WO2016134666A1 - 图像匹配发现好友的方法和装置 - Google Patents
图像匹配发现好友的方法和装置 Download PDFInfo
- Publication number
- WO2016134666A1 WO2016134666A1 PCT/CN2016/074650 CN2016074650W WO2016134666A1 WO 2016134666 A1 WO2016134666 A1 WO 2016134666A1 CN 2016074650 W CN2016074650 W CN 2016074650W WO 2016134666 A1 WO2016134666 A1 WO 2016134666A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- matching
- matched
- type
- identifier
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Definitions
- Embodiments of the present invention relate to communication technologies, and in particular, to a method and apparatus for image matching to discover a friend.
- one method is to recommend potential friends to the user according to various information such as an account number, a nickname, a phone number, a work unit, a hobby, and a recent activity filled out by the user.
- the client After discovering the potential friends of the user, the client presents the friend's account number, nickname, etc. to the user interface, and the user searches through the account number, nickname, etc., and then adds the friend.
- Another way is to scan the QR code generated by the friend, quickly get the information of the friend, and apply to add as a friend.
- the method in the prior art is single and has poor flexibility.
- the user In the second method, the user must obtain the QR code of the friend to be added as a friend, which is inflexible and is inconvenient for the user to send a friend.
- the embodiment of the invention provides a method and a device for image matching to find a friend, which can discover friends in a flexible and convenient manner.
- a first aspect of the present invention provides a method for image matching to discover a friend, including:
- the client receives a matching type of the image to be matched input by the user and the image to be matched;
- the client obtains matching parameters of the image to be matched by using a matching algorithm corresponding to the matching type of the image to be matched;
- the server Sending, by the client, the matching parameter of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm to the server, so that the server is configured according to the matching parameter of the image to be matched, Matching the matching type of the image to be matched and the identifier of the matching algorithm to match the image in the image library, and finding a target image that matches the image to be matched;
- the client receives the matching result returned by the server, and the matching result includes information of the matched user to which the target image belongs.
- the client adopts an image to be matched
- the matching algorithm corresponding to the matching type acquires matching parameters of the image to be matched, including:
- the client extracts a face feature of the image to be matched by using a matching algorithm corresponding to the face matching type.
- the client adopts an image to be matched
- the matching algorithm corresponding to the matching type acquires matching parameters of the image to be matched, including:
- the client extracts a color feature of the background of the image to be matched by using an algorithm corresponding to the background matching type.
- the client adopts an image to be matched
- the matching algorithm corresponding to the matching type acquires matching parameters of the image to be matched, including:
- the client extracts a texture feature of the image to be matched by using an algorithm corresponding to the location matching type.
- the matching parameter of the to-be-matched image further includes the shooting location information of the to-be-matched image.
- the method further includes:
- the client acquires the shooting location information of the image to be matched from the file header information of the image to be matched.
- the client adopts an image to be matched
- the matching algorithm corresponding to the matching type acquires matching parameters of the image to be matched, including:
- the client adopts an algorithm corresponding to the author matching type, and the to-be-matched Obtaining information of the author of the image to be matched in the file header information of the image.
- a second aspect of the present invention provides a method for image matching to discover a friend, including:
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm;
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and uses the image with successful matching as the target image;
- the server acquires the information of the user to which the target image belongs, generates a matching result according to the information of the user to which the target image belongs, and sends the matching result to the client.
- the identifier of the matching algorithm is the face matching
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including:
- the server extracts a face feature of the image in the image library by using a matching algorithm corresponding to the face matching type according to the matching type of the image to be matched and the identifier of the matching algorithm;
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and the image that is successfully matched is used as the target image, including:
- the server matches the face feature of the image to be matched with the face feature of the image in the image library, and uses the image with successful matching as the target image.
- the identifier of the matching algorithm is the background matching type.
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including:
- the server extracts an image in the image library by using a matching algorithm corresponding to the background matching type according to the matching type of the image to be matched and the identifier of the matching algorithm. Color characteristics of the background;
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and the image that is successfully matched is used as the target image, including:
- the server matches the color feature of the background of the image to be matched with the color feature of the background of the image in the image library, and uses the image with successful matching as the target image.
- the server acquires information about a user to which the target image belongs, according to the target image
- the information of the user generates a matching result
- the matching result is sent to the client, including:
- the server adds information of the user to which the target image belongs to the matching result.
- the identifier of the matching algorithm is the location matching type.
