WO2015192575A1 - 一种基于通讯录的照片匹配方法及终端 - Google Patents

一种基于通讯录的照片匹配方法及终端 Download PDF

Info

Publication number
WO2015192575A1
WO2015192575A1 PCT/CN2014/089364 CN2014089364W WO2015192575A1 WO 2015192575 A1 WO2015192575 A1 WO 2015192575A1 CN 2014089364 W CN2014089364 W CN 2014089364W WO 2015192575 A1 WO2015192575 A1 WO 2015192575A1
Authority
WO
WIPO (PCT)
Prior art keywords
photo
contact
portrait recognition
portrait
data
Prior art date
Application number
PCT/CN2014/089364
Other languages
English (en)
French (fr)
Inventor
乔辉
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to RU2017101584A priority Critical patent/RU2667802C2/ru
Priority to AU2014397825A priority patent/AU2014397825A1/en
Priority to EP14895018.1A priority patent/EP3159808A4/en
Priority to US15/319,988 priority patent/US20170139911A1/en
Publication of WO2015192575A1 publication Critical patent/WO2015192575A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23Updating
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172Classification, e.g. identification

Definitions

  • the present invention relates to the field of photo query applications, and in particular, to a photo matching method and terminal based on an address book.
  • Existing photos are generally stored in different folders according to different time.
  • the terminal automatically creates folders named January, February, and so on, and stores the photos in the corresponding files according to the shooting time of the photos.
  • the user can view the photo according to the shooting time, but there are also some problems. For example, if the user needs to view a photo of a contact at different times, he or she needs to scroll through multiple folders, and after viewing most of the photos, In order to see all the photos you want to see, the operation is complicated and wastes time. When the number of photos that users need to view is too much, this kind of search technology will greatly reduce the user experience.
  • the embodiment of the invention provides a photo matching method and a terminal based on an address book, so as to at least solve the problem of complicated operation when the existing photo is queried.
  • the present invention provides a photo matching method based on an address book.
  • the method includes: selecting or creating a new contact and establishing a photo index table for the contact; obtaining a portrait recognition parameter of the contact; sequentially from the photo database Selecting a photo, extracting all the human face image recognition data in the selected photo, and matching the portrait recognition parameter with all the human face image recognition data in the selected photo one by one, if any of the human face image identification data is successfully matched, the selected image data is selected.
  • the photo information of the photo is added to the photo index table.
  • the step of acquiring the portrait recognition parameter of the contact in the above embodiment includes: setting a threshold value of the portrait recognition data, selecting a photo according to the user operation, and extracting all the human face image recognition data in the selected photo of the user, when the number of the extracted face recognition data is less than When the portrait recognition data quantity threshold value, a portrait recognition data is selected as the portrait recognition parameter according to the user operation; or the portrait recognition data transmitted by the other terminal is received, and the received portrait recognition data is taken as the portrait recognition parameter.
  • the above embodiment further includes: when a new photo is added to the photo database, extracting all the human face image recognition data in the new photo; and matching the portrait recognition parameter of each contact with all the human face image recognition data in the new photo; If any of the human portrait recognition data in the new photo has a matching portrait recognition parameter, it is determined that all the successfully matched portrait recognition parameters are in the photo index table of the contact corresponding to each successfully matched portrait recognition parameter. Add photo information for new photos.
  • the above embodiment further includes: if all the portrait recognition data in the new photo does not match the successful portrait recognition parameter, prompting to create a new contact; establishing a photo index table for the newly created contact, and selecting all the portrait recognition in the new photo according to the user operation
  • One of the data is a portrait recognition parameter of the newly created contact; sequentially selecting a photo from the photo database, extracting all the human face image recognition data in the selected photo; matching the portrait recognition parameter of the newly created contact with all the portrait recognition data one by one, if all the portraits If any of the identification data in the identification data is successfully matched, the photo information of the selected photo is added to the photo index table of the newly created contact.
  • the foregoing embodiment further includes: setting a reminder quantity threshold; determining whether the data quantity of all the human figure identification data in the new photo is greater than the reminder quantity threshold; if less than, prompting to create a new contact.
  • the above embodiment further includes: adding contact information of the contact in the selected photo.
  • the above embodiment further includes: when the photo in the photo database is deleted or moved, updating the photo information after the photo is deleted or moved according to the contact information of the deleted or moved photo to the photo index table of the corresponding contact. .
  • the step of obtaining the portrait recognition data from the photograph in the above embodiment includes performing face recognition processing on the photograph, extracting facial feature data on the recognized portion of the corresponding human face, and using the facial feature data as the portrait recognition data.
  • the present invention also provides a terminal.
  • the terminal includes: a photo index table establishing module configured to select or create a new contact and establish a photo index table for the contact; a portrait recognition parameter acquisition module configured to acquire a portrait recognition parameter of the contact; and, configured to sequentially select a photo from the photo database, extract all the human face image recognition data in the selected photo, and match the portrait recognition parameter and all the portrait recognition data one by one If any of the person image recognition data is successfully matched with the identification data, the photo information of the selected photo is added to the photo processing matching module of the photo index table.
  • the terminal acquires the portrait recognition parameter of a contact according to the user operation and establishes a photo index table for the contact, which is equivalent to establishing a relationship between the portrait recognition parameter and a photo index table, and then utilizing
  • the contact identification parameter of the contact person identifies the figure identification data of each photo in the photo database Match one by one, and add photo information (such as storage location, name, etc.
  • the photo index table can be quickly queried to all the photos related to the contact, and the operation is simple, and the operation of the existing query photo is complicated. The problem has enhanced the user experience.
  • FIG. 1 is a flowchart of a photo matching method according to a first embodiment of the present invention
  • FIG. 2 is a schematic diagram of functional modules of a terminal according to a second embodiment of the present invention.
  • FIG. 3 is a schematic diagram of functional modules of a terminal according to a third embodiment of the present invention.
  • FIG. 4 is a flowchart of a photo matching method according to a fourth embodiment of the present invention.
  • the core idea of the embodiment of the present invention is to establish a relationship between a contact recognition parameter of a contact and a photo index table thereof, and use some identification technology (such as facial recognition technology) to match the photo database in the terminal, and the photo containing the same portrait recognition parameter is included.
  • Some identification technology such as facial recognition technology
  • These photos are photos including the same contact
  • FIG. 1 is a flowchart of a photo matching method according to a first embodiment of the present invention. As shown in FIG. 1 , in the embodiment, the photo album-based photo matching method provided by the present invention includes the following steps:
  • the terminal selects or newly creates one or more contacts according to the user operation, and establishes a corresponding photo index table for each contact, and the photo index table is used to index the photos related to the contact;
  • the portrait recognition parameter is to process the photo selected by the user for each contact, and obtain the portrait recognition parameter of the contact.
  • the portrait recognition parameter includes all parameters for different characters, such as facial features, relative positions of the two pupils and the tip of the nose. , pupil color, head and shoulder width ratio can be used to identify the character's characteristic parameters;
  • the method for obtaining the portrait recognition parameter of the contact is obtained by the terminal processing the photo selected by the user, specifically:
