, a combination of hardware and software, software, or software in execution.
  • a module can be, but is not limited to being, a process running on a processor, a processor, an object, an executable code, a line of execution Program, program, and/or computer.
  • an application running on a server and a server can be a module.
  • One or more modules can reside within a process and/or a thread of execution, and a module can be located in a computer and/or distributed between two or more computers.
  • the embodiment of the present application further provides a mobile terminal.
  • a mobile terminal As shown in FIG. 14 , for the convenience of description, only the parts related to the embodiments of the present application are shown. If the specific technical details are not disclosed, please refer to the method part of the embodiment of the present application.
  • the mobile terminal can be any mobile device, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), an on-board computer, a wearable device, or the like, and the mobile terminal is used as a mobile phone as an example. :
  • FIG. 15 is a block diagram showing a partial structure of a mobile phone related to a mobile terminal provided by an embodiment of the present application.
  • the mobile phone includes: a radio frequency (RF) circuit 1510 , a memory 1520 , an input unit 1530 , a display unit 1540 , a sensor 1550 , an audio circuit 1560 , a wireless fidelity (WiFi) module 1570 , and a processor 1580 .
  • RF radio frequency
  • the RF circuit 1510 can be used for receiving and transmitting information during the transmission and reception of information or during the call.
  • the downlink information of the base station can be received and processed by the processor 1580.
  • the uplink data can also be sent to the base station.
  • RF circuits include, but are not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.
  • LNA Low Noise Amplifier
  • RF circuitry 1510 can also communicate with the network and other devices via wireless communication.
  • the above wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division). Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), e-mail, Short Messaging Service (SMS), and the like.
  • GSM Global System of Mobile communication
  • GPRS General Pack
  • the memory 1520 can be used to store software programs and modules, and the processor 1580 executes various functional applications and data of the mobile phone by running software programs and modules stored in the memory 1520. deal with.
  • the memory 1520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as an application of a sound playing function, an application of an image playing function, etc.);
  • the data storage area can store data (such as audio data, address book, etc.) created according to the use of the mobile phone.
  • memory 1520 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • the input unit 1530 can be configured to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the handset 1500.
  • the input unit 1530 may include a touch panel 1531 and other input devices 1532.
  • the touch panel 1531 which may also be referred to as a touch screen, can collect touch operations on or near the user (such as a user using a finger, a stylus, or the like on the touch panel 1531 or near the touch panel 1531. Operation) and drive the corresponding connection device according to a preset program.
  • the touch panel 1531 can include two portions of a touch detection device and a touch controller.
  • the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
  • the processor 1580 is provided and can receive commands from the processor 1580 and execute them.
  • the touch panel 1531 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
  • the input unit 1530 may also include other input devices 1532.
  • other input devices 1532 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.).
  • the display unit 1540 can be used to display information input by the user or information provided to the user as well as various menus of the mobile phone.
  • the display unit 1540 may include a display panel 1541.
  • the display panel 1541 can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.
  • the touch panel 1531 can cover the display panel 1541. When the touch panel 1531 detects a touch operation thereon or nearby, the touch panel 1531 transmits to the processor 1580 to determine the type of the touch event, and then the processor 1580 is The type of touch event provides a corresponding visual output on display panel 1541.
  • touch panel 1531 and the display panel 1541 are used as two independent components to implement the input and input functions of the mobile phone.
  • the touch panel 1531 and the display panel 1541 can be integrated to implement the input of the mobile phone. And output function.
  • the handset 1500 can also include at least one type of sensor 1550, such as a light sensor, motion sensor, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1541 according to the brightness of the ambient light, and the proximity sensor may close the display panel 1541 and/or when the mobile phone moves to the ear. Or backlight.
  • the motion sensor may include an acceleration sensor, and the acceleration sensor can detect the magnitude of the acceleration in each direction, and the magnitude and direction of the gravity can be detected at rest, and can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching), and vibration recognition related functions (such as Pedometer, tapping, etc.; in addition, the phone can also be equipped with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors.
  • the acceleration sensor can detect the magnitude of the acceleration in each direction, and the magnitude and direction of the gravity can be detected at rest, and can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching), and vibration recognition related functions (such as Pedometer, tapping, etc.; in addition, the phone can also be equipped with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors.
  • Audio circuitry 1560, speaker 1561, and microphone 1562 can provide an audio interface between the user and the handset.
  • the audio circuit 1560 can transmit the converted electrical data of the received audio data to the speaker 1561, and convert it into a sound signal output by the speaker 1561.
  • the microphone 1562 converts the collected sound signal into an electrical signal, and the audio circuit 1560. After receiving, it is converted into audio data, and then processed by the audio data output processor 1580, transmitted to another mobile phone via the RF circuit 1510, or outputted to the memory 1520 for subsequent processing.
  • WiFi is a short-range wireless transmission technology.
  • the mobile phone through the WiFi module 1570 can help users to send and receive e-mail, browse the Internet and access streaming media, etc. It provides users with wireless broadband Internet access.
  • FIG. 15 shows the WiFi module 1570, it will be understood that it does not belong to the essential configuration of the handset 1500 and may be omitted as needed.
  • the processor 1580 is a control center for the handset that connects various portions of the entire handset using various interfaces and lines, by executing or executing software programs and/or modules stored in the memory 1520, and invoking data stored in the memory 1520, The phone's various functions and processing data, so that the overall monitoring of the phone.
  • processor 1580 can include one or more processing units.
  • the processor 1580 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application, etc.; The device mainly handles wireless communication. It will be appreciated that the above described modem processor may also not be integrated into the processor 1580.
  • the handset 1500 also includes a power source 1590 (such as a battery) that powers the various components.
  • a power source 1590 such as a battery
  • the power source can be logically coupled to the processor 1580 via a power management system to manage functions such as charging, discharging, and power management through the power management system.
  • the handset 1500 can also include a camera, a Bluetooth module, and the like.
  • the processor 1580 included in the mobile terminal implements the following steps when executing the computer program stored in the memory:
  • the mobile terminal clusters the first face image set to obtain the first clustering information.
  • the first clustering information includes a first image identifier; the second clustering information includes a second image identifier; and the processor 1580 performing the updating of the first clustering information according to the type of the comparison result comprises: acquiring the first image identifier And the second image identification set; the first image identification set includes a second image identification set, and the first image identification set is not equal to the second image identification set, and the first facial image set is re-aggregated according to the second clustering information
  • the class gets the updated first cluster information.
  • the first cluster information includes a first face identifier; the second cluster information includes a second face identifier; the processor 1580 performs updating the first cluster information and the second cluster according to the type of the comparison result. At least one of the information includes: obtaining a first face identifier and a second face identifier of the same image, and when the second face identifier has more faces than the first face identifier, the second image of the same image is used The class information replaces the first cluster information.
  • the processor 1580 further performs: when the face in the first face identifier is more than the face in the second face identifier, and the face in the first face identifier has a user group identifier, Uploading the first cluster information of the same image to the server, and the first clustering information is used to replace the second cluster of the same image Class information.
  • the processor 1580 further performs: when the face in the first face identifier is more than the face in the second face identifier, and the face in the first face identifier does not carry the user group identifier The first cluster information is replaced with the second cluster information of the same image.
  • the processor 1580 further executes: when the second face identifier is unmanned, the first cluster information of the same image is uploaded to the server, and the first cluster information is used to replace the second cluster of the same image. information.
  • the first clustering information includes a first grouping identifier; the second clustering information includes a second grouping identifier; the processor 1580 performs the updating of the first clustering information and the second clustering information according to the type of the comparison result.
  • the processor 1580 performs, when receiving the first clustering request, the mobile terminal clusters the first facial image set to obtain the first clustering information, including: when detecting that the image update list is not empty, acquiring the image Updating first face feature information of the face image in the list; matching similarity between the first face feature information and the second face feature information, wherein the second face feature information is a person whose mobile terminal has clustered the face image The face feature information; when the similarity exceeds the preset threshold, the first face feature information is divided into the group corresponding to the second face feature information.
  • the processor 1580 further performs at least one of: sending a second clustering request to the server according to a preset time interval; timing sending a second clustering request to the server; receiving a trigger request sent by the server And detecting that the current second face image set of the mobile terminal is different from the second face image set of the last uploading server of the mobile terminal, and sending a second clustering request to the server.
  • the processor 1580 further performs: when receiving a face image sent by the server, Detecting whether the same face image is stored in the mobile terminal; when the mobile terminal does not store the same face image, storing the face image sent by the server; when the mobile terminal stores the same face image, detecting whether the image information of the same face image is the same; When the image information of the same face image is different, the face image whose image operation time is later is stored.
  • FIG. 16 is a schematic diagram showing the internal structure of a server in an embodiment.
  • the server includes a processor connected through a system bus, a non-volatile storage medium, an internal memory, and a network interface.
  • the processor is used to provide computing and control capabilities to support the operation of the entire computer device.
  • the memory is used to store data, programs, etc., and at least one computer program is stored on the memory, and the computer program can be executed by the processor to implement the wireless network communication method suitable for the computer device provided in the embodiments of the present application.
  • the memory may include a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random storage memory (Random-Access-Memory, RAM).
  • the memory includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer program.
  • the computer program can be executed by a processor for implementing an image processing method provided by the various embodiments above.
  • the internal memory provides a cached operating environment for operating system computer programs in a non-volatile storage medium.
  • the network interface may be an Ethernet card or a wireless network card or the like for communicating with an external computer device.
  • the server can be implemented with a stand-alone server or a server cluster consisting of multiple servers. It will be understood by those skilled in the art that the structure shown in FIG.
  • 16 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied.
  • the specific server may include a ratio. More or fewer components are shown in the figures, or some components are combined, or have different component arrangements.
  • the processor further performs: combining the second face image set uploaded by the plurality of mobile terminals when receiving the second face image set uploaded by the plurality of mobile terminals of the same account; and combining the merged faces
  • the image set is compared with the second face image set uploaded by each of the plurality of mobile terminals, and the face images in the merged face image set are respectively sent to each of the plurality of mobile terminals according to the comparison result.
  • the processor further performs: receiving a second face image set uploaded by the plurality of mobile terminals of the same account, and image information of the same image in the second face image set uploaded by the plurality of mobile terminals of the same account. When they are different, the same image with the latest image operation time is stored.
  • the processor after receiving the second clustering request uploaded by the mobile terminal, the processor further performs: generating a clustering request queue according to the order in which the second clustering request is received; when detecting the clustering request queue And including multiple second clustering requests uploaded by the same mobile terminal, and combining multiple second clustering requests uploaded by the same mobile terminal into one second clustering request.
  • the processor further performs: when detecting a plurality of second clustering requests uploaded by the plurality of mobile terminals including the same account in the clustering request queue, uploading the plurality of mobile terminals of the same account
  • the second clustering request is merged into a second clustering request; the second facial image set corresponding to the plurality of mobile terminals of the same account is acquired; and the second facial image set corresponding to the plurality of mobile terminals of the same account is clustered.
  • Two clustering information respectively sending second cluster information to a plurality of mobile terminals of the same account.
  • the embodiment of the present application also provides a computer readable storage medium.
  • One or more non-transitory computer readable storage media containing computer executable instructions that, when executed by one or more processors, cause the processor to perform the following steps:
  • the mobile terminal clusters the first face image set to obtain the first clustering information.
  • the first cluster information includes a first image identifier; the second cluster information includes a second image identifier; and updating the first cluster information according to the type of the comparison result comprises: acquiring the first image identifier set and the second The image identification set; when the first image identification set includes the second image identification set, and the first image identification set is not equal to the second image identification set, re-clustering the first facial image set according to the second cluster information to obtain an update First clustering information.
  • the first cluster information includes a first face identifier; the second cluster information includes a second face identifier; and at least one of the first cluster information and the second cluster information is updated according to the type of the comparison result.
  • the method includes: acquiring a first face identifier and a second face identifier of the same image, and replacing a face in the second face identifier with a face in the first face identifier, replacing the second cluster information with the same image A cluster of information.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: when the face in the first face identifier is more than the face in the second face identifier, and the first The face in the face identifier has a user group identifier, and the first cluster information of the same image is uploaded to the server, and the first cluster information is used to replace the second cluster information of the same image.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: when the face in the first face identifier is more than the face in the second face identifier, and the first The face in the face identifier has no user group identifier, and the first cluster information is replaced by the second cluster information of the same image.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: uploading the first cluster information of the same image to the server when the second face identifier is unmanned, The first clustering information is used to replace the second clustering information of the same image.
  • the first cluster information includes a first group identifier; the second cluster information includes a second group identifier; and at least one of updating the first cluster information and the second cluster information according to the type of the comparison result includes Obtaining a first group identifier and a second group identifier of the same image, when the first group identifier is different from the second group identifier, acquiring a first time corresponding to the first group identifier and a second time corresponding to the second group identifier; When the first moment is later than the second moment, the first cluster of the same image is sent The first clustering information is used to replace the second clustering information of the same image; when the second time is later than the first time, the first clustering information is replaced by the second clustering information of the same image.
  • the mobile terminal clustering the first facial image set to obtain the first clustering information includes: when detecting that the image update list is not empty, acquiring the image update list First face feature information of the face image; the first face feature information and the second face feature information are similarly matched, and the second face feature information is face feature information of the clustered face image of the mobile terminal; When the similarity exceeds the preset threshold, the first facial feature information is divided into the packets corresponding to the second facial feature information.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: transmitting the second clustering request to the server at a preset time interval; timing transmitting the second cluster to the server Receiving a trigger request sent by the server, detecting that the current second face image set of the mobile terminal is different from the second face image set of the last uploading server of the mobile terminal, and sending a second clustering request to the server.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: detecting whether the same face image is stored in the mobile terminal when receiving the face image transmitted by the server; The terminal does not store the same face image, and stores the face image sent by the server; when the mobile terminal stores the same face image, detects whether the image information of the same face image is the same; when the image information of the same face image is different, the image is stored A face image that is operated at a later time.
  • the embodiment of the present application also provides a computer readable storage medium.
  • One or more non-transitory computer readable storage media containing computer executable instructions that, when executed by one or more processors, cause the processor to perform the following steps:
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: moving the plurality of mobile images when the second facial image set uploaded by the plurality of mobile terminals of the same account is received The second face image set uploaded by the terminal is merged; the merged face image set is respectively compared with the second face image set uploaded by each of the plurality of mobile terminals, and is respectively sent to the plurality of mobile terminals according to the comparison result.
  • Each mobile terminal transmits a face image in the merged face image set.
  • the processor when the computer executable instructions are executed by the one or more processors, the processor is further configured to: receive the second face image set uploaded by the plurality of mobile terminals of the same account, when multiple of the same account When the image information of the same image in the second face image set uploaded by the mobile terminal is different, the same image whose image operation time is the latest is stored.
  • the processor after receiving the second clustering request uploaded by the mobile terminal, when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: receiving the second clustering request The sequence generates a clustering request queue; when detecting that the clustering request queue includes multiple second clustering requests uploaded by the same mobile terminal, combining the plurality of second clustering requests uploaded by the same mobile terminal into one second cluster request.
  • the processor when the computer executable instructions are executed by the one or more processors, causing the processor to further perform: when detecting a plurality of second aggregations uploaded by the plurality of mobile terminals including the same account in the cluster request queue a class request, combining a plurality of second clustering requests uploaded by the plurality of mobile terminals of the same account into one second clustering request; acquiring a second face image set corresponding to the plurality of mobile terminals of the same account; The second face image set corresponding to the plurality of mobile terminals is clustered to obtain second cluster information; and the second cluster information is separately sent to the plurality of mobile terminals of the same account.
  • Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory can include random access memory (RAM), which acts as an external cache.
  • RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual Data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchronized Link (Synchlink) DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamics RAM (RDRAM).
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDR SDRAM dual Data rate SDRAM
  • ESDRAM Enhanced SDRAM
  • SLDRAM Synchronized Link
  • SLDRAM Synchronized Link
  • RDRAM Memory Bus
  • RDRAM Direct RAM
  • DRAM Direct Memory Bus Dynamic RAM
  • RDRAM Memory Bus Dynamics RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种图像处理方法,包括:当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息;接收服务器发送的第二聚类信息,所述第二聚类信息是所述服务器对所述移动终端上传的第二人脸图像集合的聚类信息;获取所述第一聚类信息与所述第二聚类信息的对比结果,根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种。