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including:
- the server extracts a texture feature of the image in the image library by using an algorithm corresponding to the location matching type according to the matching type of the image to be matched and the identifier of the matching algorithm;
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and the image that is successfully matched in the image library is used as the target image, and includes:
- the server matches the texture feature of the image to be matched with the texture feature of the image in the image library, and uses the image with successful matching as the target image.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the location matching type
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including:
- the server extracts, according to the matching type of the to-be-matched image and the identifier of the matching algorithm, an texture corresponding to the location matching type, and extracts an image of the image in the image library, and images from the image library. Obtaining shooting location information of an image in the image library in the file header information;
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and the image that is successfully matched is used as the target image, including:
- the server matches the texture feature and the shooting location information in the image to be matched with the texture feature and the shooting location information of the image in the image library, and uses the image with successful matching as the target image.
- the identifier of the matching algorithm is the author matching type.
- the server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including:
- the server obtains, according to the matching type of the to-be-matched image and the identifier of the matching algorithm, an algorithm corresponding to the author matching type, and obtains the image library from the file header information of the image in the image library.
- the information of the author of the image is a registered trademark of the author of the image.
- the server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and the image that is successfully matched is used as the target image, including:
- the server matches the information of the author of the image to be matched with the information of the author of the image in the image library, and uses the image with successful matching as the target image.
- a third aspect of the present invention provides a client, including:
- a receiving module configured to receive a matching type of the image to be matched input by the user and the image to be matched
- An obtaining module configured to use a matching calculation corresponding to a matching type of the image to be matched Obtaining a matching parameter of the image to be matched;
- a sending module configured to send, to the server, a matching parameter of the image to be matched, a matching type of the image to be matched, and an identifier of the matching algorithm, so that the server matches the matching parameter of the image to be matched Matching the matching type of the matching image and the identifier of the matching algorithm with the image in the image library to find a target image that matches the image to be matched;
- the receiving module is further configured to receive a matching result returned by the server, where the matching result includes information of the matched user to which the target image belongs.
- the acquiring module is specifically configured to: adopt the The matching algorithm corresponding to the face matching type extracts the facial features of the image to be matched.
- the acquiring module is specifically configured to: adopt An algorithm corresponding to the background matching type extracts a color feature of the background of the image to be matched.
- the acquiring module is specifically configured to: adopt An algorithm corresponding to the location matching type extracts texture features of the image to be matched.
- the matching parameter of the to-be-matched image further includes the shooting location information of the image to be matched.
- the acquiring module is further configured to: obtain, from the file header information of the image to be matched, location information of the image to be matched.
- the acquiring module is specifically configured to: adopt The algorithm of the author of the image to be matched is obtained from the file header information of the image to be matched.
- a fourth aspect of the present invention provides a server, including:
- a receiving module configured to receive a matching parameter of the image to be matched sent by the client, a matching type of the image to be matched, and a matching algorithm corresponding to the matching type of the image to be matched Identification
- An obtaining module configured to acquire, according to a matching type of the image to be matched and an identifier of the matching algorithm, a matching parameter of an image in an image library
- a matching module configured to match a matching parameter of the image to be matched with a matching parameter of an image in the image library, and use a successfully matched image as the target image;
- a sending module configured to acquire information about a user to which the target image belongs, generate a matching result according to the information of the user to which the target image belongs, and send the matching result to the client.
- the identifier of the matching algorithm is the face matching
- the acquiring module is specifically configured to: according to the matching type of the image to be matched and the identifier of the matching algorithm, extract the image database by using a matching algorithm corresponding to the face matching type The face features of the image;
- the matching module is specifically configured to: match a face feature of the image to be matched with a face feature of an image in the image library, and use a successfully matched image as the target image.
- the acquiring module is configured to: extract the image in the image library by using a matching algorithm corresponding to the background matching type according to the matching type of the image to be matched and the identifier of the matching algorithm. Color characteristics of the background;
- the matching module is specifically configured to: match a color feature of a background of the image to be matched with a color feature of a background of an image in the image library, and use a successfully matched image as the target image.
- the sending module is specifically configured to:
- the acquiring module is configured to: extract an image in the image library by using an algorithm corresponding to the location matching type according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the matching module is specifically configured to: match a texture feature of the image to be matched with a texture feature of an image in the image library, and use a successfully matched image as the target image.
- the identifier of the matching algorithm is the location matching type.
- An identifier of the corresponding matching algorithm where the acquiring module is specifically configured to: according to the matching type of the image to be matched and the identifier of the matching algorithm, extract an image in the image library by using an algorithm corresponding to the location matching type a texture feature, and acquiring shooting location information of an image in the image library from file header information of the image in the image library;
- the matching module is specifically configured to: match the texture feature and the shooting location information in the image to be matched with the texture feature and the shooting location information of the image in the image library, and use the successfully matched image as the target image.