  • the portrait recognition parameter specifically, the threshold value of the number of portrait recognition data is set to three, and all the portrait recognition data provided by the terminal refers to all the portrait identification data that are extracted after satisfying the recognition condition, such as a contact selected by the user.
  • the main character is one, and there may be many pedestrians in the street as the background of the photo, and in order to follow the matching of the portrait recognition parameters, there are certain recognition conditions for the portrait recognition parameters (the face must be clearly visible, etc.) Therefore, the data of the portrait recognition data actually extracted by the terminal is only one, so that the extracted portrait recognition data can be used as the portrait recognition parameter of the contact, and correspondingly, if two personal image recognition data is extracted, According to the user operation, select the user-specified portrait Data as a parameter of the contact face recognition;
  • the way to obtain the portrait recognition parameter of the contact is obtained by the terminal from other devices according to the user operation, such as:
  • the user/terminal can communicate with other users/terminals to obtain the portrait identification data of the contact in the other user/terminal, and use it as the portrait recognition parameter of the contact;
  • S103 sequentially select a photo from the photo database, extract all the human face image recognition data in the selected photo, and match the portrait recognition parameter with all the human face image recognition data in the selected photo one by one, if any human image recognition data has any human face image recognition data and If the matching is successful, the photo information of the selected photo is added to the photo index table;
  • the terminal sequentially selects photos from the photo database, and performs processing for each selected photo by extracting all the portrait device data in the selected photo.
  • the portrait recognition data is one
  • the terminal is associated with a contact.
  • the portrait recognition parameter is matched. If the matching is successful, the photo is considered to be a photo of the contact.
  • the portrait recognition data is 2 or more, it is respectively matched with the portrait recognition parameter of a contact, as long as the If a portrait identification data is successfully matched, the photo is considered to be a photo of the contact.
  • the photo information (such as name, placement/storage location, etc.) of the photo can be found by the terminal.
  • the information to the photo can be added to the photo index table of the corresponding contact;
  • the matching threshold when the portrait recognition data in a photo is matched with the portrait recognition parameter of a contact, the matching threshold may be set according to the resolution of the photo (if the photo resolution is high, the matching threshold is set to 95%). When the photo resolution is low, the matching threshold is set to 85%), so that as long as the matching degree/similarity of the portrait recognition data and the portrait recognition parameter is greater than the matching threshold, it is considered that the portrait recognition data and the portrait recognition parameter are successfully matched; In some embodiments, it may also be considered that the portrait recognition data and the portrait recognition parameter are successfully matched only when the portrait recognition data and the portrait recognition parameter are completely matched/identical;
  • the photo information of the photo is taken. Added to the photo index table of the contact corresponding to all the matching portrait recognition parameters
  • This embodiment provides a method for searching for a photo of a photo database in a terminal, which is convenient for the user to query the photo information of all the photos of the contact according to the photo index table when the user needs to view the photo of the contact.
  • the placement/storage location finds/downloads a photo of the corresponding name and presents it to the user.
  • the photo matching method shown in FIG. 1 further includes:
  • any of the human portrait recognition data in the new photo has a matching portrait recognition parameter, it is determined that all the successfully matched portrait recognition parameters are in the photo index table of the contact corresponding to each successfully matched portrait recognition parameter. Add photo information for new photos;
  • This embodiment gives a specific scheme for how to process a new photo. If the new photo cannot extract valid portrait recognition data, the new photo is considered to be a landscape photo/invalid photo, etc., and is not processed when a valid portrait is extracted. When identifying the data (one or more), it is matched with the portrait recognition parameters of each contact one by one, so that all the portrait identification data in the new photo can be matched separately, and the new photo is avoided. Some photos of the contacts are added to the photo index table of some of the contacts.
  • the photo matching method according to the above embodiment further includes:
  • the new contact is prompted; if all the portrait recognition data in the new photo does not match the successful portrait recognition parameter, it means that the new photo is before the user If there is no stored/associated contact, the user can be reminded to create/associate contacts. Of course, if the user takes a photo taken casually such as street shooting, the user can also choose not to create a new contact for the new photo;
  • the photo matching method given in the foregoing embodiment further includes:
  • the setting of the threshold number of reminders can be set by the resolution of the new photo, or can be set by the user;
  • the threshold number of reminders is set to prevent the terminal from acquiring the portrait recognition parameter that does not satisfy the recognition condition according to the photo.
  • Such a portrait recognition parameter cannot uniquely determine the character, and a photo matching error phenomenon may occur, which should be used by the user.
  • a portrait recognition parameter cannot uniquely determine the character, and a photo matching error phenomenon may occur, which should be used by the user.
  • a photo matching error phenomenon may occur, which should be used by the user.
  • the photo matching method after adding the photo information of the selected photo to the photo index table, further includes: adding contact information of the contact in the selected photo; After adding the photo information of the photo 1 of the contact a to the photo index table a, the contact information of the contact a is added in the photo 1 (may be any information for identifying the contact, such as the contact name, the phone number) And so on), by the implementation of the embodiment, when the user clicks on a photo/input of a contact information in the photo database, the terminal can quickly contact the photo/input clicked by the user through the contact information in the photo. All photos associated with the person information are displayed to the user, and the user cannot view them one by one.
  • the photo matching method further includes: deleting or moving the photo according to the contact information of the deleted or moved photo when the photo in the photo database is deleted or moved.
  • the photo information is updated to the photo index table of the corresponding contact; this embodiment implements dynamic update of each contact photo index table, and ensures that the photo index table corresponding to each contact in the terminal is the latest and effective, such that When the user selects a contact, the terminal can completely display the photo related to the contact to the user.
  • the step of obtaining the portrait recognition data from the photograph in the above embodiment comprises: performing face recognition processing on the photograph, extracting facial feature data on the identified portion of the corresponding human face, and using the facial feature data as the portrait recognition data.
  • facial feature data can be eyes, eyebrows, mouth, nose, face, amount
  • the head feature, the relative position, and the like can identify feature parameters of different faces; correspondingly, when the extracted face feature data is multiple (ie, there are multiple faces in the photo), each facial feature data is separately used as A portrait identifies the data.
  • the terminal 2 is a schematic diagram of functional modules of a terminal according to a second embodiment of the present invention. As shown in FIG. 2, in the embodiment, the terminal 2 provided by the present invention includes the following functional modules:
  • a photo index table creating module 201 for selecting or creating a new contact and creating a photo index table for it;
  • a portrait recognition parameter acquisition module 202 configured to acquire a portrait recognition parameter of the contact
  • the portrait recognition parameter acquisition module 202 in the embodiment shown in FIG. 2 includes:
  • the method is configured to receive the portrait recognition data transmitted by the other terminal, and use the received portrait recognition data as a second acquisition sub-module of the portrait recognition parameter.
  • FIG. 3 is a schematic diagram of a functional module of a terminal according to a third embodiment of the present invention.
  • the terminal 2 provided by the present invention further includes one of the following functional modules on the basis of FIG. 2 or Multiple:
  • a new photo extraction module 204 configured to extract all the human face image recognition data in the new photo when a new photo is added to the photo database