Description

图像处理方法、装置、移动终端、服务器和存储介质 技术领域
本申请涉及计算机技术领域,特别是涉及一种图像处理方法、装置、移动终端、服务器和存储介质。
背景技术
随着智能移动终端和互联网技术的飞速发展,对智能移动终端中图像的分类技术越来越成熟。常用的对智能移动终端中图像分类可包括:将图像按照人脸、地点和时间进行分组。对智能移动终端中图像进行分组可使用户分类查看智能移动终端中图像,用户查看智能移动终端中图像的方式更便捷、更快速。
发明内容
根据本申请的各种实施例,提供一种图像处理方法、装置、移动终端、服务器和存储介质。
一种图像处理方法,包括:
当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息;
接收服务器发送的第二聚类信息,所述第二聚类信息是所述服务器对所述移动终端上传的第二人脸图像集合的聚类信息;
获取所述第一聚类信息与所述第二聚类信息的对比结果,根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种。
一种图像处理装置,应用于移动终端,包括:
第一聚类模块,用于当接收到第一聚类请求,移动终端对第一人脸图像 集合聚类得到第一聚类信息;
接收模块,用于接收服务器发送的第二聚类信息,所述第二聚类信息是所述服务器对所述移动终端上传的第二人脸图像集合的聚类信息;
获取模块,用于获取所述第一聚类信息与所述第二聚类信息的对比结果;
更新模块,用于根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种。
一种移动终端,包括存储器及处理器,所述存储器中储存有计算机可读指令,所述指令被所述处理器执行时,使得所述处理器执行如上所述的图像处理方法。
一个或多个包含计算机可读指令的非易失性计算机可读存储介质,当所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行如上所述的图像处理方法。
一种图像处理方法,包括:
当接收到移动终端上传的第二聚类请求,对所述移动终端上传的第二人脸图像集合聚类得到第二聚类信息;
向所述移动终端发送所述第二聚类信息;
接收所述移动终端上传的更新后第二聚类信息,用所述更新后第二聚类信息替换所述第二聚类信息。
一种图像处理装置,应用于服务器,包括:
第二聚类模块,用于当接收到移动终端上传的第二聚类请求,对所述移动终端上传的第二人脸图像集合聚类得到第二聚类信息;
发送模块,用于向所述移动终端发送所述第二聚类信息;
接收模块,用于接收所述移动终端上传的更新后第二聚类信息;
替换模块,用于用所述更新后第二聚类信息替换所述第二聚类信息。
一种服务器,包括存储器及处理器,所述存储器中储存有计算机可读指令,所述指令被所述处理器执行时,使得所述处理器执行如上所述的图像处理方法。
一个或多个包含计算机可读指令的非易失性计算机可读存储介质,当所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行如上所述的图像处理方法。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更好地描述和说明这里公开的那些发明的实施例和/或示例,可以参考一幅或多幅附图。用于描述附图的附加细节或示例不应当被认为是对所公开的发明、目前描述的实施例和/或示例以及目前理解的这些发明的最佳模式中的任何一者的范围的限制。
图1为一个实施例中图像处理方法的应用环境示意图;
图2为一个实施例中移动终端与第一服务器、第二服务器进行交互的时序图;
图3为一个实施例中图像处理方法的流程图;
图4为另一个实施例中图像处理方法的流程图;
图5为另一个实施例中图像处理方法的流程图;
图6为另一个实施例中图像处理方法的流程图;
图7为另一个实施例中图像处理方法的流程图;
图8为另一个实施例中图像处理方法的流程图;
图9为一个实施例中图像处理装置的结构框图;
图10为另一个实施例中图像处理装置的结构框图;
图11为另一个实施例中图像处理装置的结构框图;
图12为另一个实施例中图像处理装置的结构框图;
图13为另一个实施例中图像处理装置的结构框图;
图14为另一个实施例中图像处理装置的结构框图;
图15为与本申请实施例提供的移动终端相关的手机的部分结构的框图;
图16为一个实施例中服务器的内部结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。
可以理解,本申请所使用的术语“第一”、“第二”等可在本文中用于描述各种元件,但这些元件不受这些术语限制。这些术语仅用于将第一个元件与另一个元件区分。举例来说,在不脱离本申请的范围的情况下,可以将第一聚类模块称为第二聚类模块,且类似地,可将第二聚类模块称为第一聚类模块。第一聚类模块和第二聚类模块两者都是聚类模块,但不是同一聚类模块。
图1为一个实施例中图像处理方法的应用环境示意图。如图1所示,该应用环境包括第一移动终端110、第二移动终端120、第一服务器130和第二服务器140。在第一移动终端110中存储有图像,上述图像可存储于第一移动终端110内存中,也可存储于第一移动终端110内置SD(Secure Digital Memory Card,安全数码卡)卡中。第一移动终端110可识别上述图像中包含的人脸图像,提取人脸图像中人脸特征信息,根据人脸特征信息对人脸图像进行聚类。第一移动终端110还可人脸图像上传第一服务器130,第一服务器130可提取人脸图像中人脸特征信息,并将提取出人脸特征信息发送给第二服务器140。第二服务器140可对人脸特征信息进行聚类,并将聚类信息发送给第一移动终端110。第一移动终端110在接收到第二服务器140发送的聚类信息后,可将第一移动终端110和第二服务器140对同一张人脸图像的聚类信息进行对比,并根据对比结果更新第一移动终端110对同一张人脸图像的聚类信息或第二服务器140对同一张人脸图像的聚类信息。第一移动终端110还可根据第二服务器140发送的聚类信息对第一移动终端110中未上传人脸图像进行聚类。
第二移动终端120与第一移动终端110的功能相同,第二移动终端120可对第二移动终端120中人脸图像进行聚类。第二移动终端120可将人脸图像上传第一服务器130。第一服务器130可识别出人脸图像中人脸特征信息,并将人脸特征信息上传第二服务器140。第二服务器140可对人脸特征信息进行聚类,并将聚类信息返回第二移动终端120。第二移动终端120在接收到第二服务器140发送的聚类信息后,可将第二移动终端120和第二服务器140对同一张人脸图像的聚类信息进行对比,并根据对比结果更新第二移动终端110对同一张人脸图像的聚类信息或第二服务器140对同一张人脸图像的聚类信息。第二移动终端120还可根据第二服务器140发送的聚类信息对第二移动终端120中未上传人脸图像进行聚类。
第一移动终端110或第二移动终端120上传第一服务器130的人脸图像可为内存中存储的人脸图像,也可为内置SD卡中存储的人脸图像,也可为内存和内置SD卡中存储的人脸图像。第一服务器130可为单独的一个服务器,也可为多个第一服务器130组成的第一服务器集群,或第一服务器集群中的某一台服务器;第二服务器140可为单独的一个服务器,也可为多个第二服务器140组成的第二服务器集群,或第二服务器集群中的某一台服务器。
第一移动终端110和第二移动终端120可为属于同一账号的两个移动终端,也可为属于不同账号的两个移动终端。
当第一移动终端110和第二移动终端120为属于同一账号的两个移动终端时,第一服务器130可将第一移动终端110和第二移动终端120上传的人脸图像合并。第一服务器130还可将合并后人脸图像发送给第一移动终端110和第二移动终端120,使第一移动终端110和第二移动终端120的数据同步。第一移动终端110和第二移动终端120可对第二服务器140发送第二聚类请求,第二服务器140可根据接收到第二聚类请求的顺序生成聚类请求队列。当第二服务器140检测到上述聚类请求队列中包括第一移动终端110发送的多个第二聚类请求,可将多个第二聚类请求合并为一个第二聚类请求。当第二服务器140检测到上述聚类请求队列中包括第二移动终端120发送的多个 第二聚类请求,可将多个第二聚类请求合并为一个第二聚类请求。当第二服务器140检测到上述聚类请求队列中包括第一移动终端110上传的第二聚类请求和第二移动终端120上传的第二聚类请求,可将多个第二聚类请求合并为一个第二聚类请求。
当第一移动终端110和第二移动终端120为属于不同账号的两个移动终端时,第一移动终端110和第二移动终端120可向第二服务器140上传第二聚类请求。第二服务器140可根据接收到第二聚类请求的顺序生成聚类请求队列,并按照聚类请求队列的顺序对第二聚类信息对应的人脸特征信息进行聚类。
在一个实施例中,第一服务器130和第二服务器140可为同一服务器。第一移动终端110或第二移动终端120可将人脸图像上传到服务器,服务器可提取人脸图像中人脸特征信息,并对提取出人脸特征信息进行聚类。服务器可将聚类信息返回第一移动终端110或第二移动终端120。服务器可根据接收到的第二聚类请求的顺序生成聚类请求队列,并将同一终端上传的多个第二聚类请求合并为一个第二聚类请求,将同一账号的多个移动终端分别上传的第二聚类请求合并为一个第二聚类请求。
图2为一个实施例中移动终端与第一服务器、第二服务器进行交互的时序图。如图2所示,移动终端210与第一服务器220、第二服务器230进行交互的过程,包括:
(1)接收到第一聚类请求,移动终端210对第一人脸图像集合聚类得到第一聚类信息。
当移动终端210接收到第一聚类请求时,可对移动终端210中第一人脸图像集合聚类得到第一聚类信息。上述第一人脸图像集合包括移动终端210内存存储的人脸图像和移动终端210内置SD(Secure Digital Memory Card,安全数字存储卡)卡中存储人脸图像。移动终端210对第一人脸图像集合聚类包括:移动终端210根据特征识别模型提取第一人脸图像集合中人脸图像的人脸特征信息,对上述人脸特征信息进行相似度匹配,根据匹配结果对第 一人脸图像集合中人脸图像进行聚类。
(2)移动终端210将第二人脸图像集合上传第一服务器220。
第一人脸图像集合包括第二人脸图像集合,上述第二人脸图像集合为移动终端210内存存储的人脸图像。移动终端210可将第二人脸图像集合上传第一服务器220。其中,移动终端210在上传第二人脸图像集合时,会获取第二人脸图像集合中第二服务器230上一次已聚类的人脸图像和用户分组的人脸图像,对第二服务器230上一次已聚类的人脸图像,移动终端210会上传对应的标记信息,使第二服务器230无需对已聚类的人脸图像重新聚类。对用户分组的人脸图像,移动终端210会上传人脸图像对应的用户分组信息,使第二服务器230和移动终端210对人脸图像的分组一致。
(3)第一服务器220提取第二人脸图像集合中人脸图像的人脸特征信息。
第一服务器220可根据特征识别模型提取第二人脸图像集合中人脸图像的人脸特征信息。第一服务器220中特征识别模型与第二服务器230中特征识别模型可相同或不同。
(4)第一服务器220将人脸特征信息发送给第二服务器230。
(5)移动终端210向第二服务器230发送第二聚类请求。
移动终端210可向第二服务器230发送第二聚类请求,使第二服务器230对第二人脸图像集合对应的人脸特征信息聚类。服务器可接收多个移动终端210上传的第二聚类请求,服务器可根据接收到第二聚类请求的顺序生成聚类请求队列,按照聚类请求队列中第二聚类请求的顺序对第二人脸图像集合进行聚类。第二服务器230可将同一移动终端210上传的多个第二聚类请求合并为一个第二聚类请求,第二服务器230也可将同一账号的多个移动终端210上传的多个第二聚类请求合并为一个第二聚类请求。
(6)第二服务器230对人脸特征信息进行聚类,得到第二聚类信息。
第二服务器230对人脸特征信息进行相似度匹配,根据匹配结果对人脸特征信息进行聚类。
(7)第二服务器230将第二聚类信息发送给移动终端210。
(8)移动终端210用第二聚类信息替换第一聚类信息。
(9)移动终端210根据第二聚类信息对第一人脸图像集合中除第二人脸图像集合外人脸图像进行聚类。
(10)移动终端210将第一聚类信息上传第二服务器230,第一聚类信息用于替换第二聚类信息。
移动终端210可将第一聚类信息和第二聚类信息进行对比,并根据对比结果更新第一聚类信息或第二聚类信息。其中,移动终端210还可根据第二聚类信息对第一人脸图像集合中除第二人脸图像集合外人脸图像进行聚类。
图3为一个实施例中图像处理方法的流程图。如图3所示,一种图像处理方法,应用于移动终端,包括:
步骤302,当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息。
移动终端可对存储的图像进行人脸识别,识别出存储的图像中包含的人脸图像。移动终端再根据特征识别模型提取人脸图像中人脸特征信息,并根据人脸特征信息对人脸图像进行聚类。上述第一聚类请求是对移动终端中存储的人脸图像进行聚类的请求。上述第一人脸图像集合是移动终端中存储的人脸图像,包括存储于移动终端内存中人脸图像和存储于移动终端内置SD卡中人脸图像。移动终端接收到第一聚类请求后,可对移动终端中存储的人脸图像进行聚类。