- the identifier of the matching algorithm is the author matching type.
- An identifier of the matching algorithm where the acquiring module is specifically configured to: according to the matching type of the image to be matched and the identifier of the matching algorithm, adopt an algorithm corresponding to the author matching type, and use an image from the image library Obtaining information of the author of the image in the image library in the file header information;
- the matching module is specifically configured to: match the information of the author of the image to be matched with the information of the author of the image in the image library, and match the image with success As the target image.
- the client obtains a matching parameter of a to-be-matched image by using a matching algorithm corresponding to a matching type of the image to be matched, and then obtains a matching parameter of the image to be matched, and then And sending, to the server, the matching parameter, the matching type, and the identifier of the matching algorithm of the image to be matched, and the server matches the image in the image library according to the matching parameter, the matching type, and the identifier of the matching algorithm to find the image to be matched.
- the matching target image and the matching result returned to the client, the matching result includes the information of the user to which the matched target image belongs, and the user to which the target image belongs is a friend.
- the above method finds a friend by using image matching of the user's existing image resources, so that the user can find the friend.
- Embodiment 1 is a flowchart of a method for matching an image to find a friend according to Embodiment 1 of the present invention
- FIG. 2 is a flowchart of a method for matching an image to find a friend according to Embodiment 2 of the present invention
- FIG. 3 is a schematic structural diagram of a client according to Embodiment 3 of the present invention.
- FIG. 4 is a schematic structural diagram of a server according to Embodiment 4 of the present invention.
- FIG. 5 is a schematic structural diagram of a terminal according to Embodiment 5 of the present invention.
- FIG. 6 is a schematic structural diagram of a server according to Embodiment 6 of the present invention.
- FIG. 1 is a flowchart of a method for matching a friend to find an image according to a first embodiment of the present invention.
- the method provided by the embodiment is performed by a client, and the client may be an application installed on the terminal, as shown in FIG. 1 .
- the method of this embodiment may include the following steps:
- Step 101 The client receives a matching type of the image to be matched and the image to be matched input by the user.
- the user can select an image from the local image library of the terminal where the client is located as the image to be matched, or start the camera to take a photo as the image to be matched.
- the user can select a matching type of the image to be matched through a selection button on the user interface, and the matching types of the image to be matched include: a face matching type, a background matching type, a location matching type, and an author matching type.
- Step 102 The client obtains a matching parameter of the image to be matched by using a matching algorithm corresponding to the matching type of the image to be matched.
- each matching type corresponds to a different matching algorithm
- the client selects a matching algorithm corresponding to the matching type to obtain matching parameters of the image to be matched according to the matching type of the image to be matched, which will be specifically described below:
- the client uses the matching algorithm corresponding to the face matching type to extract the facial features of the image to be matched.
- the matching algorithm corresponding to the face matching type refers to the algorithm used to extract facial features.
- the commonly used methods for extracting facial features include: template matching based methods, singular value feature based methods, singular value based methods, local hold projection methods, Principal component method, elastic matching method, eigenface method (based on KL transform), artificial neural network method, support vector machine method, integral image feature method and probability model method.
- the client extracts the color feature of the background of the image to be matched by using an algorithm corresponding to the background matching type.
- the background of the image refers to the main color of the image
- the color feature of the image refers to the overall hue of the image, which is mixed according to a specified algorithm to obtain a primary color value.
- the algorithm corresponding to the background matching type refers to an algorithm used to extract the background feature of the image, and the commonly used method for extracting the background feature includes: pressing the image Prime color value clustering, color histogram peaking, etc.
- the client extracts the texture feature of the image to be matched by using an algorithm corresponding to the location matching type.
- a texture feature is a visual feature that reflects homogeneity in an image independent of color or brightness.
- the algorithm corresponding to the location matching type refers to the method used to extract the texture features of the image.
- the commonly used methods for extracting texture features include: autocorrelation function, Fourier transform, run length analysis, grayscale difference analysis, and gray level co-occurrence matrix analysis. .
- the matching parameter of the image to be matched includes not only the texture feature of the image to be matched, but also the shooting location information of the image to be matched, and the client is from the image to be matched.
- the location information of the image to be matched is obtained in the header information.
- the file header information of the image stores information of the shooting location of the image and the information of the author of the image, and the header information may further include information such as the time of the photographer, the brand model of the camera that captured the image, and the like.
- the file format of the image to be matched is the Exchangeable Image File (Exif)
- the data storage of the Exif format image is exactly the same as the JPEG format.
- Exif format is inserted in the JPEG format header.