  • a new photo matching module 205 configured to match the portrait recognition parameters of each contact with all the human face recognition data in the new photo one by one;
  • a new photo processing module 206 for adding photo information of a new photo in the table
  • a reminder quantity threshold setting module 210 configured to set a reminder quantity threshold
  • a reminder quantity threshold determining module 211 configured to determine whether the number of data of all the portrait identification data in the new photo is greater than the reminder number threshold
  • a photo processing module 213 configured to add contact information of the contact in the selected photo after adding the photo information of the selected photo to the photo index table;
  • the photo information after the photo is deleted or moved is updated to the photo index table in the photo index table of the corresponding contact according to the contact information of the deleted or moved photo.
  • the face recognition module 215 is configured to perform face recognition processing on the photo, extract face feature data at the recognized corresponding face portion, and use the face feature data as the face recognition data.
  • the terminal 2 may be a mobile device such as a mobile phone or a tablet, or may be a fixed device such as a computer that has an address book containing contacts.
  • the terminal is assumed to be a mobile phone
  • the photo database includes three folders (before April, April, and May), and a total of 100 photos are included.
  • the film there are 15 photos related to the contact a (recorded as photo 1, photo 2, ..., photo 15), and the 15 photos belong to different folders, and related to the addition and deletion of photos, etc.
  • the face recognition data/parameter is the face recognition data/parameter;
  • FIG. 4 is a flowchart of the photo query method according to the fourth embodiment of the present invention. As can be seen from FIG. 4, in the embodiment, the photo query method provided by the present invention is provided. Includes the following steps:
  • S401 The user selects the contact a, the terminal obtains the portrait recognition parameter a of the contact a according to the user operation, and establishes a photo index table a for the contact a;
  • the terminal establishes a photo index table for a contact as an example.
  • this step may be repeated to establish a photo index table for each of the multiple contacts, and respectively obtain the portrait. Identify the purpose of the parameter;
  • the terminal After the user selects the contact a, the terminal performs facial recognition and the like on the photo selected by the user according to the user operation, and acquires a facial recognition parameter of the designated person in the user-specified image, and uses the facial recognition parameter as the portrait recognition parameter a of the contact. To match other photos;
  • S402 The terminal sequentially acquires the portrait recognition data of each photo in the photo database, and uses the portrait recognition parameter a to match each of the portrait recognition data one by one. When any of the portrait recognition data in a photo is successfully matched, the photo is added to the photo index table a. ;
  • the terminal uses the portrait recognition parameter a to match 100 photos in the photo database. For each photo, face recognition is first performed to determine whether a face appears. If it does not appear, the photo is a landscape photo and is not processed. If it appears, this is The photo may be a photo of a person, and then face recognition is performed to determine whether the facial parameter in the photo of the character includes matching with the portrait recognition parameter a. If the matching is successful, the photo includes the image of the contact a, and the photo of the photo is taken. The information is added to the photo index table a. If not, the photo does not contain the image of the contact a, and is not processed;
  • the photo information of the photo may appear in the photo index table of the plurality of contacts;
  • the photo index table a includes photo information of 15 photos, exemplarily: photo 1, located in the folder "before 4 months”; photo 2, located in the folder " April”; Photo 3, located in the folder "May”; ...etc. 15 photo photos;
  • S403 The terminal receives and processes the new photo 101, and updates the photo index table.
  • the new photo 101 received by the terminal may be a newly taken photo or a photo transmitted by another terminal;
  • the terminal After receiving the new photo 101, the terminal sequentially performs face recognition and face recognition processing to determine whether the portrait recognition parameter a is included in the new photo 101. If yes, the storage location and name of the new photo 101 are added to the photo index table a. If the new photo 101 does not include the portrait recognition parameter a and is a person photo, it is determined whether the new photo 101 satisfies the condition of the newly created contact, such as determining whether the number of faces in the new photo 101 is greater than a preset threshold (the preset threshold may be Automatically or manually set according to the shooting resolution or photo resolution of the terminal, for example, 2).
  • the preset threshold may be Automatically or manually set according to the shooting resolution or photo resolution of the terminal, for example, 2).
  • the facial feature parameters obtained by photo recognition are not very clear, it may not be used to identify other photos. If not less than or equal to the preset threshold, the user is reminded to create/associate the contact b for one or more facial features in the photo 101, and the user selects the facial feature of the newly created/associated contact as the contact b.
  • the portrait recognition parameter b, and a new photo index table b for the contact b further, using the portrait recognition parameter b to perform photos in the photo database With the match to photograph the photo information added to the photo index sheet b;
  • the user when the user is reminded to newly create/associate the contact b for one or more facial features in the photo 101, the user may also choose not to create/associate the contact, which is mainly for street shooting, the subject is unfamiliar, New photos are unfamiliar and so on;
  • the contact information of the corresponding contact is added in the photo, for example, the contact information of the contact a is added in the photo 1, so that the terminal can know Which contact is the photo associated with;
  • the photo in the photo database has an update operation such as deletion/moving/copying
  • the photo index table of the contact is updated synchronously. If not, the photo does not belong to any contact and is not processed;
  • the photo 1 is deleted because the photo 1 has the name of the contact a (contact information), that is, the photo index table a needs to be updated at this time, and the photo information about the photo 1 in the photo index table a is deleted; moving/copying, etc.
  • the update operation is similar to this. For example, if you move/copy photo 1, you need to modify the photo information after the photo 1 is moved/copied in the photo index table a;
  • S405 The terminal displays the photo that the user looks for according to the photo index table.
  • the user query photo includes two paths:
  • the user selects the contact a, the terminal finds the corresponding photo index table a, and displays the photos 1 to 15 recorded in the photo index table a to the user through the small window/new window;
  • the user selects the photo 1 / enters the contact a, the terminal finds the corresponding photo index table a, and displays the photos 1 to 15 recorded in the photo index table a to the user through the small window/new window.
  • the terminal acquires the portrait recognition parameter of a contact according to the user operation and establishes a photo index table for the contact, which is equivalent to establishing a relationship between the portrait recognition parameter and a photo index table, and then using the contact recognition parameter of the contact to the photo database.
  • Matching adding the photo information of the matched photos (the photos are obviously related to the contact) (such as the storage location, name, etc. information that can be queried) to the photo index table, so that the user does not need the photo
  • the photo index table can be quickly queried to all the photos related to the contact, the operation is simple, the complicated operation of the existing photo query technology is solved, and the user experience is enhanced.
  • the address matching method and terminal based on the address book provided by the embodiment of the present invention have the following beneficial effects: when the user needs to view the photo of a contact, the photo is not required to be used for each photo in the photo database. View, that is, you can quickly query all the photos related to the contact according to the photo index table, which is easy to operate, solves the complicated operation of the existing query photos, and achieves the effect of enhancing the user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Library & Information Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Processing Or Creating Images (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明提供了一种基于通讯录的照片匹配方法及终端,该方法包括:选择或新建联系人并为其建立照片索引表;获取联系人的人像识别参数;依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将人像识别参数与所选择照片中所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到照片索引表。通过本发明的实施,终端根据用户操作获取某联系人的人像识别参数并为建立照片索引表,进而利用人像识别参数对照片数据库内各照片逐一进行匹配,将匹配成功照片增加到照片索引表中,这样用户在查看某联系人的照片时就可以根据照片索引表快速看到该联系人的所有照片,操作简单。