触发第一聚类请求的条件可包括以下情况中一种或多种:
(1)移动终端中特征识别模型更新。
(2)移动终端中图像更新列表不为空。
(3)移动终端接收到服务器发送的第二聚类信息,当检测到第二聚类信息对应的第二人脸图像集合小于第一人脸图像集合,触发第一聚类请求。
移动终端中存储有特征识别模型。当移动终端接收到服务器发送的最新版本的特征识别模型,移动终端可将移动终端中当前特征识别模型的版本号与服务器发送的特征识别模型的版本号进行对比,若移动终端当前特征识别 模型的版本号低于服务器发送的特征识别模型的版本号,移动终端更新特征识别模型。移动终端更新特征识别模型后,移动终端可根据更新后特征识别模型重新提取第一人脸图像集合中人脸图像的人脸特征信息,并根据人脸特征信息对第一人脸图像集合中人脸图像聚类得到第一聚类信息。在一个实施例中,移动终端更新特征识别模型后,可将第一人脸图像集合中已存储的人脸特征信息转换为更新后特征识别模型对应的人脸特征信息。移动终端仅对第一人脸图像集合中未存储人脸特征信息的人脸图像进行特征识别,获取人脸特征信息。移动终端再根据第一人脸图像集合中人脸图像对应的人脸特征信息对第一人脸图像集合聚类得到第一聚类信息。
移动终端中存储有图像更新列表,当移动终端中新增人脸图像或移动终端中人脸图像信息变更,移动终端会将新增人脸图像或变更信息的人脸图像存储于图像更新列表中。移动终端检测到图像更新列表不为空,触发第一聚类请求。在接收到第一聚类请求后,移动终端对图像更新列表中人脸图像提取人脸特征信息,在根据人脸特征信息对图像更新列表中人脸图像进行聚类。
移动终端接收到服务器发送的第二聚类信息后,可查找第二聚类信息对应的第二人脸图像集合。移动终端可检测第二人脸图像集合中人脸图像与第一人脸图像集合中人脸图像是否相同,当检测到第一人脸图像集合中人脸图像多于第二人脸图像集合中人脸图像时,触发第一聚类请求。移动终端将第一人脸图像集合中除第二人脸图像集合外的人脸图像作为第三人脸图像集合。移动终端提取第三人脸图像集合中人脸图像的人脸特征信息,移动终端可将第三人脸图像集合中人脸图像的人脸特征信息与第二人脸图像集合中人脸图像的人脸特征信息进行相似度匹配,当相似度超过第一阈值,则将第三人脸图像集合中人脸图像划分到第二人脸图像集合中人脸图像对应的分组。上述第二人脸图像集合中人脸图像对应的分组是移动终端根据第二聚类信息获取的。上述第一阈值可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。
在一个实施例中,当移动终端接收到第一聚类请求后,移动终端还可检 测当前条件是否满足预设条件。若检测到当前条件满足预设条件,则移动终端对第一人脸图像集合聚类得到第一聚类信息。
检测当前条件是否满足预设条件包括:
(1)检测当前时刻与上一次移动终端对第一人脸图像集合聚类的时刻之间的时间差是否超过预设时长,若超过预设时长,则满足预设条件。
(2)检测当前时刻是否是预设时刻,若当前时刻是预设时刻,则满足预设条件。
(3)检测移动终端是否处于充电状态,若移动终端处于充电状态,则满足预设条件。
上述预设条件中预设时刻和预设时长可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。移动终端中BatteryManager可通过intent广播电池信息,包括电池的充电状态、充电电流等。当充电状态改变时,BatteryManager会发送系统广播,移动终端可通过广播接收器接收到系统广播,根据系统广播内容判断移动终端当前的电池状态。
步骤304,接收服务器发送的第二聚类信息,第二聚类信息是服务器对移动终端上传的第二人脸图像集合的聚类信息。
移动终端可将第二人脸图像集合上传服务器,并向服务器发送第二聚类请求,以使服务器对第二人脸图像集合进行聚类。上述第二人脸图像集合可为移动终端中内存存储图像中包含的人脸图像。服务器在接收到移动终端上传的第二人脸图像集合和对应的第二聚类请求后,可根据特征识别模型提取第二人脸图像集合中人脸图像的人脸特征信息。服务器再将第二人脸图像集合中人脸图像的人脸特征信息进行相似度匹配,将相似度超过第二阈值的人像特征信息划分到同一分组。上述第二阈值可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。在对第二人脸图像集合中人脸特征信息聚类完毕后,服务器可将对第二人脸图像集合的聚类信息返还移动终端,即服务器可将第二聚类信息发送给移动终端。其中,移动终端和服务器中特征识别模型可相同或不同。
其中,移动终端在接收到第二聚类信息后,若检测到当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合不相同,则移动终端丢弃接收到第二聚类信息。
步骤306,获取第一聚类信息与第二聚类信息的对比结果,根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种。
移动终端在接收到服务器发送的第二聚类信息后,可将第一聚类信息与第二聚类信息进行对比。将第一聚类信息与第二聚类信息进行对比包括:
(1)检测第一聚类信息和第二聚类信息中对同一图像识别的人脸是否相同。
(2)检测第一聚类信息和第二聚类信息中对同一图像的分组是否相同。
(3)检测第一聚类信息对应的人脸图像和第二聚类信息对应的人脸图像是否相同。
移动终端可根据对比结果选择更新第一聚类信息、第二聚类信息、第一聚类信息和第二聚类信息。
本申请实施例中图像处理方法,通过将移动终端对人脸图像的聚类信息与服务器对人脸图像的聚类信息进行对比,并根据对比结果来选择更新第一聚类信息或第二聚类信息,或同时更新第一聚类信息和第二聚类信息,使得移动终端对人脸图像的聚类信息和服务器对人脸图像的聚类信息能够同步。移动终端根据对比结果的不同选择更新不同的聚类信息,使得移动终端保存聚类信息的方式更加多样化和智能化。
在一个实施例中,第一聚类信息包括第一图像标识;第二聚类信息包括第二图像标识。步骤306中根据对比结果的类型更新第一聚类信息包括:
(1)获取第一图像标识集合和第二图像标识集合。
图像标识是用于唯一标识图像的字符串,可为数字、字母和符号等。上述第一图像标识是移动终端中第一人脸图像集合中人脸图像的图像标识。上述第二图像标识是服务器接收到的第二人脸图像集合中人脸图像的图像标识。移动终端可获取第一图像标识集合和第二图像标识集合,并将第一图像标识 集合与第二图像标识集合对比。
(2)当第一图像标识集合包含第二图像标识集合,且第一图像标识集合不等于第二图像标识集合,根据第二聚类信息对第一人脸图像集合重新聚类得到更新后第一聚类信息。
通过将第一图像标识集合与第二图像标识集合对比,可将第一人脸图像集合中人脸图像与第二人脸图像集合中人脸图像进行对比。若第一图像标识集合包含第二图像标识集合,且第一图像标识集合不等于第二图像标识集合,更新第一聚类信息。即当检测到第一人脸图像集合除包含第二人脸图像集合中所有人脸图像外,还包含其他人脸图像,移动终端可更新第一聚类信息。移动终端更新第一聚类信息包括:
移动终端获取第一聚类信息中对第二人脸图像集合的聚类信息,移动终端用服务器发送的第二聚类信息替换移动终端对第二人脸图像集合的聚类信息。移动终端将第一人脸图像集合中除第二人脸图像集合外的人脸图像作为第三人脸图像集合。移动终端提取第三人脸图像集合中人脸图像的人脸特征信息,移动终端可将第三人脸图像集合中人脸图像的人脸特征信息与第二人脸图像集合中人脸图像的人脸特征信息进行相似度匹配,当相似度超过第一阈值,则将第三人脸图像集合中人脸图像划分到第二人脸图像集合中人脸图像对应的分组。上述第一阈值可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。
本申请实施例中图像处理方法,移动终端接收到服务器下发的人脸图像的聚类信息后,可将服务器对人脸图像的聚类信息替换移动终端对同一人脸图像的聚类信息,并根据服务器对人脸图像的聚类结果对移动终端中其他人脸图像进行聚类。以服务器的聚类结果为标准,提高了数据的稳定性,也提高了对图像聚类的准确率。
在一个实施例中,第一聚类信息包括第一人脸标识;第二聚类信息包括第二人脸标识。步骤306中根据对比结果的类型更新第一聚类信息包括:获取同一图像的第一人脸标识和第二人脸标识,当第二人脸标识中人脸多于第 一人脸标识中人脸,用同一图像的第二聚类信息替换第一聚类信息。
人脸标识是用于唯一标识一张人脸的字符串,包括数字、字母和符号等。第一人脸标识是第一人脸集合中一张人脸图像包含的人脸标识的集合。第二人脸标识是服务器下发的第二聚类信息中一张人脸图像包含的人脸标识的集合。移动终端可获取同一图像的第一人脸标识和第二人脸标识,并将第一人脸标识与第二人脸标识对比。当第二人脸标识中人脸多于第一人脸标识中人脸,用同一图像的第二聚类信息替换第一聚类信息。即对同一张人脸图像服务器识别的人脸多于移动终端识别的人脸,以服务器识别的人脸为准,移动终端用服务器对这张图像的第二聚类信息替换移动终端对这张图像的第一聚类信息。
本申请实施例中图像处理方法,可检测服务器和移动终端对同一图像识别的人脸是否一致。若检测对同一图像服务器识别的人脸多于移动终端识别的人脸,则以服务器识别人脸为准,用服务器对这张图像的聚类信息替换移动终端对这张图像的聚类信息。因服务器处理图像数据量较大、识别的人脸图像更多,以服务器识别的人脸个数为准,提高了人脸识别的准确性。
在一个实施例中,步骤306中根据对比结果的类型更新第二聚类信息包括:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸带有用户分组标识,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
用户分组标识是用于标记用户手动分组信息的字符串,包括数字、字母和符号等。移动终端可获取同一图像的第一人脸标识和第二人脸标识,当检测到第一人脸标识中人脸多于第二人脸标识中人脸,可检测第一人脸标识中多出的人脸是否带有用户分组标识。即当移动终端检测到对同一张人脸图像移动终端识别的人脸多于服务器识别的人脸,检测移动终端识别的多出的人脸是否带有用户分组标识。检测第一人脸标识中多出的人脸是否带有用户分组标识:检测上述多出的人脸对应的图像是否带有用户分组标识,若图像带有用户分组标识,检测上述用户分组标识是否与多出的人脸对应。其中,上 述用户分组标识与多出的人脸对应包括:用户对多出的人脸对应的图像进行手动分组,且该分组是对多出的人脸进行聚类的分组。例如,移动终端识别图像1包含的人脸A、人脸B和人脸C,服务器识别图像1中包含的人脸A和人脸B,则移动终端识别的人脸中多出人脸C,移动终端检测用户是否对图像1手动分组,若用户对图像1手动分组,检测用户是否将图像1分到人脸C的分组,若用户将图像1分到人脸C的分组,则多出的人脸C带有用户分组标识。
当检测到第一人脸标识中多出的人脸带有用户分组标识,移动终端以用户操作为准,将同一图像的第一聚类信息上传服务器。服务器在接收到第一聚类信息,可用接收到第一聚类信息替换同一图像的第二聚类信息。
本申请实施例中图像处理方法,在检测到服务器和移动终端对同一图像识别人脸不一致,且移动终端识别的人脸多于服务器识别的人脸时,检测用户是否对移动终端多识别的人脸进行了手动分组。若用户对移动终端多十倍的人脸进行了手动分组,则保留用户的手动分组,将移动终端对图像的聚类信息上传服务器。服务器将移动终端对图像的聚类信息替换服务器对同一图像的聚类信息,保证了数据同步。上述方法中保留用户的手动分组提高了用户粘性。
在一个实施例中,步骤306中根据对比结果的类型更新第一聚类信息包括:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸不带有用户分组标识,用同一图像的第二聚类信息替换第一聚类信息。
移动终端获取同一图像的第一人脸标识和第二人脸标识后,若检测到第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸不带有用户分组标识,则用服务器对图像的聚类信息替换移动终端对同一图像的聚类信息。即对同一张人脸图像,移动终端识别的人脸多于服务器识别的人脸,且移动终端识别的多出的人脸不带有用户分组标识,则以服务器识别的人脸为准,用服务器对图像的聚类信息替换移动终端对同一图像的聚类 信息。
在一个实施例中,移动终端获取同一图像的第一人脸标识和第二人脸标识,当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸不带有用户分组标识时,移动终端可将移动终端识别的多出的人脸隐藏,并对上述同一图像重新聚类。即对同一张人脸图像,移动终端识别的人脸多于服务器识别的人脸,且移动终端识别的多出的人脸不带有用户分组标识,移动终端可将上述同一图像中多出的人脸状态改为隐藏,即移动终端不再提取上述多出人脸的人脸特征信息。移动终端重新对上述同一图像进行特征提取获取人脸特征信息,并将上述同一图像的人脸特征信息与已聚类图像的人脸特征信息进行相似度匹配,根据相似度结果对上述同一图像进行聚类。