- Image information including aperture, shutter, white balance, ISO, focus, date and time, shooting conditions, camera brand, model, color coding, sound recorded during shooting, and thumbnails.
- Exif JPEG+ shooting parameters.
- the client uses the algorithm corresponding to the author matching type to obtain the information of the author of the image to be matched from the file header information of the image to be matched.
- Step 103 The client sends the matching parameter of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm to the server, so that the server matches the matching parameter of the image to be matched, the matching type of the image to be matched, and the matching algorithm. Matches the image in the image library to find the target image that matches the image to be matched.
- the client After obtaining the matching parameter of the image to be matched, the client sends the matching parameter of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm to the server.
- the client can specifically send the matching parameters of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm in the following message format: application protocol header + matching type + upload data type + matching parameter + matching algorithm identifier + End or Not, where the application protocol header includes However, it is not limited to Hypertext Transfer Protocol (HTTP), Hyper Text Transfer Protocol over Secure Socket Layer (HTTPS).
- HTTP Hypertext Transfer Protocol
- HTTPS Hyper Text Transfer Protocol over Secure Socket Layer
- the upload data type is used to define the type of matching parameters that are uploaded.
- the matching parameter of the image to be matched is the facial feature of the image to be matched.
- the matching parameter of the image to be matched is the background feature of the image to be matched.
- the matching parameter of the image to be matched is the texture feature of the image to be matched, or the matching parameter of the image to be matched is the texture feature and the shooting location information of the image to be matched.
- the matching type of the image to be matched is the author matching type
- the matching parameter of the image to be matched is the information of the author of the image to be matched.
- the matching type of the image to be matched is other types, the matching parameter of the image to be matched is the entire image.
- the server After receiving the matching parameter of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm, the server selects the same matching algorithm as the client to extract the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm. Match the parameters, and then match the matching parameters of the image to be matched with the matching parameters of the image in the image library, and use the image with successful matching as the target image.
- the matching parameter of the image to be matched is extracted according to the matching type.
- the client only needs to send the matching parameter of the image to be matched to the server, and the server performs the image according to the matching parameter of the image to be matched.
- Matching without sending the entire image to the server, since the matching parameters of the image to be matched are smaller than the entire image, the occupied network resources can be saved.
- Step 104 The client receives a matching result returned by the server, where the matching result includes information of the user to which the matched target image belongs.
- the matching result returned by the server to the client includes information of the user to which the matched target image belongs, and the user to which the target image belongs is a friend, and the information of the user to which the target image belongs includes: the user's account number, nickname, and user image.
- the server When there are multiple target images, the server generates a list of user information and sends the list of user information to the client. After the client receives the matching result, it is presented to the user in the form of a list or other forms, and the user can add the desired user as a friend by selecting the Add button.
- the client obtains the matching parameter of the image to be matched by using the matching algorithm corresponding to the matching type of the image to be matched, and then matches the matching parameter of the image to be matched.
- the identifier of the type and the matching algorithm is sent to the server, so that the server matches the image in the image library according to the matching parameter, the matching type and the identifier of the matching algorithm of the image to be matched, finds the target image that matches the image to be matched, and provides the target image to the client.
- the matching result returned by the terminal, the matching result includes the information of the user to which the matched target image belongs, and the user to which the target image belongs is a friend.
- the above method finds a friend by using image matching of the user's existing image resources, so that the user can find the friend.
- FIG. 2 is a flowchart of a method for matching an image to find a friend according to a second embodiment of the present invention. The embodiment is described from the perspective of a server. As shown in FIG. 2, the method provided in this embodiment may include the following steps:
- Step 201 The server receives the matching parameter of the to-be-matched image sent by the client, the matching type of the image to be matched, and the identifier of the matching algorithm corresponding to the matching type of the image to be matched.
- Step 202 The server acquires matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the client sends the identifier of the matching algorithm corresponding to the matching type of the image to be matched and the matching type of the image to be matched to the server, so that the server uses the same matching algorithm to extract the matching parameters of the image in the image library.
- the identifier of the matching algorithm is the identifier of the matching algorithm corresponding to the face matching type
- the server obtains the matching of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the parameter is specifically: the server extracts the facial features of the image in the image library by using a matching algorithm corresponding to the face matching type according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the identifier of the matching algorithm is the identifier of the matching algorithm corresponding to the background matching type
- the server obtains the matching of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the parameter is specifically: the server extracts the color feature of the background of the image in the image library by using a matching algorithm corresponding to the background matching type according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the identifier of the matching algorithm is The identifier of the matching algorithm corresponding to the location matching type
- the server obtains the matching parameter of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, specifically: the matching type of the image according to the image to be matched and the identifier of the matching algorithm
- the texture of the image in the image library is extracted by an algorithm corresponding to the location matching type.