Description

一种基于通讯录的照片匹配方法及终端 技术领域
本发明涉及照片查询应用领域,尤其涉及一种基于通讯录的照片匹配方法及终端。
背景技术
现有的照片在存储时一般是按照时间的不同存储到不同的文件夹,如终端自动建立分别命名为2014年1月、2月等文件夹,根据照片的拍摄时间将照片存放到对应的文件夹内,这样用户就可以根据拍摄时间来查看照片了,但是也存在一些问题,如用户需要查看某联系人在不同时间的照片时,就需要翻阅多个文件夹,并且查看大部分照片之后,才能看到所有希望看到的照片,操作繁杂及浪费时间,当用户需要查看的照片过多时,这类查找技术将大大降低用户的使用体验。
因此,如何提供一种可以降低用户操作繁杂度的照片匹配技术,是本领域技术人员亟待解决的技术问题。
发明内容
本发明实施例提供了一种基于通讯录的照片匹配方法及终端,以至少解决现有查询照片时操作繁杂的问题。
本发明提供了一种基于通讯录的照片匹配方法,在一个实施例中,该方法包括:选择或新建联系人并为其建立照片索引表;获取联系人的人像识别参数;依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将人像识别参数与所选择照片中所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到照片索引表。
上述实施例中的获取联系人的人像识别参数的步骤包括:设置人像识别数据数量阈值,根据用户操作选择照片,提取用户所选择照片中的所有人像识别数据,当提取到的人像识别数据数量小于人像识别数据数量阈值时,根据用户操作选择一个人像识别数据作为人像识别参数;或者,接收其他终端传输的人像识别数据,将接收到的人像识别数据作为人像识别参数。
上述实施例还包括:当有新照片增加到照片数据库时,提取新照片中的所有人像识别数据;将各联系人的人像识别参数与新照片中的所有人像识别数据一一进行匹配; 若新照片中的所有人像识别数据中任一人像识别数据存在匹配成功的人像识别参数,则确定所有匹配成功的人像识别参数,在各匹配成功的人像识别参数对应的联系人的照片索引表中增加新照片的照片信息。
上述实施例还包括:若新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则提示新建联系人;为新建联系人建立照片索引表,根据用户操作选择新照片中的所有人像识别数据的一个作为新建联系人的人像识别参数;依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据;将新建联系人的人像识别参数与所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到新建联系人的照片索引表。
上述实施例在提示新建联系人之前还包括:设置提醒数量阈值;判断新照片中的所有人像识别数据的数据数量是否大于提醒数量阈值;若小于则提示新建联系人。
上述实施例在将所选择照片的照片信息增加到照片索引表之后,还包括:在所选择照片中添加联系人的联系人信息。
上述实施例还包括:在照片数据库中的照片发生删除或移动时,根据发生删除或移动的照片的联系人信息,将照片发生删除或移动后的照片信息更新到对应联系人的照片索引表中。
上述实施例中的从照片中获得人像识别数据的步骤包括:对照片进行人脸识别处理,在识别到的对应人脸的部位提取面部特征数据,将面部特征数据作为人像识别数据。
为将本发明运用于实际生活中,本发明也提供了一种终端,在一个实施例中,该终端包括:设置为选择或新建联系人并为其建立照片索引表的照片索引表建立模块;设置为获取联系人的人像识别参数的人像识别参数获取模块;以及,设置为依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将人像识别参数与所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到照片索引表的照片处理匹配模块。
本发明的有益效果:
本发明实施例提供的照片匹配方法,终端根据用户操作获取某联系人的人像识别参数并为该联系人建立照片索引表,相当于建立了一个人像识别参数与一个照片索引表的关联,进而利用该联系人的人像识别参数对照片数据库内各照片的人像识别数据 逐一进行匹配,将匹配成功的照片(这些照片显然都与该联系人有关)的照片信息(如存储位置、名称等可以查询到照片的信息)增加到照片索引表中,这样用户在需要查看某联系人的照片时,就不需要对照片数据库中的每个照片进行查看,即可以根据照片索引表快速查询到与该联系人有关的所有照片,操作简单,解决了现有查询照片时操作繁杂的问题,增强了用户的使用体验。
附图说明
图1为本发明第一实施例提供的照片匹配方法的流程图;
图2为本发明第二实施例提供的终端的功能模块示意图;
图3为本发明第三实施例提供的终端的功能模块示意图;
图4为本发明第四实施例提供的照片匹配方法的流程图。
具体实施方式
现通过具体实施方式结合附图的方式对本发明做出进一步的诠释说明。
本发明实施例的核心思想是建立联系人的人像识别参数与其照片索引表的关联,利用一些身份识别技术(如面部识别技术)对终端内的照片数据库进行匹配,将包含相同人像识别参数的照片(这些照片就是包括同一联系人的照片)增加到对应联系人的照片索引表中,这样,在用户需要查看某联系人的所有照片时,就可以根据照片索引表快速的查询到该联系人的相关照片。
第一实施例:
图1为本发明第一实施例提供的照片匹配方法的流程图,由图1可知,在本实施例中,本发明提供的基于通讯录的照片匹配方法包括以下步骤:
S101:选择或新建联系人并为其建立照片索引表;
终端根据用户操作选择或新建一个或多个联系人,并分别为每一个联系人建立一个对应的照片索引表,这个照片索引表用于对与该联系人相关的照片进行索引;
S102:获取联系人的人像识别参数;
人像识别参数是对用户为每一个联系人选择的照片进行处理,得到该联系人的人像识别参数,人像识别参数包括用于分别不同人物的所有参数,如面部特征、两瞳孔与鼻尖的相对位置、瞳孔颜色、头顶与肩宽比例等可以用于识别人物的特征参数即可;
在一些实施例中,获取联系人的人像识别参数的途径是终端对用户选择的照片进行处理得到,具体的为:
设置人像识别数据数量阈值,根据用户操作选择照片,提取用户所选择照片中的所有人像识别数据,当提取到的人像识别数据数量小于人像识别数据数量阈值时,根据用户操作选择一个人像识别数据作为人像识别参数;具体的,设置人像识别数据数量阈值为3个,终端所提供到的所有人像识别数据是指在满足识别条件下所请提取到的所有人像识别数据,如在用户选择的一联系人的照片中,主要人物为一个,而作为照片背景的街道可能有很多行人,而为了后续进行人像识别参数的匹配,对人像识别参数有一定的识别条件(必须能够清楚的看到人脸等),这样终端实际所提取到的人像识别数据的数据仅为1个,这样就可以把提取到的人像识别数据作为该联系人的人像识别参数,相应的,如果提取到2个人像识别数据,则根据用户操作,选择用户指定的人像识别数据作为该联系人的人像识别参数;
在一些实施例中,获取联系人的人像识别参数的途径是终端根据用户操作从其他设备所获得的,具体的如:
接收其他终端传输的人像识别数据,将接收到的人像识别数据作为人像识别参数;例如,用户需要为一联系人指定照片,而其他用户/终端设备已经对同一联系人分配了人像识别参数,那么,本用户/终端就可以与其他用户/终端通信,获取其他用户/终端中该联系人的人像识别数据,并将其作为该联系人的人像识别参数;