本申请实施例中图像处理方法,在检测到服务器和移动终端对同一图像识别人脸不一致,且移动终端识别的人脸多于服务器识别的人脸时,检测用户是否对移动终端多识别的人脸进行了手动分组。若用户对移动终端多十倍的人脸没有进行手动分组,则以服务器识别的人脸为准。因服务器识别的人脸数据量较大、数据量稳定,以服务器识别的人脸为准提高对人脸图像识别的准确率。
在一个实施例中,步骤306中根据对比结果的类型更新第二聚类信息包括:当第二人脸标识中无人脸,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
移动终端在获取同一图像的第一人脸标识和第二人脸标识后,若检测到第一人脸标识中有人脸且第二人脸标识中无人脸,则以上述同一图像的第一人脸标识为准。即对同一张人脸图像,移动终端识别出人脸而服务器未识别出人脸,则保留移动终端对上述同一图像识别出的人脸。移动终端可将上述图像的第一聚类信息上传服务器,服务器根据接收到第一信息替换同一图像的第二聚类信息。
本申请实施例中图像处理方法,在检测到对同一图像的移动终端识别出 人脸,而服务器未识别出人脸时,保留移动终端对图像识别出人脸。避免在服务器故障,识别人脸错误时造成数据错误的情况。通过将移动终端和服务器对同一图像的识别人脸对比,提高了对图像人脸识别的准确率。
在一个实施例中,第一聚类信息包括第一分组标识;第二聚类信息包括第二分组标识。步骤306中根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种包括:
步骤402,获取同一图像的第一分组标识和第二分组标识,当第一分组标识与第二分组标识不相同时,获取第一分组标识对应的第一时刻和第二分组标识对应的第二时刻。
分组标识是用于标识人脸图像所在分组的字符串,包括数字、字母和符号等。第一分组标识是移动终端对图像的分组标识,第二分组标识是服务器对图像的分组标识。当移动终端获取到同一图像的第一分组标识和第二分组标识后,可将第一分组标识与第二分组标识进行对比。当第一分组标识与第二分组标识不相同时,可获取第一分组标识对应的第一时刻和第二分组标识对应的第二时刻。上述第一时刻表示移动终端中上述同一图像的图像信息上一次更新的时刻。上述第二时刻表示服务器中上述同一图像的图像信息上一次更新的时刻。
步骤404,当第一时刻晚于第二时刻,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
当第一时刻晚于第二时刻,表示在上述同一图像上传服务器后,移动终端中上述同一图像的图像信息有更新,则以移动终端的对上述同一图像的分组为准。移动终端将上述同一图像的第一聚类信息上传服务器,服务器根据接收到第一聚类信息替换同一图像的第二聚类信息。
步骤406,当第二时刻晚于第一时刻,用同一图像的第二聚类信息替换第一聚类信息。
当第二时刻晚于第一时刻,表示服务器中上述同一图像的图像信息较新。移动终端存储服务器对图像的聚类信息,即移动终端用上述同一图像的第二 聚类信息替换第一聚类信息。例如,属于同一账号的两个移动终端A和B都上传图像2到服务器,其中,移动终端A中图像2的图像信息更新时刻为2017年9月4日18:00,移动终端B中图像2的图像信息更新时刻为2017年9月3日17:00,则服务器存储移动终端上传的图像2,并将对图像2的聚类信息发送给移动终端A和移动终端B。移动终端B检测到移动终端B和服务器对图像2的分组标识不一致,且服务器下发的图像2对应的图像信息更新时刻晚于移动终端B中图像2对应的图像信息更新时刻,则移动终端B存储服务器对图像2的聚类信息。
本申请实施例中图像处理方法,在检测到移动终端和服务器对同一图像的分组不一致时,以图像信息更新时刻较晚的图像对应的分组为准。使得在图像信息更新后,多端能够及时根据更新图像信息后图像进行聚类,保证了数据处理的一致性,避免了多端数据不一致导致的数据紊乱。
在一个实施例中,步骤302中当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息包括:
步骤502,当检测到图像更新列表不为空,获取图像更新列表中人脸图像的第一人脸特征信息。
移动终端中存储有图像更新列表,当移动终端新增图像或图像信息更新时,移动终端会将新增图像和图像信息更新的图像标记在图像更新列表中。上述图像信息更新包括:图像中识别人脸变化,图像分组变化等。当移动终端检测到图像更新列表中有图像时,可根据特征识别模型获取图像更新列表中人脸图像的第一人脸特征信息。其中,当图像中识别人脸增加时,在获取第一人脸特征信息时会对应添加增加人脸的人脸特征信息。当图像中识别人脸减少时,在获取第一人脸特征信息时会对应删除减少人脸的人脸特征信息。
步骤504,将第一人脸特征信息与第二人脸特征信息进行相似度匹配,第二人脸特征信息是移动终端已聚类人脸图像的人脸特征信息。
步骤506,当相似度超过预设阈值,将第一人脸特征信息划分到第二人脸特征信息对应的分组。
移动终端可将第一人脸特征信息与移动终端已聚类人脸的人脸特征信息进行相似度匹配。当相似度超过预设阈值时,可将第一人脸特征信息划分到第二人脸特征信息对应的分组,上述预设阈值可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。
本申请实施例中图像处理方法,在移动终端中图像更新时,对更新的图像重新进行聚类,保证了在图像信息更新时,及时更新图像对应的聚类信息,保证了对图像处理的及时性。
在一个实施例中,上述图像处理方法还包括以下情况中至少一种:
(1)按照预设的时间间隔向服务器发送第二聚类请求。
(2)定时向服务器发送第二聚类请求。
(3)接收到服务器发送的触发请求,检测到移动终端当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合不相同,向服务器发送第二聚类请求。
移动终端可向服务器发送第二聚类请求,服务器可根据第二聚类请求对移动终端上传的第二人脸图像集合进行聚类。其中,移动终端可按照预设的时间间隔向服务器发送第二聚类请求,移动终端也可定时向服务器发送第二聚类请求。移动终端还可根据服务器发送的触发请求来向服务器发送第二聚类请求,当移动终端接收到服务器发送的触发请求后,可检测移动终端当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合是否相同。若不相同,表示移动终端中第二人脸图像集合中人脸图像变化,重新上传第二人脸图像集合,并向服务器发送第二聚类请求。
本申请实施例中图像处理方法,移动终端可在不同的条件下向服务器发送第二聚类请求,既保证了服务器对移动终端中图像进行聚类的实时性,又保证了移动终端仅在特定条件下向服务器发送第二聚类请求。定时发送和按照预设的时间间隔发送避免移动终端高频次的向服务器发送第二聚类,降低了移动终端的功耗。在充电状态下发送第二聚类请求,避免在移动终端电量较低时发送第二聚类请求增加移动终端功耗、造成移动终端电量损耗较快的 情况,提高了用户粘性。
在一个实施例中,上述图像处理方法还包括:
步骤602,当接收到服务器发送的人脸图像,检测移动终端中是否存储同一人脸图像。
服务器可将同一账号的多个移动终端上传的人脸图像合并,并将合并后人脸图像集合与各个移动终端上传的第二人脸图像集合分别对比。服务器可将合并后人脸图像集合中除第二人脸图像集合外的人脸图像分别发送给对应的移动终端。移动终端在接收到服务器发送的人脸图像后,可检测移动终端中是否有同一人脸图像。
步骤604,当移动终端没有存储同一人脸图像,存储服务器发送的人脸图像。
步骤606,当移动终端存储同一人脸图像,检测同一人脸图像的图像信息是否相同;当同一人脸图像的图像信息不相同时,存储图像操作时刻较晚的人脸图像。
若移动终端中没有服务器发送的人脸图像,则移动终端存储服务器发送的人脸图像。若移动终端有服务器发送的人脸图像,检测服务器发送的人脸图像的图像信息与移动终端中同一图像的图像信息是否相同。若不相同,则存储图像操作时刻较晚的人脸图像。即若移动终端中人脸图像的图像操作时刻较晚,则不保存服务器发送的人脸图像,移动终端还可将人脸图像上传服务器,使得服务器存储图像操作时刻较晚的人脸图像。若服务器发送的人脸图像的图像操作时刻较晚,则用服务器发送的人脸图像替换移动终端中同一人脸图像。
本申请实施例中图像处理方法,在多端中实现图像同步时,存储图像操作时间最晚的图像。在保证多端数据同步时,还保证了图像数据的及时更新,提高了数据的稳定性和实时性。
图7为另一个实施例中图像处理方法的流程图。如图7所示,一种图像处理方法,应用于服务器,包括:
步骤702,当接收到移动终端上传的第二聚类请求,对移动终端上传的第二人脸图像集合聚类得到第二聚类信息。
服务器可接收移动终端上传的第二人脸图像集合。上述第二人脸图像集合可为移动终端存储于内存中人脸图像的集合。服务器在接收到移动终端上传的第二人脸图像集合和第二聚类请求后,可对第二人脸图像集合聚类得到第二聚类信息。服务器对第二人脸图像集合聚类包括:服务器根据特征识别模型提取第二人脸图像集合中人脸图像的人脸特征信息。服务器再将第二人脸图像集合中人脸图像的人脸特征信息进行相似度匹配,将相似度超过第二阈值的人像特征信息划分到同一分组。上述第二阈值可为移动终端预设的值,也可为服务器预设的值,也可为用户手动输入的值。
步骤704,向移动终端发送第二聚类信息。
在对第二人脸图像集合中人脸特征信息聚类完毕后,服务器可将对第二人脸图像集合的聚类信息返还移动终端,即服务器可将第二聚类信息发送给移动终端。
步骤706,接收移动终端上传的更新后第二聚类信息,用更新后第二聚类信息替换第二聚类信息。
服务器还可接收移动终端上传的更新后第二聚类信息,服务器可查找更新后第二聚类信息对应的原有第二聚类信息,用更新后第二聚类信息替换原有第二聚类信息。
本申请实施例中图像处理方法,服务器可对移动终端上传的人脸图像进行聚类。服务器还可接收移动终端上传的更新后人脸图像的聚类信息,并用更新后人脸图像的聚类信息替换原有聚类信息。通过服务器对图像聚类,保证对人脸图像识别的准确率。对聚类信息进行更新,保证了多端数据的一致性,提高了数据的稳定性。
在一个实施例中,上述图像处理方法还包括:
(1)当接收到同一账号的多个移动终端上传的第二人脸图像集合,将多个移动终端上传的第二人脸图像集合合并。
(2)将合并后人脸图像集合分别与多个移动终端中每个移动终端上传的第二人脸图像集合进行对比,根据对比结果分别向多个移动终端中每个移动终端发送合并后人脸图像集合中人脸图像。
服务器可将同一账号的多个移动终端上传的第二人脸图像集合合并,并将合并后人脸图像集合与各个移动终端上传的第二人脸图像集合分别对比。服务器可将合并后人脸图像集合中除第二人脸图像集合外的人脸图像分别发送给对应的移动终端。
本申请实施例中图像处理方法,可实现同一账号的多个移动终端之间图像数据的同步,保证了多端数据的一致,提高了数据的稳定性。
在一个实施例中,上述图像处理方法还包括:接收同一账号的多个移动终端上传的第二人脸图像集合,当同一账号的多个移动终端上传的第二人脸图像集合中同一图像的图像信息不相同时,存储图像操作时刻最晚的同一图像。
服务器可接收同一账号的多个移动终端上传的第二人脸图像集合,并将同一账号的多个移动终端上传的第二人脸图像集合合并。若移动终端检测到同一账号的多个移动终端上传的同一图像的图像信息不相同时,服务器在多个同一图像中查找图像操作时刻最晚的一个并存储。
本申请实施例中,当服务器接收到同一账号的多个移动终端上传的同一图像时,若检测到多个移动终端上传的同一图像的图像信息不一致,则服务器存储图像操作时刻最晚的图像,保证了数据的实时性。
在一个实施例中,在步骤702当接收到移动终端上传的第二聚类请求之后,上述图像处理方法还包括:
(1)根据接收到第二聚类请求的顺序生成聚类请求队列。
(2)当检测到聚类请求队列中包括同一移动终端上传的多个第二聚类请求,将同一移动终端上传的多个第二聚类请求合并为一个第二聚类请求。
服务器可接收多个移动终端上传的第二聚类请求,并根据接收到第二聚类请求的顺序生成聚类请求队列。当服务器检测到在聚类请求队列中存在同 一移动终端上传的多个第二聚类请求,可将同一终端上传的多个聚类请求合并为一个第二聚类请求。
本申请实施例中图像处理方法,服务器将同一移动终端上传的多个第二聚类请求合并为一个第二聚类请求,避免了多个第二聚类请求多次触发图像聚类浪费服务器资源的情况,降低服务器功耗,提高了服务器的处理速度。
在一个实施例中,上述图像处理方法还包括:
步骤802,当检测到聚类请求队列中包括同一账号的多个移动终端上传的多个第二聚类请求,将同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求。
步骤804,获取同一账号的多个移动终端对应的第二人脸图像集合。
步骤806,对同一账号的多个移动终端对应的第二人脸图像集合聚类得到第二聚类信息。
步骤808,向同一账号的多个移动终端分别发送第二聚类信息。