- the server extracts the texture of the image in the image library by using an algorithm corresponding to the location matching type according to the matching type of the image to be matched and the identifier of the matching algorithm, and acquires the image in the image library from the file header information of the image in the image library. Location information.
- the identifier of the matching algorithm is the identifier of the matching algorithm corresponding to the author matching type
- the server obtains the matching of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the parameter is specifically: the server obtains the information of the author of the image in the image library from the file header information of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm.
- Step 203 The server matches the matching parameter of the image to be matched with the matching parameter of the image in the image library, and uses the image with successful matching as the target image.
- the server matches the facial features of the image to be matched with the facial features of the image in the image library, and the image with successful matching is taken as the target image.
- the server matches the color feature of the background of the image to be matched with the color feature of the background of the image in the image library, and uses the image with successful matching as the target image.
- the server matches the texture feature of the image to be matched with the texture feature of the image in the image library, and uses the image with successful matching as the target image.
- the server matches the texture feature and the shooting location information in the image to be matched with the texture feature and the shooting location information of the image in the image library, and uses the image with successful matching as the target image.
- the server matches the information of the author of the image to be matched with the information of the author of the image in the image library, and the image with successful matching is taken as the target image.
- Step 204 The server acquires information about the user to which the target image belongs, generates a matching result according to the information of the user to which the target image belongs, and sends the matching result to the client.
- the server After matching the target image, the server acquires the information of the user to which the target image belongs.
- the matching type is the face matching type, the location matching type, and the author matching type
- the server sends the information of the user to which the target image belongs to the client.
- the matching type is the background matching type
- the server obtains the information of the user to which the target image belongs, and determines whether the number of images matching the image to be matched in the image of the user to which the target image belongs is greater than a preset threshold, if the target image belongs to If the number of images matching the image to be matched in the image of the user is greater than the threshold, the server adds the information of the user to which the target image belongs to the matching result, that is, the user to which the target image belongs and the plurality of images to be matched.
- the server uses the user as a friend. For example, if the threshold is 10, if the color feature of more than 10 images and the color feature of the image to be matched differ within plus or minus 3 of the image uploaded by a user, the user is determined to be a friend, and the user's information is determined. Add to the matching result. According to this rule, all users who meet the conditions are found out.
- the server receives the matching parameter of the matching parameter, the matching type, and the matching type of the matching type of the image to be matched sent by the client, and obtains the image database according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the user's information generates a matching result and sends the matching result to the client.
- the above method finds a friend by using image matching of the user's existing image resources, so that the user can find the friend.
- FIG. 3 is a schematic structural diagram of a client according to Embodiment 3 of the present invention.
- the client provided in this embodiment includes: a receiving module 11, an obtaining module 12, and a sending module 13.
- the receiving module 11 is configured to receive a matching type of the image to be matched and the image to be matched input by the user;
- the obtaining module 12 is configured to acquire a matching parameter of the image to be matched by using a matching algorithm corresponding to the matching type of the image to be matched;
- the sending module 13 is configured to send, to the server, the matching parameter of the image to be matched, the matching type of the image to be matched, and the identifier of the matching algorithm, so that the server matches the matching parameter of the image to be matched, Matching the matching type of the image to be matched and the identifier of the matching algorithm to the image in the image library to find the image to be matched Matching target image;
- the receiving module 11 is further configured to receive a matching result returned by the server, where the matching result includes information of the matched user to which the target image belongs.
- the acquiring module 12 is specifically configured to: extract a facial feature of the image to be matched by using a matching algorithm corresponding to the face matching type.
- the acquiring module 12 is specifically configured to: extract, by using an algorithm corresponding to the background matching type, a color feature of a background of the image to be matched.
- the acquiring module 12 is specifically configured to: extract an texture feature of the image to be matched by using an algorithm corresponding to the location matching type.
- the matching parameter of the image to be matched further includes the shooting location information of the image to be matched, and the acquiring module 12 is further configured to: obtain the image to be matched from the file header information of the image to be matched. Location information.
- the acquiring module 12 is specifically configured to: obtain the to-be-obtained from the file header information of the to-be-matched image by using an algorithm corresponding to the author matching type Match the image of the author of the image.
- the client in this embodiment can be used to perform the method in the first embodiment.
- the specific implementation and technical effects are similar, and details are not described herein again.
- FIG. 4 is a schematic structural diagram of a server according to Embodiment 4 of the present invention.