S103:依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将人像识别参数与所选择照片中所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到照片索引表;
具体的,终端依次从照片数据库中选择照片,针对每一张所选择照片都进行如下处理:提取所选择照片内的所有人像设备数据,当人像识别数据为1个时,将其与某联系人的人像识别参数进行匹配,若匹配成功,则认为这个照片是该联系人的照片,当人像识别数据为2个及以上时,将其分别与某联系人的人像识别参数进行匹配,只要其中的一个人像识别数据匹配成功,则认为这个照片是该联系人的照片,当认为某照片是一联系人的照片时,就将该照片的照片信息(如名称、放置/存储位置等可以让终端查找到该照片的信息均可)增加到对应联系人的照片索引表中;
在一些实施例中,将某照片内的人像识别数据与某联系人的人像识别参数进行匹配时,可以根据照片的分辨率设置匹配阈值(如照片分辨率很高时,设置匹配阈值为95%,照片分辨率较低时,设置匹配阈值为85%),这样,只要人像识别数据与人像识别参数的匹配度/相似度大于匹配阈值,就认为人像识别数据与人像识别参数匹配成功;相应的,在一些实施例中,还可以仅在人像识别数据与人像识别参数的完全匹配/相同时,才认为人像识别数据与人像识别参数匹配成功;
在一些实施例中,若某照片提取到多个人像识别数据,并且这多个人像识别数据中的2个及以上人像识别数据分别与不同的人像识别参数匹配成功,则将这个照片的照片信息增加到所有匹配成功的人像识别参数对应的联系人的照片索引表中
本实施例提供了如何对终端内照片数据库的照片进行查找的方法,方便了用户,在用户需要查看某联系人的照片时,根据照片索引表查询到该联系人所有照片的照片信息,到对应的放置/存储位置查找/下载对应名称的照片,并向用户展示。
在一些实施例中,图1所示的照片匹配方法还包括:
当有新照片增加到照片数据库时,提取新照片中的所有人像识别数据;
将各联系人的人像识别参数与新照片中的所有人像识别数据一一进行匹配;
若新照片中的所有人像识别数据中任一人像识别数据存在匹配成功的人像识别参数,则确定所有匹配成功的人像识别参数,在各匹配成功的人像识别参数对应的联系人的照片索引表中增加新照片的照片信息;
本实施例对新照片如何处理给出了具体的方案,若新照片无法提取到有效的人像识别数据,则认为这个新照片是风景照片/无效照片等,就不处理,当提取到有效的人像识别数据(1个或多个)时,将其与各联系人的人像识别参数一一进行匹配,这样就可以实现对新照片内的所有人像识别数据分别进行匹配,避免了新照片是某些联系人的合影照片,而仅添加到部分联系人的照片索引表内的情况出现。
在一些实施例中,上述实施例给出的照片匹配方法还包括:
若新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则提示新建联系人;若新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则代表着新照片是用户之前没有存储/关联联系人,就可以提醒用户新建/关联联系人,当然,若用户为街拍等随性拍摄的照片,用户也可以选择不为新照片新建联系人;
为新建联系人建立照片索引表,根据用户操作选择新照片中的所有人像识别数据的一个作为新建联系人的人像识别参数;该步骤与S101及S102类似,不再赘述;
依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据;将新建联系人的人像识别参数与所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到新建联系人的照片索引表;该步骤与S103类似,不再赘述。
在一些实施例中,上述实施例给出的照片匹配方法在提示新建联系人之前还包括:
设置提醒数量阈值;提醒数量阈值的设置由可以根据新照片的分辨率自行设置,也可以有用户设置;
判断新照片中的所有人像识别数据的数据数量是否大于提醒数量阈值;
若小于,则提示新建联系人,若大于或等于则不提示新建联系人;
在本实施例中,设置提醒数量阈值是为了避免终端根据照片获取不满足识别条件的人像识别参数,这类人像识别参数并不能唯一的确定人物,会出现照片匹配错误的现象,应该用户的使用体验。
在一些实施例中,上述实施例给出的照片匹配方法在将所选择照片的照片信息增加到照片索引表之后,还包括:在所选择照片中添加联系人的联系人信息;具体的,如在将联系人a的照片1的照片信息增加到照片索引表a之后,在照片1中增加联系人a的联系人信息(可以是任意用于识别联系人的信息,如联系人名称、电话号码等等),通过本实施例的实施,用户在照片数据库内点击某照片/输入某联系人信息时,终端就可以通过照片中的联系人信息快速的将与用户所点击的照片/输入的联系人信息相关联的所有照片展示给用户,而不能用户一一查看。
在一些实施例中,上述实施例给出的照片匹配方法还包括:在照片数据库中的照片发生删除或移动时,根据发生删除或移动的照片的联系人信息,将照片发生删除或移动后的照片信息更新到对应联系人的照片索引表中;本实施例实现了各联系人照片索引表的动态更新,保证了终端内对应于各联系人的照片索引表都是最新的、有效的,这样用户选择某联系人时,终端都可以完整的向用户展示该联系人有关的照片。
在一些实施例中,上述实施例从照片中获得人像识别数据的步骤包括:对照片进行人脸识别处理,在识别到的对应人脸的部位提取面部特征数据,将面部特征数据作为人像识别数据;具体的,面部特征数据可以是眼睛、眉毛、嘴巴、鼻子、脸庞、额 头特征以及相对位置等等可以识别出不同人脸的特征参数;相应的,当提取到的面部特征数据为多个(即照片内有多个人脸)时,每一个面部特征数据都单独的作为一个人像识别数据。
第二实施例:
图2为本发明第二实施例提供的终端的功能模块示意图,由图2可知,在本实施例中,本发明提供的终端2包括以下功能模块:
设置为选择或新建联系人并为其建立照片索引表的照片索引表建立模块201;
设置为获取联系人的人像识别参数的人像识别参数获取模块202;以及
设置为依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将人像识别参数与所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到照片索引表的照片处理匹配模块203。
在一些实施例中,图2所示实施例中的人像识别参数获取模块202包括:
设置为设置人像识别数据数量阈值,根据用户操作选择照片,提取用户所选择照片中的所有人像识别数据,当提取到的人像识别数据数量小于人像识别数据数量阈值时,根据用户操作选择一个人像识别数据作为人像识别参数的第一获取子模块;
以及
设置为接收其他终端传输的人像识别数据,将接收到的人像识别数据作为人像识别参数的第二获取子模块。
第三实施例:
图3为本发明第三实施例提供的终端的功能模块示意图,由图3可知,在本实施例中,本发明提供的终端2在图2的基础上,还包括以下功能模块中的一个或多个:
设置为当有新照片增加到照片数据库时,提取新照片中的所有人像识别数据的新照片提取模块204;
设置为将各联系人的人像识别参数与新照片中的所有人像识别数据一一进行匹配的新照片匹配模块205;
设置为若新照片中的所有人像识别数据中任一人像识别数据存在匹配成功的人像识别参数,则确定所有匹配成功的人像识别参数,在各匹配成功的人像识别参数对应的联系人的照片索引表中增加新照片的照片信息的新照片处理模块206;