服务器还可检测聚类请求队列中是否存在同一账号的多个移动终端上传的多个第二聚类请求,若存在,将同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求。服务器还可将同一账号的多个移动终端上传的第二人脸图像集合合并。当服务器接收到同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求后,可获取同一账号的多个移动终端上传的第二人脸图像集合合并形成的合并人脸图像集合,提取合并后人脸图像集合中人脸图像的人脸特征信息,对合并后人脸图像集合中人脸图像的人脸特征信息进行聚类得到第二聚类信息,将第二聚类信息发送给同一账号的多个移动终端中上传了第二聚类请求的移动终端。服务器也可将第二聚类信息分别发送给同一账号的多个移动终端中每个移动终端。
本申请实施例中图像处理方法,服务器可将同一账号的多个移动终端上传的第二聚类请求合并为一个,避免多个聚类请求多次触发服务器对人脸图像进行聚类,节省了服务器资源,提高了服务器中图像处理的速度。
上述各个实施例中图像处理方法的流程图中的各个步骤按照箭头的指示 依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,其可以以其他的顺序执行。而且,上述各个实时例中图像处理方法的流程图中至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,其执行顺序也不必然是依次进行,而是可以与其他步骤或者其他步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
图9为一个实施例中图像处理装置的结构框图。如图9所示,一种图像处理装置,运行于移动终端,包括:
第一聚类模块902,用于当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息。
接收模块904,用于接收服务器发送的第二聚类信息,第二聚类信息是服务器对移动终端上传的第二人脸图像集合的聚类信息。
获取模块906,用于获取第一聚类信息与第二聚类信息的对比结果。
更新模块908,用于根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种。
在一个实施例中,第一聚类信息包括第一图像标识;第二聚类信息包括第二图像标识。更新模块908还用于获取第一图像标识集合和第二图像标识集合;当第一图像标识集合包含第二图像标识集合,且第一图像标识集合不等于第二图像标识集合,根据第二聚类信息对第一人脸图像集合重新聚类得到更新后第一聚类信息。
在一个实施例中,第一聚类信息包括第一人脸标识;第二聚类信息包括第二人脸标识;更新模块908还用于获取同一图像的第一人脸标识和第二人脸标识,当第二人脸标识中人脸多于第一人脸标识中人脸,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,更新模块908还用于当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸带有用户分组标识,将同一 图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
在一个实施例中,更新模块908还用于当第二人脸标识中无人脸,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
在一个实施例中,第一聚类信息包括第一分组标识;第二聚类信息包括第二分组标识。更新模块908还用于获取同一图像的第一分组标识和第二分组标识,当第一分组标识与第二分组标识不相同时,获取第一分组标识对应的第一时刻和第二分组标识对应的第二时刻;当第一时刻晚于第二时刻,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息;当第二时刻晚于第一时刻,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,第一聚类模块902还用于当检测到图像更新列表不为空,获取图像更新列表中人脸图像的第一人脸特征信息;将第一人脸特征信息与第二人脸特征信息进行相似度匹配,第二人脸特征信息是移动终端已聚类人脸图像的人脸特征信息;当相似度超过预设阈值,将第一人脸特征信息划分到第二人脸特征信息对应的分组。
图10为另一个实施例中图像处理装置的结构框图。上述图像处理装置包括第一聚类模块1002、接收模块1004、获取模块1006、更新模块1008和第二发送模块1010。其中,第一聚类模块1002、接收模块1004、获取模块1006、更新模块1008与图9中对应的模块功能相同。
第二发送模块1010,用于按照预设的时间间隔向服务器发送第二聚类请求。
第二发送模块1010还用于定时向服务器发送第二聚类请求。
第二发送模块1010还用于接收到服务器发送的触发请求,检测到移动终端当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合不相同,向服务器发送第二聚类请求。
图11为另一个实施例中图像处理装置的结构框图。上述图像处理装置包括第一聚类模块1102、接收模块1104、获取模块1106、更新模块1108、检测模块1110和第一存储模块1112。其中,第一聚类模块1102、接收模块1104、获取模块1106、更新模块1108与图9中对应的模块功能相同。
检测模块1110,用于当接收到服务器发送的人脸图像,检测移动终端中是否存储同一人脸图像。
第一存储模块1112,用于当移动终端没有存储同一人脸图像,存储服务器发送的人脸图像。
第一存储模块1112还用于当移动终端存储同一人脸图像,检测同一人脸图像的图像信息是否相同;当同一人脸图像的图像信息不相同时,存储图像操作时刻较晚的人脸图像。
图12为另一个实施例中图像处理装置的结构框图。如图12所示,一种图像处理装置,运行于服务器,包括:
第二聚类模块1202,用于当接收到移动终端上传的第二聚类请求,对移动终端上传的第二人脸图像集合聚类得到第二聚类信息。
第一发送模块1204,用于向移动终端发送第二聚类信息。
接收模块1206,用于接收移动终端上传的更新后第二聚类信息。
替换模块1208,用于用更新后第二聚类信息替换第二聚类信息。
图13为另一个实施例中图像处理装置的结构框图。如图13所示,一种图像处理装置,包括第二聚类模块1302、第一发送模块1304、接收模块1306、替换模块1308、合并模块1310和对比模块1312。其中,第二聚类模块1302、第一发送模块1304、接收模块1306、替换模块1308与图12中对应的模块功能相同。
合并模块1310,用于当接收到同一账号的多个移动终端上传的第二人脸图像集合,将多个移动终端上传的第二人脸图像集合合并;
对比模块1312,用于将合并后人脸图像集合分别与多个移动终端中每个移动终端上传的第二人脸图像集合进行对比。
第一发送模块1304还用于根据对比结果分别向多个移动终端中每个移动终端发送合并后人脸图像集合中人脸图像。
在一个实施例中,合并模块1310还用于根据接收到第二聚类请求的顺序生成聚类请求队列;当检测到聚类请求队列中包括同一移动终端上传的多个第二聚类请求,将同一移动终端上传的多个第二聚类请求合并为一个第二聚类请求。
在一个实施例中,合并模块1310还用于当检测到聚类请求队列中包括同一账号的多个移动终端上传的多个第二聚类请求,将同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求。第二聚类模块1302还用于获取同一账号的多个移动终端对应的第二人脸图像集合;对同一账号的多个移动终端对应的第二人脸图像集合聚类得到第二聚类信息。第一发送模块1304还用于向同一账号的多个移动终端分别发送第二聚类信息。
图14为另一个实施例中图像处理装置的结构框图。如图14所示,一种图像处理装置,包括第二聚类模块1402、第一发送模块1404、接收模块1406、替换模块1408和存储模块1410。其中,第二聚类模块1402、第一发送模块1404、接收模块1406、替换模块1408与图12中对应的模块功能相同。
接收模块1406还用于接收同一账号的多个移动终端上传的第二人脸图像集合。
存储模块1410,用于当同一账号的多个移动终端上传的第二人脸图像集合中同一图像的图像信息不相同时,存储图像操作时刻最晚的同一图像。
上述图像处理装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。其中,网络接口可以是以太网卡或无线网卡等。上述各模块可以硬件形式内嵌于或独立于服务器中的处理器中,也可以以软件形式存储于服务器中的存储器中,以便于处理器调用执行以上各个模块对应的操作。
如在本申请中所使用的,术语“模块”旨在表示计算机相关的实体,它可以是硬件、硬件和软件的组合、软件、或者执行中的软件。例如,模块可以是但不限于是,在处理器上运行的进程、处理器、对象、可执行码、执行的线 程、程序和/或计算机。作为说明,运行在服务器上的应用程序和服务器都可以是模块。一个或多个模块可以驻留在进程和/或执行的线程中,并且模块可以位于一个计算机内和/或分布在两个或更多的计算机之间。
本申请实施例还提供了一种移动终端。如图14所示,为了便于说明,仅示出了与本申请实施例相关的部分,具体技术细节未揭示的,请参照本申请实施例方法部分。该移动终端可以为包括手机、平板电脑、PDA(Personal Digital Assistant,个人数字助理)、POS(Point of Sales,销售终端)、车载电脑、穿戴式设备等任意终端设备,以移动终端为手机为例:
图15为与本申请实施例提供的移动终端相关的手机的部分结构的框图。参考图15,手机包括:射频(Radio Frequency,RF)电路1510、存储器1520、输入单元1530、显示单元1540、传感器1550、音频电路1560、无线保真(wireless fidelity,WiFi)模块1570、处理器1580、以及电源1590等部件。本领域技术人员可以理解,图15所示的手机结构并不构成对手机的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
其中,RF电路1510可用于收发信息或通话过程中,信号的接收和发送,可将基站的下行信息接收后,给处理器1580处理;也可以将上行的数据发送给基站。通常,RF电路包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(LowNoiseAmplifier,LNA)、双工器等。此外,RF电路1510还可以通过无线通信与网络和其他设备通信。上述无线通信可以使用任一通信标准或协议,包括但不限于全球移动通讯系统(Global System of Mobile communication,GSM)、通用分组无线服务(General Packet Radio Service,GPRS)、码分多址(Code Division Multiple Access,CDMA)、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)、长期演进(Long Term Evolution,LTE))、电子邮件、短消息服务(Short Messaging Service,SMS)等。
存储器1520可用于存储软件程序以及模块,处理器1580通过运行存储在存储器1520的软件程序以及模块,从而执行手机的各种功能应用以及数据 处理。存储器1520可主要包括程序存储区和数据存储区,其中,程序存储区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能的应用程序、图像播放功能的应用程序等)等;数据存储区可存储根据手机的使用所创建的数据(比如音频数据、通讯录等)等。此外,存储器1520可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
输入单元1530可用于接收输入的数字或字符信息,以及产生与手机1500的用户设置以及功能控制有关的键信号输入。具体地,输入单元1530可包括触控面板1531以及其他输入设备1532。触控面板1531,也可称为触摸屏,可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板1531上或在触控面板1531附近的操作),并根据预先设定的程式驱动相应的连接装置。在一个实施例中,触控面板1531可包括触摸检测装置和触摸控制器两个部分。其中,触摸检测装置检测用户的触摸方位,并检测触摸操作带来的信号,将信号传送给触摸控制器;触摸控制器从触摸检测装置上接收触摸信息,并将它转换成触点坐标,再送给处理器1580,并能接收处理器1580发来的命令并加以执行。此外,可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板1531。除了触控面板1531,输入单元1530还可以包括其他输入设备1532。具体地,其他输入设备1532可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)等中的一种或多种。