- the server provided in this embodiment includes: a receiving module 21, an obtaining module 22, a matching module 23, and a sending module 23.
- the receiving module 21 is configured to receive, by the client, a matching parameter of the image to be matched, a matching type of the image to be matched, and an identifier of a matching algorithm corresponding to the matching type of the image to be matched.
- the obtaining module 22 is configured to acquire matching parameters of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm;
- the matching module 23 is configured to match the matching parameter of the image to be matched with the matching parameter of the image in the image library, and use the image with successful matching as the target image;
- the sending module 24 is configured to acquire information about a user to which the target image belongs, according to the The information of the user to which the target image belongs generates a matching result, and the matching result is sent to the client.
- the identifier of the matching algorithm is an identifier of the matching algorithm corresponding to the face matching type
- the acquiring module 22 is specifically configured to: according to the image to be matched
- the matching type and the identifier of the matching algorithm are used to extract the facial features of the image in the image library by using a matching algorithm corresponding to the face matching type.
- the matching module 23 is specifically configured to: match a facial feature of the image to be matched with a facial feature of an image in the image library, and use a successfully matched image as the target image.
- the identifier of the matching algorithm is the identifier of the matching algorithm corresponding to the background matching type
- the obtaining module 22 is specifically configured to: according to the image to be matched Matching type and identifier of the matching algorithm, and using a matching algorithm corresponding to the background matching type to extract a color feature of a background of an image in the image library.
- the matching module 23 is specifically configured to: match a color feature of a background of the image to be matched with a color feature of a background of an image in the image library, and use a successfully matched image as the target image.
- the sending module 24 is specifically configured to: acquire information about a user to which the target image belongs; and determine an image of the user to which the target image belongs. Whether the number of images matching the image to be matched is greater than a preset threshold; if the number of images matching the image to be matched in the image of the user to which the target image belongs is greater than the threshold, the target is The information of the user to which the image belongs is added to the matching result.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the location matching type
- the acquiring module 22 is specifically configured to: according to the image to be matched
- the matching type and the identifier of the matching algorithm extract the texture features of the image in the image library by using an algorithm corresponding to the location matching type.
- the matching module 23 is specifically configured to: match the texture feature of the image to be matched with the texture feature of the image in the image library, and use the image with successful matching as the target image.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the location matching type
- the acquiring module 22 Specifically, according to the matching type of the image to be matched and the identifier of the matching algorithm, an algorithm corresponding to the location matching type is used to extract a texture feature of an image in the image library, and from the image library.
- the shooting location information of the image in the image library is obtained from the file header information of the image.
- the matching module 23 is specifically configured to: match the texture feature and the shooting location information in the image to be matched with the texture feature and the shooting location information of the image in the image library, and match the successfully matched image. As the target image.
- the identifier of the matching algorithm is the identifier of the matching algorithm corresponding to the author matching type
- the acquiring module 22 is specifically configured to: according to the image to be matched
- the matching type and the identifier of the matching algorithm are obtained by using an algorithm corresponding to the author matching type, and acquiring information of the author of the image in the image library from the file header information of the image in the image library.
- the matching module 23 is specifically configured to: match the information of the author of the image to be matched with the information of the author of the image in the image library, and use the image with successful matching as the target image.
- the server in this embodiment may be used to perform the method in the second embodiment.
- the specific implementation manners and technical effects are similar, and details are not described herein again.
- FIG. 5 is a schematic structural diagram of a terminal according to Embodiment 5 of the present invention.
- the terminal 300 provided in this embodiment includes: a processor 31, a memory 32, a communication interface 33, and a communication bus 34.
- 32 and communication interface 33 are coupled to processor 31 via communication bus 34 for storing computer instructions, communication interface 33 for communicating with other devices, and processor 31 for executing computer instructions stored in memory 32 for execution The method described below:
- the matching algorithm corresponding to the matching type of the image to be matched is used to obtain the matching parameter of the image to be matched, including: matching with the face A matching algorithm corresponding to the type extracts a face feature of the image to be matched.
- the matching algorithm corresponding to the matching type of the image to be matched is used to obtain the matching parameter of the image to be matched, including: adopting a matching type with the background Corresponding algorithm extracts color features of the background of the image to be matched.
- the matching algorithm corresponding to the matching type of the to-be-matched image acquires matching parameters of the image to be matched, including: adopting a matching type with the location Corresponding algorithm extracts texture features of the image to be matched.
- the matching parameter of the image to be matched further includes the shooting location information of the image to be matched, and the processor 31 is further configured to: obtain the to-be-matched from the file header information of the image to be matched. The location of the image.