设置为若新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则提示新建联系人的新建联系人提醒模块207;
设置为为新建联系人建立照片索引表,根据用户操作选择新照片中的所有人像识别数据的一个作为新建联系人的人像识别参数的新建联系人设置模块208;
设置为依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将新建联系人的人像识别参数与所有人像识别数据逐一进行匹配,若所有人像识别数据中有任一人像识别数据与其匹配成功,则将所选择照片的照片信息增加到新建联系人的照片索引表的新建联系人匹配模块209;
设置为设置提醒数量阈值的提醒数量阈值设置模块210;
设置为判断新照片中的所有人像识别数据的数据数量是否大于提醒数量阈值的提醒数量阈值判断模块211;
设置为若小于则提示新建联系人的新建联系人提醒处理模块212;
设置为在将所选择照片的照片信息增加到照片索引表之后,在所选择照片中添加联系人的联系人信息的照片处理模块213;
设置为在照片数据库中的照片发生删除或移动时,根据发生删除或移动的照片的联系人信息,将照片发生删除或移动后的照片信息更新到对应联系人的照片索引表中的照片索引表更新模块214;
设置为对照片进行人脸识别处理,在识别到的对应人脸的部位提取面部特征数据,将面部特征数据作为人像识别数据的面部识别模块215。
在一些实施例中,本发明所涉及的终端2可以是手机、平板等移动设备,也可以是电脑等内置有包含联系人的通讯录的固定设备。
第四实施例:
现结合一具体应用实例来说明本发明的主要技术方案,在本应用实例中,假定终端为手机,照片数据库包括3个文件夹(4月之前、4月、5月),总共包含100张照 片,与联系人a相关的照片有15张(记为照片1、照片2、……、照片15),并且这15张照片分属不同的文件夹,并涉及照片的新增及删除等更新操作,人像识别数据/参数为面部识别数据/参数;图4为本发明第四实施例提供的照片查询方法的流程图,由图4可知,在本实施例中,本发明提供的照片查询方法包括以下步骤:
S401:用户选择联系人a,终端根据用户操作获取联系人a的人像识别参数a,并为联系人a建立照片索引表a;
本实施例仅以终端为一个联系人建立照片索引表为例进行说明,可以预见的时,在其他实施例中,可以重复本步骤以达到为多个联系人分别建立照片索引表、分别获取人像识别参数的目的;
用户选择联系人a后,终端根据用户操作,对用户选择的照片进行面部识别等处理,获取用户指定图像内指定人物的面部识别参数,将该面部识别参数作为该联系人的人像识别参数a,以匹配其他照片;
S402:终端依次获取照片数据库中各照片的人像识别数据,利用人像识别参数a逐一匹配各人像识别数据,在某照片内的任一人像识别数据匹配成功时,将该照片增加到照片索引表a;
终端利用人像识别参数a匹配照片数据库内的100张照片,针对每张照片,先进行人脸识别,判断是否出现人脸,若未出现,这个照片为风景照片,不处理,若出现,则这种照片可能为人物照片,进而进行人脸识别,判断该人物照片内的面部参数是否包括与人像识别参数a匹配,若匹配成功,则这个照片包含联系人a的图像,将这张照片的照片信息增加到照片索引表a,若否,则这张照片未包含联系人a的图像,不处理;
可以预见的是,若某一张照片包括多个人脸(如合影等),这张照片的照片信息是可以出现在多个联系人的照片索引表内的;
承接本实施例的假设,终端执行本步骤之后,照片索引表a内包括15张照片的照片信息,示例性的为:照片1,位于文件夹“4月之前”;照片2,位于文件夹“4月”;照片3,位于文件夹“5月”;……等等15张照片的照片信息;
S403:终端接收并处理新照片101,更新照片索引表;
终端接收到的新照片101的方式可以是新拍摄的照片,或者其他终端传输过来的照片;
终端在接收到新照片101后,依次进行人脸识别、面部识别处理,判断新照片101内是否包含人像识别参数a,若是,则将该新照片101的存放位置及名称增加到照片索引表a;若新照片101没有包括人像识别参数a,且为人物照片,则判断新照片101是否满足新建联系人的条件,如判断新照片101内的人脸数量是否大于预设阈值(预设阈值可以根据终端的拍摄分辨率或照片分辨率来自动或手动设定,例如2个),若大于预设阈值(此时照片识别得到的面部特征参数就不是很清楚,可能不能用来识别其他照片),则不处理,若小于/等于预设阈值,则提醒用户为照片101内的一个或多个面部特征新建/关联联系人b,并将用户选择新建/关联联系人的面部特征作为联系人b的人像识别参数b,同时为联系人b新建照片索引表b,进一步的,利用人像识别参数b对照片数据库内的照片进行匹配,将匹配到的照片的照片信息增加到照片索引表b;
相应的,在提醒用户为照片101内的一个或多个面部特征分别新建/关联联系人b时,用户也可以选择不新建/关联联系人,此时主要是针对街拍、拍摄对象不熟悉、新照片不熟悉等情况;
S404:照片数据库内的照片发生删除/移动等更新操作时,同步更新照片索引表;
在将某照片的照片信息增加到某联系人的照片索引表之后,在该照片内增加对应联系人的联系人信息,如在照片1内增加联系人a的联系人信息,这样终端就可以知道照片是与哪个联系人相关的;
在此基础上,若照片数据库内的照片发生删除/移动/复制等更新操作时,首先判断发生更新操作的照片内是否有联系人信息,若是,则该照片为某联系人的照片,需要对该联系人的照片索引表同步更新,若否,则该照片不属于任何联系人,不处理;
例如照片1删除,因为照片1内有联系人a的名称(联系人信息),也即此时需要对照片索引表a更新,删除照片索引表a中有关照片1的照片信息;移动/复制等更新操作与此类似,如移动/复制照片1,则需要在照片索引表a中修改照片1移动/复制后的照片信息;
相应的,当一个照片内有多个联系人信息时,需要同时对这多个联系人各自的照片索引表都进行处理;
S405:终端根据照片索引表向用户展示用户所查找的照片;
用户查询照片包括两个路径:
一,在通讯录内查询:用户选择联系人a,终端查找到对应的照片索引表a,将照片索引表a内记载的照片1至15通过小窗口/新窗口展示给用户;
二,在照片数据库内查询:用户选择照片1/输入联系人a,终端查找到对应的照片索引表a,将照片索引表a内记载的照片1至15通过小窗口/新窗口展示给用户。
综上可知,通过本发明的实施,至少存在以下有益效果:
终端根据用户操作获取某联系人的人像识别参数并为该联系人建立照片索引表,相当于建立了一个人像识别参数与一个照片索引表的关联,进而利用该联系人的人像识别参数对照片数据库进行匹配,将匹配到的照片(这些照片显然都与该联系人有关)的照片信息(如存储位置、名称等可以查询到照片的信息)增加到照片索引表中,这样用户就不需要对照片数据库中的每个照片进行查看,即可以根据照片索引表快速查询到与该联系人有关的所有照片,操作简单,解决了现有照片查询技术操作繁杂的问题,增强了用户的使用体验。
以上仅是本发明的具体实施方式而已,并非对本发明做任何形式上的限制,凡是依据本发明的技术实质对以上实施方式所做的任意简单修改、等同变化、结合或修饰,均仍属于本发明技术方案的保护范围。
工业实用性
如上所述,本发明实施例提供的一种基于通讯录的照片匹配方法及终端,具有以下有益效果:用户在需要查看某联系人的照片时,就不需要对照片数据库中的每个照片进行查看,即可以根据照片索引表快速查询到与该联系人有关的所有照片,操作简单,解决了现有查询照片时操作繁杂的问题,达到了增强用户的使用体验的效果。