显示单元1540可用于显示由用户输入的信息或提供给用户的信息以及手机的各种菜单。显示单元1540可包括显示面板1541。在一个实施例中,可以采用液晶显示器(Liquid Crystal Display,LCD)、有机发光二极管(Organic Light-Emitting Diode,OLED)等形式来配置显示面板1541。在一个实施例中,触控面板1531可覆盖显示面板1541,当触控面板1531检测到在其上或附近的触摸操作后,传送给处理器1580以确定触摸事件的类型,随后处理器1580根据触摸事件的类型在显示面板1541上提供相应的视觉输出。虽然在图15 中,触控面板1531与显示面板1541是作为两个独立的部件来实现手机的输入和输入功能,但是在某些实施例中,可以将触控面板1531与显示面板1541集成而实现手机的输入和输出功能。
手机1500还可包括至少一种传感器1550,比如光传感器、运动传感器以及其他传感器。具体地,光传感器可包括环境光传感器及接近传感器,其中,环境光传感器可根据环境光线的明暗来调节显示面板1541的亮度,接近传感器可在手机移动到耳边时,关闭显示面板1541和/或背光。运动传感器可包括加速度传感器,通过加速度传感器可检测各个方向上加速度的大小,静止时可检测出重力的大小及方向,可用于识别手机姿态的应用(比如横竖屏切换)、振动识别相关功能(比如计步器、敲击)等;此外,手机还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器等。
音频电路1560、扬声器1561和传声器1562可提供用户与手机之间的音频接口。音频电路1560可将接收到的音频数据转换后的电信号,传输到扬声器1561,由扬声器1561转换为声音信号输出;另一方面,传声器1562将收集的声音信号转换为电信号,由音频电路1560接收后转换为音频数据,再将音频数据输出处理器1580处理后,经RF电路1510可以发送给另一手机,或者将音频数据输出至存储器1520以便后续处理。
WiFi属于短距离无线传输技术,手机通过WiFi模块1570可以帮助用户收发电子邮件、浏览网和访问流式媒体等,它为用户提供了无线的宽带互联网访问。虽然图15示出了WiFi模块1570,但是可以理解的是,其并不属于手机1500的必须构成,可以根据需要而省略。
处理器1580是手机的控制中心,利用各种接口和线路连接整个手机的各个部分,通过运行或执行存储在存储器1520内的软件程序和/或模块,以及调用存储在存储器1520内的数据,执行手机的各种功能和处理数据,从而对手机进行整体监控。在一个实施例中,处理器1580可包括一个或多个处理单元。在一个实施例中,处理器1580可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等;调制解调处理 器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器1580中。
手机1500还包括给各个部件供电的电源1590(比如电池),优选的,电源可以通过电源管理系统与处理器1580逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。
在一个实施例中,手机1500还可以包括摄像头、蓝牙模块等。
在本申请实施例中,该移动终端所包括的处理器1580执行存储在存储器上的计算机程序时实现如上以下步骤:
(1)当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息。
(2)接收服务器发送的第二聚类信息,第二聚类信息是服务器对移动终端上传的第二人脸图像集合的聚类信息。
(3)获取第一聚类信息与第二聚类信息的对比结果,根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种。
在一个实施例中,第一聚类信息包括第一图像标识;第二聚类信息包括第二图像标识;处理器1580执行根据对比结果的类型更新第一聚类信息包括:获取第一图像标识集合和第二图像标识集合;当第一图像标识集合包含第二图像标识集合,且第一图像标识集合不等于第二图像标识集合,根据第二聚类信息对第一人脸图像集合重新聚类得到更新后第一聚类信息。
在一个实施例中,第一聚类信息包括第一人脸标识;第二聚类信息包括第二人脸标识;处理器1580执行根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种包括:获取同一图像的第一人脸标识和第二人脸标识,当第二人脸标识中人脸多于第一人脸标识中人脸,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,处理器1580还执行:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸带有用户分组标识,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚 类信息。
在一个实施例中,处理器1580还执行:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸不带有用户分组标识,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,处理器1580还执行:当第二人脸标识中无人脸,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
在一个实施例中,第一聚类信息包括第一分组标识;第二聚类信息包括第二分组标识;处理器1580执行根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种包括:获取同一图像的第一分组标识和第二分组标识,当第一分组标识与第二分组标识不相同时,获取第一分组标识对应的第一时刻和第二分组标识对应的第二时刻;当第一时刻晚于第二时刻,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息;当第二时刻晚于第一时刻,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,处理器1580执行当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息包括:当检测到图像更新列表不为空,获取图像更新列表中人脸图像的第一人脸特征信息;将第一人脸特征信息与第二人脸特征信息进行相似度匹配,第二人脸特征信息是移动终端已聚类人脸图像的人脸特征信息;当相似度超过预设阈值,将第一人脸特征信息划分到第二人脸特征信息对应的分组。
在一个实施例中,处理器1580还执行以下情况中至少一种:按照预设的时间间隔向服务器发送第二聚类请求;定时向服务器发送第二聚类请求;接收到服务器发送的触发请求,检测到移动终端当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合不相同,向服务器发送第二聚类请求。
在一个实施例中,处理器1580还执行:当接收到服务器发送的人脸图像, 检测移动终端中是否存储同一人脸图像;当移动终端没有存储同一人脸图像,存储服务器发送的人脸图像;当移动终端存储同一人脸图像,检测同一人脸图像的图像信息是否相同;当同一人脸图像的图像信息不相同时,存储图像操作时刻较晚的人脸图像。
图16为一个实施例中服务器的内部结构示意图。如图16所示,该服务器包括通过系统总线连接的处理器、非易失性存储介质、内存储器和网络接口。其中,该处理器用于提供计算和控制能力,支撑整个计算机设备的运行。存储器用于存储数据、程序等,存储器上存储至少一个计算机程序,该计算机程序可被处理器执行,以实现本申请实施例中提供的适用于计算机设备的无线网络通信方法。存储器可包括磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)等非易失性存储介质,或随机存储记忆体(Random-Access-Memory,RAM)等。例如,在一个实施例中,存储器包括非易失性存储介质及内存储器。非易失性存储介质存储有操作系统和计算机程序。该计算机程序可被处理器所执行,以用于实现以上各个实施例提供的一种图像处理方法。内存储器为非易失性存储介质中的操作系统计算机程序提供高速缓存的运行环境。网络接口可以是以太网卡或无线网卡等,用于与外部的计算机设备进行通信。服务器可以用独立的服务器或者是多个服务器组成的服务器集群来实现。本领域技术人员可以理解,图16中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的服务器的限定,具体的服务器可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
在一个实施例中,上述服务器中处理器执行计算机可读指令时,可实现以下步骤:
(1)当接收到移动终端上传的第二聚类请求,对移动终端上传的第二人脸图像集合聚类得到第二聚类信息。
(2)向移动终端发送第二聚类信息。
(3)接收移动终端上传的更新后第二聚类信息,用更新后第二聚类信息 替换第二聚类信息。
在一个实施例中,处理器还执行:当接收到同一账号的多个移动终端上传的第二人脸图像集合,将多个移动终端上传的第二人脸图像集合合并;将合并后人脸图像集合分别与多个移动终端中每个移动终端上传的第二人脸图像集合进行对比,根据对比结果分别向多个移动终端中每个移动终端发送合并后人脸图像集合中人脸图像。
在一个实施例中,处理器还执行:接收同一账号的多个移动终端上传的第二人脸图像集合,当同一账号的多个移动终端上传的第二人脸图像集合中同一图像的图像信息不相同时,存储图像操作时刻最晚的同一图像。
在一个实施例中,在当接收到移动终端上传的第二聚类请求之后,处理器还执行:根据接收到第二聚类请求的顺序生成聚类请求队列;当检测到聚类请求队列中包括同一移动终端上传的多个第二聚类请求,将同一移动终端上传的多个第二聚类请求合并为一个第二聚类请求。
在一个实施例中,处理器还执行:当检测到聚类请求队列中包括同一账号的多个移动终端上传的多个第二聚类请求,将同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求;获取同一账号的多个移动终端对应的第二人脸图像集合;对同一账号的多个移动终端对应的第二人脸图像集合聚类得到第二聚类信息;向同一账号的多个移动终端分别发送第二聚类信息。
本申请实施例还提供了一种计算机可读存储介质。一个或多个包含计算机可执行指令的非易失性计算机可读存储介质,当计算机可执行指令被一个或多个处理器执行时,使得处理器执行以下步骤:
(1)当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息。
(2)接收服务器发送的第二聚类信息,第二聚类信息是服务器对移动终端上传的第二人脸图像集合的聚类信息。
(3)获取第一聚类信息与第二聚类信息的对比结果,根据对比结果的类 型更新第一聚类信息和第二聚类信息中至少一种。
在一个实施例中,第一聚类信息包括第一图像标识;第二聚类信息包括第二图像标识;根据对比结果的类型更新第一聚类信息包括:获取第一图像标识集合和第二图像标识集合;当第一图像标识集合包含第二图像标识集合,且第一图像标识集合不等于第二图像标识集合,根据第二聚类信息对第一人脸图像集合重新聚类得到更新后第一聚类信息。
在一个实施例中,第一聚类信息包括第一人脸标识;第二聚类信息包括第二人脸标识;根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种包括:获取同一图像的第一人脸标识和第二人脸标识,当第二人脸标识中人脸多于第一人脸标识中人脸,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸带有用户分组标识,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当第一人脸标识中人脸多于第二人脸标识中人脸,且第一人脸标识中多出的人脸不带有用户分组标识,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当第二人脸标识中无人脸,将同一图像的第一聚类信息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息。
在一个实施例中,第一聚类信息包括第一分组标识;第二聚类信息包括第二分组标识;根据对比结果的类型更新第一聚类信息和第二聚类信息中至少一种包括:获取同一图像的第一分组标识和第二分组标识,当第一分组标识与第二分组标识不相同时,获取第一分组标识对应的第一时刻和第二分组标识对应的第二时刻;当第一时刻晚于第二时刻,将同一图像的第一聚类信 息上传服务器,第一聚类信息用以替换同一图像的第二聚类信息;当第二时刻晚于第一时刻,用同一图像的第二聚类信息替换第一聚类信息。