- the matching algorithm corresponding to the matching type of the image to be matched is used to obtain the matching parameter of the image to be matched, including: adopting a matching type with the author Corresponding algorithm acquires information of the author of the image to be matched from the header information of the image to be matched.
- the terminal in this embodiment can be used to perform the method in the first embodiment.
- the specific implementation manners and technical effects are similar, and details are not described herein again.
- FIG. 6 is a schematic structural diagram of a server according to Embodiment 6 of the present invention.
- the server 400 provided in this embodiment includes: a processor 41, a memory 42, a communication interface 43, and a communication bus 44. 42 and communication interface 43 are coupled to processor 41 via communication bus 44 for storing computer instructions, communication port 43 for communicating with other devices, and processor 41 for executing computer instructions stored in memory 42 for execution The method described below:
- Matching parameters of the matching parameter of the image to be matched with the image of the image library Performing matching, and matching the successfully image as the target image;
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the face matching type. Acquiring the matching parameter of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including: according to the matching type of the image to be matched and the identifier of the matching algorithm, adopting A matching algorithm corresponding to the face matching type extracts a face feature of the image in the image library.
- Matching the matching parameter of the image to be matched with the matching parameter of the image in the image library, and using the image that is successfully matched as the target image includes: selecting a face feature of the image to be matched The face features of the images in the image library are matched, and the image with successful matching is used as the target image.
- the identifier of the matching algorithm is an identifier of the matching algorithm corresponding to the background matching type. Acquiring the matching parameter of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including: according to the matching type of the image to be matched and the identifier of the matching algorithm, adopting A matching algorithm corresponding to the background matching type extracts a color feature of the background of the image in the image library.
- Matching the matching parameter of the image to be matched with the matching parameter of the image in the image library, and using the image with the matching as the target image includes: color feature of the background of the image to be matched The color features of the background of the image in the image library are matched, and the image with successful matching is used as the target image.
- the matching type of the image to be matched is the background matching type
- the acquiring information of the user to which the target image belongs generating a matching result according to the information of the user to which the target image belongs, and transmitting the matching result to the Determining, by the client, the information of the user to which the target image belongs, and determining whether the number of images matching the image to be matched in the image of the user to which the target image belongs is greater than a preset threshold; If the number of images matching the image to be matched in the image of the user to which the image belongs is greater than the threshold, information of the user to which the target image belongs is added to the matching result.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the location matching type.
- the matching parameter includes: extracting a texture feature of the image in the image library by using an algorithm corresponding to the location matching type according to the matching type of the image to be matched and the identifier of the matching algorithm.
- the texture feature is matched with the texture feature of the image in the image library, and the image with successful matching is used as the target image.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the location matching type.
- Acquiring the matching parameter of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm including: according to the matching type of the image to be matched and the identifier of the matching algorithm, adopting An algorithm corresponding to the location matching type extracts texture features of the image in the image library, and acquires shooting location information of the image in the image library from file header information of the image in the image library.
- Matching the matching parameter of the image to be matched with the matching parameter of the image in the image library, and using the image with successful matching as the target image includes: performing texture feature and shooting in the image to be matched The location information is matched with the texture feature and the shooting location information of the image in the image library, and the image with successful matching is used as the target image.
- the identifier of the matching algorithm is an identifier of a matching algorithm corresponding to the author matching type. Acquiring the matching parameter of the image in the image library according to the matching type of the image to be matched and the identifier of the matching algorithm, including: according to the matching type of the image to be matched and the identifier of the matching algorithm, adopting The algorithm corresponding to the author matching type acquires information of the author of the image in the image library from the file header information of the image in the image library.
- Matching the matching parameter of the image to be matched with the matching parameter of the image in the image library, and using the image that is successfully matched as the target image includes: information about the author of the image to be matched and the The information of the author of the image of the image in the image library is matched, and the image with the matching success is taken as the target image.
- the server in this embodiment may be used to perform the method in the second embodiment.
- the specific implementation manners and technical effects are similar, and details are not described herein again.
- the aforementioned program can be stored In a computer readable storage medium.