Claims (16)

  1. 一种基于通讯录的照片匹配方法,包括:
    选择或新建联系人并为其建立照片索引表;
    获取所述联系人的人像识别参数;
    依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将所述人像识别参数与所述所选择照片中所有人像识别数据逐一进行匹配,若所述所有人像识别数据中有任一人像识别数据与其匹配成功,则将所述所选择照片的照片信息增加到所述照片索引表。
  2. 如权利要求1所述的照片匹配方法,其中,所述获取所述联系人的人像识别参数的步骤包括:
    设置人像识别数据数量阈值,根据用户操作选择照片,提取用户所选择照片中的所有人像识别数据,当提取到的人像识别数据数量小于所述人像识别数据数量阈值时,根据用户操作选择一个人像识别数据作为所述人像识别参数;
    或者,
    接收其他终端传输的人像识别数据,将接收到的人像识别数据作为所述人像识别参数。
  3. 如权利要求1所述的照片匹配方法,其中,所述照片匹配方法还包括:
    当有新照片增加到所述照片数据库时,提取所述新照片中的所有人像识别数据;
    将各联系人的人像识别参数与所述新照片中的所有人像识别数据一一进行匹配;
    若所述新照片中的所有人像识别数据中任一人像识别数据存在匹配成功的人像识别参数,则确定所有匹配成功的人像识别参数,在各匹配成功的人像识别参数对应的联系人的照片索引表中增加所述新照片的照片信息。
  4. 如权利要求3所述的照片匹配方法,其中,所述照片匹配方法还包括:
    若所述新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则提示新建联系人;
    为所述新建联系人建立照片索引表,根据用户操作选择所述新照片中的所有人像识别数据的一个作为所述新建联系人的人像识别参数;
    依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据;将所述新建联系人的人像识别参数与所述所有人像识别数据逐一进行匹配,若所述所有人像识别数据中有任一人像识别数据与其匹配成功,则将所述所选择照片的照片信息增加到所述新建联系人的照片索引表。
  5. 如权利要求4所述的照片匹配方法,其中,所述照片匹配方法在提示新建联系人之前还包括:
    设置提醒数量阈值;
    判断所述新照片中的所有人像识别数据的数据数量是否大于所述提醒数量阈值;
    若小于则提示新建联系人。
  6. 如权利要求1所述的照片匹配方法,其中,在将所述所选择照片的照片信息增加到所述照片索引表之后,还包括:在所述所选择照片中添加所述联系人的联系人信息。
  7. 如权利要求6所述的照片匹配方法,其中,还包括:在所述照片数据库中的照片发生删除或移动时,根据发生删除或移动的照片的联系人信息,将所述照片发生删除或移动后的照片信息更新到对应联系人的照片索引表中。
  8. 如权利要求1至7任一项所述的照片匹配方法,其中,从照片中获得人像识别数据的步骤包括:对所述照片进行人脸识别处理,在识别到的对应人脸的部位提取面部特征数据,将所述面部特征数据作为所述人像识别数据。
  9. 一种终端,包括:
    设置为选择或新建联系人并为其建立照片索引表的照片索引表建立模块;
    设置为获取所述联系人的人像识别参数的人像识别参数获取模块;以及
    设置为依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将所述人像识别参数与所述所有人像识别数据逐一进行匹配,若所述所有人像识别数据中有任一人像识别数据与其匹配成功,则将所述所选择照片的照片信息增加到所述照片索引表的照片处理匹配模块。
  10. 如权利要求9所述的终端,其中,所述人像识别参数获取模块包括:
    设置为设置人像识别数据数量阈值,根据用户操作选择照片,提取用户所选择照片中的所有人像识别数据,当提取到的人像识别数据数量小于所述人像识别数据数量阈值时,根据用户操作选择一个人像识别数据作为所述人像识别参数的第一获取子模块;
    以及
    设置为接收其他终端传输的人像识别数据,将接收到的人像识别数据作为所述人像识别参数的第二获取子模块。
  11. 如权利要求9所述的终端,其中,所述终端还包括:
    设置为当有新照片增加到所述照片数据库时,提取所述新照片中的所有人像识别数据的新照片提取模块;
    设置为将各联系人的人像识别参数与所述新照片中的所有人像识别数据一一进行匹配的新照片匹配模块;以及
    设置为若所述新照片中的所有人像识别数据中任一人像识别数据存在匹配成功的人像识别参数,则确定所有匹配成功的人像识别参数,在各匹配成功的人像识别参数对应的联系人的照片索引表中增加所述新照片的照片信息的新照片处理模块。
  12. 如权利要求11所述的终端,其中,所述终端还包括:
    设置为若所述新照片中的所有人像识别数据均没有匹配成功的人像识别参数,则提示新建联系人的新建联系人提醒模块;
    设置为为所述新建联系人建立照片索引表,根据用户操作选择所述新照片中的所有人像识别数据的一个作为所述新建联系人的人像识别参数的新建联系人设置模块;以及
    设置为依次从照片数据库中选择照片,提取所选择照片中所有人像识别数据,将所述新建联系人的人像识别参数与所述所有人像识别数据逐一进行匹配,若所述所有人像识别数据中有任一人像识别数据与其匹配成功,则将所述所选择照片的照片信息增加到所述新建联系人的照片索引表的新建联系人匹配模块。
  13. 如权利要求12所述的终端,其中,所述终端还包括:
    设置为设置提醒数量阈值的提醒数量阈值设置模块;
    设置为判断所述新照片中的所有人像识别数据的数据数量是否大于所述提醒数量阈值的提醒数量阈值判断模块;以及
    设置为若小于则提示新建联系人的新建联系人提醒处理模块。
  14. 如权利要求9所述的终端,其中,所述终端还包括:设置为在将所述所选择照片的照片信息增加到所述照片索引表之后,在所述所选择照片中添加所述联系人的联系人信息的照片处理模块。
  15. 如权利要求14所述的终端,其中,所述终端还包括:设置为在所述照片数据库中的照片发生删除或移动时,根据发生删除或移动的照片的联系人信息,将所述照片发生删除或移动后的照片信息更新到对应联系人的照片索引表中的照片索引表更新模块。
  16. 如权利要求9至15任一项所述的终端,其中,所述终端包括:设置为对所述照片进行人脸识别处理,在识别到的对应人脸的部位提取面部特征数据,将所述面部特征数据作为所述人像识别数据的面部识别模块。
PCT/CN2014/089364 2014-06-19 2014-10-23 一种基于通讯录的照片匹配方法及终端 WO2015192575A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
RU2017101584A RU2667802C2 (ru) 2014-06-19 2014-10-23 Способ и терминал сопоставления изображений по адресной книге
AU2014397825A AU2014397825A1 (en) 2014-06-19 2014-10-23 Address book based picture matching method and terminal
EP14895018.1A EP3159808A4 (en) 2014-06-19 2014-10-23 Address book based picture matching method and terminal
US15/319,988 US20170139911A1 (en) 2014-06-19 2014-10-23 Address book based picture matching method and terminal

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410274286.2 2014-06-19
CN201410274286.2A CN105279165A (zh) 2014-06-19 2014-06-19 一种基于通讯录的照片匹配方法及终端

Publications (1)

Publication Number Publication Date
WO2015192575A1 true WO2015192575A1 (zh) 2015-12-23

Family

ID=54934800

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/089364 WO2015192575A1 (zh) 2014-06-19 2014-10-23 一种基于通讯录的照片匹配方法及终端

Country Status (6)

Country Link
US (1) US20170139911A1 (zh)
EP (1) EP3159808A4 (zh)
CN (1) CN105279165A (zh)
AU (1) AU2014397825A1 (zh)
RU (1) RU2667802C2 (zh)
WO (1) WO2015192575A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106534481A (zh) * 2016-09-28 2017-03-22 努比亚技术有限公司 一种照片或视频分享系统及方法