在一个实施例中,当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息包括:当检测到图像更新列表不为空,获取图像更新列表中人脸图像的第一人脸特征信息;将第一人脸特征信息与第二人脸特征信息进行相似度匹配,第二人脸特征信息是移动终端已聚类人脸图像的人脸特征信息;当相似度超过预设阈值,将第一人脸特征信息划分到第二人脸特征信息对应的分组。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:按照预设的时间间隔向服务器发送第二聚类请求;定时向服务器发送第二聚类请求;接收到服务器发送的触发请求,检测到移动终端当前第二人脸图像集合与移动终端上一次上传服务器的第二人脸图像集合不相同,向服务器发送第二聚类请求。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当接收到服务器发送的人脸图像,检测移动终端中是否存储同一人脸图像;当移动终端没有存储同一人脸图像,存储服务器发送的人脸图像;当移动终端存储同一人脸图像,检测同一人脸图像的图像信息是否相同;当同一人脸图像的图像信息不相同时,存储图像操作时刻较晚的人脸图像。
本申请实施例还提供了一种计算机可读存储介质。一个或多个包含计算机可执行指令的非易失性计算机可读存储介质,当计算机可执行指令被一个或多个处理器执行时,使得处理器执行以下步骤:
(1)当接收到移动终端上传的第二聚类请求,对移动终端上传的第二人脸图像集合聚类得到第二聚类信息。
(2)向移动终端发送第二聚类信息。
(3)接收移动终端上传的更新后第二聚类信息,用更新后第二聚类信息替换第二聚类信息。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当接收到同一账号的多个移动终端上传的第二人脸图像集合,将多个移动终端上传的第二人脸图像集合合并;将合并后人脸图像集合分别与多个移动终端中每个移动终端上传的第二人脸图像集合进行对比,根据对比结果分别向多个移动终端中每个移动终端发送合并后人脸图像集合中人脸图像。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:接收同一账号的多个移动终端上传的第二人脸图像集合,当同一账号的多个移动终端上传的第二人脸图像集合中同一图像的图像信息不相同时,存储图像操作时刻最晚的同一图像。
在一个实施例中,在当接收到移动终端上传的第二聚类请求之后,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:根据接收到第二聚类请求的顺序生成聚类请求队列;当检测到聚类请求队列中包括同一移动终端上传的多个第二聚类请求,将同一移动终端上传的多个第二聚类请求合并为一个第二聚类请求。
在一个实施例中,当计算机可执行指令被一个或多个处理器执行时,使得处理器还执行:当检测到聚类请求队列中包括同一账号的多个移动终端上传的多个第二聚类请求,将同一账号的多个移动终端上传的多个第二聚类请求合并为一个第二聚类请求;获取同一账号的多个移动终端对应的第二人脸图像集合;对同一账号的多个移动终端对应的第二人脸图像集合聚类得到第二聚类信息;向同一账号的多个移动终端分别发送第二聚类信息。
本申请所使用的对存储器、存储、数据库或其它介质的任何引用可包括非易失性和/或易失性存储器。合适的非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM),它用作外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双 数据率SDRAM(DDR SDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)。
以上所述实施例仅表达了本申请的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对本申请专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本申请构思的前提下,还可以做出若干变形和改进,这些都属于本申请的保护范围。因此,本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种图像处理方法,包括:
    当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息;
    接收服务器发送的第二聚类信息,所述第二聚类信息是所述服务器对所述移动终端上传的第二人脸图像集合的聚类信息;
    获取所述第一聚类信息与所述第二聚类信息的对比结果,根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种。
  2. 根据权利要求1所述的方法,其特征在于:
    所述第一聚类信息包括第一图像标识;所述第二聚类信息包括第二图像标识;
    所述根据所述对比结果的类型更新所述第一聚类信息包括:
    获取第一图像标识集合和第二图像标识集合;
    当所述第一图像标识集合包含所述第二图像标识集合,且所述第一图像标识集合不等于所述第二图像标识集合,根据所述第二聚类信息对所述第一人脸图像集合重新聚类得到更新后第一聚类信息。
  3. 根据权利要求1或2所述的方法,其特征在于:
    所述第一聚类信息包括第一人脸标识;所述第二聚类信息包括第二人脸标识;
    所述根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种包括:
    获取同一图像的所述第一人脸标识和所述第二人脸标识,当所述第二人脸标识中人脸多于所述第一人脸标识中人脸,用所述同一图像的所述第二聚类信息替换所述第一聚类信息。
  4. 根据权利要求3所述的方法,其特征在于,所述方法还包括:
    当所述第一人脸标识中人脸多于所述第二人脸标识中人脸,且所述第一人脸标识中多出的人脸带有用户分组标识,将所述同一图像的所述第一聚类 信息上传所述服务器,所述第一聚类信息用以替换所述同一图像的第二聚类信息。
  5. 根据权利要求3所述的方法,其特征在于,所述方法还包括:
    当所述第一人脸标识中人脸多于所述第二人脸标识中人脸,且所述第一人脸标识中多出的人脸不带有用户分组标识,用所述同一图像的所述第二聚类信息替换所述第一聚类信息。
  6. 根据权利要求3中所述的方法,其特征在于,所述方法还包括:
    当所述第二人脸标识中无人脸,将所述同一图像的第一聚类信息上传所述服务器,所述第一聚类信息用以替换所述同一图像的第二聚类信息。
  7. 根据权利要求1至6中任一项所述的方法,其特征在于:
    所述第一聚类信息包括第一分组标识;所述第二聚类信息包括第二分组标识;
    所述根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种包括:
    获取同一图像的所述第一分组标识和所述第二分组标识,当所述第一分组标识与所述第二分组标识不相同时,获取所述第一分组标识对应的第一时刻和所述第二分组标识对应的第二时刻;
    当所述第一时刻晚于所述第二时刻,将所述同一图像的所述第一聚类信息上传所述服务器,所述第一聚类信息用以替换所述同一图像的所述第二聚类信息;
    当所述第二时刻晚于所述第一时刻,用所述同一图像的所述第二聚类信息替换所述第一聚类信息。
  8. 根据权利要求1至7中任一项所述的方法,其特征在于:
    所述当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息包括:
    当检测到图像更新列表不为空,获取所述图像更新列表中人脸图像的第一人脸特征信息;
    将第一人脸特征信息与第二人脸特征信息进行相似度匹配,所述第二人脸特征信息是所述移动终端已聚类人脸图像的人脸特征信息;
    当相似度超过预设阈值,将所述第一人脸特征信息划分到所述第二人脸特征信息对应的分组。
  9. 根据权利要求1至8中任一项所述的方法,其特征在于,所述方法还包括以下情况中至少一种:
    按照预设的时间间隔向所述服务器发送第二聚类请求;
    定时向所述服务器发送所述第二聚类请求;
    接收到所述服务器发送的触发请求,检测到所述移动终端当前第二人脸图像集合与所述移动终端上一次上传所述服务器的第二人脸图像集合不相同,向所述服务器发送所述第二聚类请求。
  10. 根据权利要求1至9中任一项所述的方法,其特征在于,所述方法还包括:
    当接收到所述服务器发送的人脸图像,检测所述移动终端中是否存储同一人脸图像;
    当所述移动终端没有存储所述同一人脸图像,存储所述服务器发送的人脸图像;
    当所述移动终端存储所述同一人脸图像,检测所述同一人脸图像的图像信息是否相同;当所述同一人脸图像的图像信息不相同时,存储图像操作时刻较晚的人脸图像。
  11. 一种图像处理方法,包括:
    当接收到移动终端上传的第二聚类请求,对所述移动终端上传的第二人脸图像集合聚类得到第二聚类信息;
    向所述移动终端发送所述第二聚类信息;
    接收所述移动终端上传的更新后第二聚类信息,用所述更新后第二聚类信息替换所述第二聚类信息。
  12. 根据权利要求11所述的方法,其特征在于,所述方法还包括:
    当接收到同一账号的多个移动终端上传的所述第二人脸图像集合,将所述多个移动终端上传的所述第二人脸图像集合合并;
    将合并后人脸图像集合分别与所述多个移动终端中每个移动终端上传的所述第二人脸图像集合进行对比,根据对比结果分别向所述多个移动终端中每个移动终端发送所述合并后人脸图像集合中人脸图像。
  13. 根据权利要求11或12所述的方法,其特征在于,所述方法包括:
    接收同一账号的多个移动终端上传的所述第二人脸图像集合,当所述同一账号的多个移动终端上传的所述第二人脸图像集合中同一图像的图像信息不相同时,存储图像操作时刻最晚的所述同一图像。
  14. 根据权利要求11至13中任一项所述的方法,其特征在于,在所述当接收到移动终端上传的第二聚类请求之后,所述方法还包括:
    根据接收到所述第二聚类请求的顺序生成聚类请求队列;
    当检测到所述聚类请求队列中包括同一移动终端上传的多个所述第二聚类请求,将所述同一移动终端上传的多个所述第二聚类请求合并为一个所述第二聚类请求。
  15. 根据权利要求14所述的方法,其特征在于,所述方法还包括:
    当检测到所述聚类请求队列中包括同一账号的多个移动终端上传的多个所述第二聚类请求,将所述同一账号的多个移动终端上传的多个所述第二聚类请求合并为一个所述第二聚类请求;
    获取所述同一账号的多个移动终端对应的第二人脸图像集合;
    对所述同一账号的多个移动终端对应的第二人脸图像集合聚类得到所述第二聚类信息;
    向所述同一账号的多个移动终端分别发送所述第二聚类信息。
  16. 一种图像处理装置,应用于移动终端,包括:
    第一聚类模块,用于当接收到第一聚类请求,移动终端对第一人脸图像集合聚类得到第一聚类信息;
    接收模块,用于接收服务器发送的第二聚类信息,所述第二聚类信息是 所述服务器对所述移动终端上传的第二人脸图像集合的聚类信息;
    获取模块,用于获取所述第一聚类信息与所述第二聚类信息的对比结果;
    更新模块,用于根据所述对比结果的类型更新所述第一聚类信息和所述第二聚类信息中至少一种。
  17. 一种图像处理装置,应用于服务器,包括:
    第二聚类模块,用于当接收到移动终端上传的第二聚类请求,对所述移动终端上传的第二人脸图像集合聚类得到第二聚类信息;
    第一发送模块,用于向所述移动终端发送所述第二聚类信息;
    接收模块,用于接收所述移动终端上传的更新后第二聚类信息;
    替换模块,用于用所述更新后第二聚类信息替换所述第二聚类信息。
  18. 一种移动终端,包括存储器及处理器,所述存储器中储存有计算机可读指令,所述指令被所述处理器执行时,使得所述处理器执行如权利要求1至10中任一项所述的图像处理方法。
  19. 一种服务器,包括存储器及处理器,所述存储器中储存有计算机可读指令,所述指令被所述处理器执行时,使得所述处理器执行如权利要求11至15中任一项所述的图像处理方法。
  20. 一个或多个包含计算机可读指令的非易失性计算机可读存储介质,当所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行如权利要求1至15中任一项所述的图像处理方法。
PCT/CN2017/101942 2017-09-15 2017-09-15 图像处理方法、装置、移动终端、服务器和存储介质 WO2019051799A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/101942 WO2019051799A1 (zh) 2017-09-15 2017-09-15 图像处理方法、装置、移动终端、服务器和存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/101942 WO2019051799A1 (zh) 2017-09-15 2017-09-15 图像处理方法、装置、移动终端、服务器和存储介质

Publications (1)

Publication Number Publication Date
WO2019051799A1 true WO2019051799A1 (zh) 2019-03-21

Family

ID=65723452

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/101942 WO2019051799A1 (zh) 2017-09-15 2017-09-15 图像处理方法、装置、移动终端、服务器和存储介质

Country Status (1)

Country Link
WO (1) WO2019051799A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110891032A (zh) * 2019-11-27 2020-03-17 佛山市蠢材科技有限公司 一种人脸数据并行下发方法、装置及电子设备
CN111738185A (zh) * 2020-06-28 2020-10-02 杭州海康威视数字技术股份有限公司 一种目标识别方法、装置及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110123071A1 (en) * 2005-09-28 2011-05-26 Facedouble, Inc. Method And System For Attaching A Metatag To A Digital Image
CN102118510A (zh) * 2011-03-17 2011-07-06 宇龙计算机通信科技(深圳)有限公司 联系人关联方法、服务器和移动终端
CN104820675A (zh) * 2015-04-08 2015-08-05 小米科技有限责任公司 相册显示方法及装置
CN105095902A (zh) * 2014-05-23 2015-11-25 华为技术有限公司 图片特征提取方法及装置
CN106464927A (zh) * 2014-06-17 2017-02-22 高通股份有限公司 接入节点上的媒体处理服务

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110123071A1 (en) * 2005-09-28 2011-05-26 Facedouble, Inc. Method And System For Attaching A Metatag To A Digital Image
CN102118510A (zh) * 2011-03-17 2011-07-06 宇龙计算机通信科技(深圳)有限公司 联系人关联方法、服务器和移动终端
CN105095902A (zh) * 2014-05-23 2015-11-25 华为技术有限公司 图片特征提取方法及装置
CN106464927A (zh) * 2014-06-17 2017-02-22 高通股份有限公司 接入节点上的媒体处理服务
CN104820675A (zh) * 2015-04-08 2015-08-05 小米科技有限责任公司 相册显示方法及装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110891032A (zh) * 2019-11-27 2020-03-17 佛山市蠢材科技有限公司 一种人脸数据并行下发方法、装置及电子设备
CN110891032B (zh) * 2019-11-27 2023-06-30 佛山市蠢材科技有限公司 一种人脸数据并行下发方法、装置及电子设备
CN111738185A (zh) * 2020-06-28 2020-10-02 杭州海康威视数字技术股份有限公司 一种目标识别方法、装置及设备
CN111738185B (zh) * 2020-06-28 2023-09-05 杭州海康威视数字技术股份有限公司 一种目标识别方法、装置及设备

Similar Documents

Publication Publication Date Title
CN107679559B (zh) 图像处理方法、装置、计算机可读存储介质和移动终端
CN107729815B (zh) 图像处理方法、装置、移动终端及计算机可读存储介质
US11290447B2 (en) Face verification method and device
CN108022274B (zh) 图像处理方法、装置、计算机设备和计算机可读存储介质
CN107679560B (zh) 数据传输方法、装置、移动终端及计算机可读存储介质
WO2019051795A1 (zh) 图像处理方法、装置、终端、服务器和计算机可读存储介质
US10824901B2 (en) Image processing of face sets utilizing an image recognition method
WO2018161540A1 (zh) 指纹注册方法及相关产品
WO2019052355A1 (zh) 图像处理方法和计算机设备、计算机可读存储介质
WO2019042049A1 (zh) 图片处理方法及移动终端
CN107679561A (zh) 图像处理方法和装置、系统、计算机设备
WO2019056938A1 (zh) 图像处理方法和计算机设备、计算机可读存储介质
WO2019051797A1 (zh) 图像处理方法和装置、计算机设备、计算机可读存储介质
WO2019011108A1 (zh) 虹膜识别方法及相关产品
WO2019052436A1 (zh) 图像处理方法、计算机可读存储介质和移动终端
US10970522B2 (en) Data processing method, electronic device, and computer-readable storage medium
WO2019109887A1 (zh) 图像处理的方法、电子设备、计算机可读存储介质
WO2019051799A1 (zh) 图像处理方法、装置、移动终端、服务器和存储介质
WO2020061731A1 (zh) 资源处理方法、电子设备和计算机可读存储介质
CN107632985B (zh) 网页预加载方法及装置
CN108513005B (zh) 联系人信息处理方法和装置、电子设备、存储介质
CN108021669B (zh) 图像分类方法和装置、电子设备、计算机可读存储介质
WO2019051801A1 (zh) 图像处理方法、装置、计算机设备及非易失性可读存储介质
CN111027406B (zh) 图片识别方法、装置、存储介质及电子设备
WO2019096207A1 (zh) 图像处理方法和计算机设备、计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17924874

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17924874

Country of ref document: EP

Kind code of ref document: A1