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102386893B1 (ko) * 2014-11-13 2022-04-15 삼성전자 주식회사 이미지 데이터의 보안 방법 및 이를 지원하는 전자 장치
CN105786986A (zh) * 2016-02-16 2016-07-20 广东欧珀移动通信有限公司 照片的查找方法及装置
CN105763710A (zh) * 2016-03-25 2016-07-13 努比亚技术有限公司 一种图片设置系统和方法
CN106101357B (zh) * 2016-06-28 2019-11-26 上海青橙实业有限公司 信息处理方法及移动终端
CN106202341B (zh) * 2016-06-30 2019-08-06 四川长虹电器股份有限公司 结合照片信息与人像识别的关系网络构建方法
CN110431838B (zh) * 2017-03-22 2022-03-29 韩国斯诺有限公司 提供人脸识别摄像机的动态内容的方法及系统
CN107704514A (zh) * 2017-08-31 2018-02-16 努比亚技术有限公司 一种照片管理方法、装置及计算机可读存储介质
WO2019075644A1 (zh) * 2017-10-17 2019-04-25 深圳传音通讯有限公司 人像照片的搜索方法和终端
CN110839242B (zh) * 2018-08-17 2023-07-04 中国移动通信集团广东有限公司 异常号码识别方法及装置
CN110717091B (zh) * 2019-09-16 2022-12-09 苏宁云计算有限公司 基于人脸识别的词条数据扩充方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101990031A (zh) * 2009-07-30 2011-03-23 索尼爱立信移动通讯股份有限公司 使用面部识别来更新个人联系人列表的系统和方法
WO2012079215A1 (zh) * 2010-12-13 2012-06-21 宇龙计算机通信科技(深圳)有限公司 协同操作方法、装置及移动通信终端
CN102779179A (zh) * 2012-06-29 2012-11-14 华为终端有限公司 一种信息关联的方法及终端
CN103034714A (zh) * 2012-12-11 2013-04-10 北京百度网讯科技有限公司 移动终端的照片分类管理方法、装置和移动终端
CN103067558A (zh) * 2013-01-17 2013-04-24 深圳市中兴移动通信有限公司 与通讯录中联系人的图片相关联的方法和装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6606398B2 (en) * 1998-09-30 2003-08-12 Intel Corporation Automatic cataloging of people in digital photographs
US7843495B2 (en) * 2002-07-10 2010-11-30 Hewlett-Packard Development Company, L.P. Face recognition in a digital imaging system accessing a database of people
US8363951B2 (en) * 2007-03-05 2013-01-29 DigitalOptics Corporation Europe Limited Face recognition training method and apparatus
EP1536616B1 (en) * 2003-11-27 2009-11-11 Sony Ericsson Mobile Communications AB Interactive phone book
US7564994B1 (en) * 2004-01-22 2009-07-21 Fotonation Vision Limited Classification system for consumer digital images using automatic workflow and face detection and recognition
US7809722B2 (en) * 2005-05-09 2010-10-05 Like.Com System and method for enabling search and retrieval from image files based on recognized information
US9241056B2 (en) * 2006-06-22 2016-01-19 Sony Corporation Image based dialing
KR100840021B1 (ko) * 2007-11-05 2008-06-20 (주)올라웍스 특성 데이터를 이용하여 디지털 데이터에 포함된 인물의얼굴에 대해 인식하는 방법 및 시스템
CN102368269A (zh) * 2011-10-25 2012-03-07 华为终端有限公司 建立关联关系的方法及装置
TWI522821B (zh) * 2011-12-09 2016-02-21 致伸科技股份有限公司 相片管理系統
CN102819726B (zh) * 2012-06-27 2016-08-24 宇龙计算机通信科技(深圳)有限公司 用于移动终端的照片处理系统及方法
US9582482B1 (en) * 2014-07-11 2017-02-28 Google Inc. Providing an annotation linking related entities in onscreen content

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101990031A (zh) * 2009-07-30 2011-03-23 索尼爱立信移动通讯股份有限公司 使用面部识别来更新个人联系人列表的系统和方法
WO2012079215A1 (zh) * 2010-12-13 2012-06-21 宇龙计算机通信科技(深圳)有限公司 协同操作方法、装置及移动通信终端
CN102779179A (zh) * 2012-06-29 2012-11-14 华为终端有限公司 一种信息关联的方法及终端
CN103034714A (zh) * 2012-12-11 2013-04-10 北京百度网讯科技有限公司 移动终端的照片分类管理方法、装置和移动终端
CN103067558A (zh) * 2013-01-17 2013-04-24 深圳市中兴移动通信有限公司 与通讯录中联系人的图片相关联的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3159808A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106534481A (zh) * 2016-09-28 2017-03-22 努比亚技术有限公司 一种照片或视频分享系统及方法

Also Published As

Publication number Publication date
EP3159808A1 (en) 2017-04-26
RU2017101584A (ru) 2018-07-19
RU2017101584A3 (zh) 2018-07-19
AU2014397825A1 (en) 2017-01-19
RU2667802C2 (ru) 2018-09-24
CN105279165A (zh) 2016-01-27
US20170139911A1 (en) 2017-05-18
EP3159808A4 (en) 2018-01-10

Similar Documents

Publication Publication Date Title
WO2015192575A1 (zh) 一种基于通讯录的照片匹配方法及终端
US11631050B2 (en) Syncing physical and electronic document
JP6123119B2 (ja) 情報を関連付ける方法および端末
EP3312801A1 (en) Method and system for providing augmented reality content using user-edited image
CN108600632B (zh) 拍照提示方法、智能眼镜及计算机可读存储介质
CN103942705A (zh) 一种基于人脸识别的广告分类匹配推送方法及系统
WO2014059655A1 (zh) 终端和粘贴方法
CN108781262B (zh) 用于合成图像的方法和使用该方法的电子装置
US20160080934A1 (en) Terminal and processing method for head portrait of contact person
WO2017067485A1 (zh) 一种图片管理方法、装置及一种终端
WO2016131286A1 (zh) 联系人信息同步方法和装置
CN103761303A (zh) 一种图片的排列显示方法及装置
CN112084756B (zh) 会议文件生成方法、装置及电子设备
CN103533169A (zh) 一种基于移动终端电子名片的字段定位链接方法
CN111488477A (zh) 相册处理方法、装置、电子设备及存储介质
CN105872252A (zh) 一种图像处理的方法及装置
JP2018097580A (ja) 情報処理装置およびプログラム
CN106713700A (zh) 图像处理方法、装置和终端
CN103327163A (zh) 查找联系人信息的方法及其通信终端
CN106791091B (zh) 图像生成方法、装置和移动终端
WO2022068719A1 (zh) 图像显示方法、装置和电子设备
CN103353879B (zh) 图像处理方法及设备
US10365880B2 (en) Data processing apparatus, data processing method, and non-transitory computer readable medium
CN110458751B (zh) 一种基于粤剧图片的面部替换方法、设备及介质
CN108121693B (zh) 一种幻灯片美化方法及装置

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: 14895018

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 15319988

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2014895018

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014895018

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2014397825

Country of ref document: AU

Date of ref document: 20141023

Kind code of ref document: A

Ref document number: 2017101584

Country of ref document: RU

Kind code of ref document: A