- the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
- Studio Devices (AREA)
Abstract
本发明实施例提供一种图像匹配发现好友的方法和装置，客户端通过接收用户输入的待匹配图像的匹配类型，采用与待匹配图像的匹配类型对应的匹配算法获取待匹配图像的匹配参数，然后，将待匹配图像的匹配参数、匹配类型和匹配算法的标识发送给服务器，服务器根据待匹配图像的匹配参数、匹配类型和匹配算法的标识与图像库中的图像进行匹配，找到与待匹配图像匹配的目标图像，并向客户端返回的匹配结果，匹配结果中包括匹配到的目标图像所属的用户的信息，目标图像所属的用户即为好友。上述方法通过利用用户已有的图像资源进行图像匹配找到好友，方便用户发现好友。
Description
本发明实施例涉及通信技术，尤其涉及一种图像匹配发现好友的方法和装置。
随着移动终端的发展，社交迅猛发展，重要性日益提升，如何通过合理的引导为用户建立社交关系，成为各大厂商争相挖掘的重点，业界知名应用，都将发现好友单独作为产品的一个主入口，发现好友的手段也层出不穷。
现有技术中，一种方法是根据用户填写的账号、昵称、电话号码、工作单位、兴趣爱好、近期活动等各种信息为用户推荐潜在的好友。客户端在发现用户潜在的好友之后，将好友的账号、昵称等呈现到用户界面上，用户通过账号、昵称等进行搜索，继而添加好友。另一种方式是扫描好友生成的二维码，快速获得好友的信息，申请添加为好友。
现有技术中的方法单一，灵活性差。第二种方式中，用户必须获取到朋友的二维码才能加为好友，灵活性差，不便于用户发下好友。
发明内容
本发明实施例提供一种图像匹配发现好友的方法和装置，能够灵活方便的发现好友。
本发明第一方面提供一种图像匹配发现好友的方法，包括：
客户端接收用户输入的待匹配图像和所述待匹配图像的匹配类型；
所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数；
所述客户端将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像匹配的目标图像；
所述客户端接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
结合本发明第一方面，在本发明第一方面的第一种可能的实现方式中，当所述待匹配图像的匹配类型为人脸匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：
所述客户端采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
结合本发明第一方面，在本发明第一方面的第二种可能的实现方式中，当所述待匹配图像的匹配类型为背景匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：
所述客户端采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
结合本发明第一方面，在本发明第一方面的第三种可能的实现方式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：
所述客户端采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。
结合本发明第一方面的第三种可能的实现方式，在本发明第一方面的第四种可能的实现方式中，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，则所述方法还包括：
所述客户端从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
结合本发明第一方面，在本发明第一方面的第五种可能的实现方式中，当所述待匹配图像的匹配类型为作者匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：
所述客户端采用与所述作者匹配类型对应的算法，从所述待匹配
图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
本发明第二方面提供一种图像匹配发现好友的方法，包括：
服务器接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像；
所述服务器获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
结合本发明第二方面，在本发明第二方面的第一种可能的实现方式中，当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：
所述服务器将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第二方面，在本发明第二方面的第二种可能的实现方式中，当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像
的背景的颜色特征；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：
所述服务器将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第二方面第二种可能的实现方式，在本发明第二方面的第三种可能的实现方式中，所述服务器获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，将所述匹配结果发送给所述客户端，包括：
所述服务器获取所述目标图像所属的用户的信息；
所述服务器判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数是否大于预先设置的阈值；
若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则所述服务器将所述目标图像所属的用户的信息添加到所述匹配结果中。
结合本发明第二方面，在本发明第二方面的第四种可能的实现方式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将所述图像库中的匹配成功的图像作为所述目标图像，包括：
所述服务器将所述待匹配图像的纹理特征与所述图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第二方面，在本发明第二方面的第五种可能的实现方
式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：
所述服务器将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第二方面，在本发明第二方面的第六种可能的实现方式中，当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识；
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：
所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息；
所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：
所述服务器将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为所述目标图像。
本发明第三方面提供一种客户端，包括：
接收模块，用于接收用户输入的待匹配图像和所述待匹配图像的匹配类型；
获取模块，用于采用与所述待匹配图像的匹配类型对应的匹配算
法获取所述待匹配图像的匹配参数；
发送模块，用于将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像匹配的目标图像；
所述接收模块，还用于接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
结合本发明第三方面，在本发明第三方面的第一种可能的实现方式中，当所述待匹配图像的匹配类型为人脸匹配类型时，所述获取模块具体用于：采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
结合本发明第三方面，在本发明第三方面的第二种可能的实现方式中，当所述待匹配图像的匹配类型为背景匹配类型时，所述获取模块具体用于：采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
结合本发明第三方面，在本发明第三方面的第三种可能的实现方式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述获取模块具体用于：采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。
结合本发明第三方面的第三种可能的实现方式，在本发明第三方面的第四种可能的实现方式中，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，所述获取模块还用于：从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
结合本发明第三方面，在本发明第三方面的第五种可能的实现方式中，当所述待匹配图像的匹配类型为作者匹配类型时，所述获取模块具体用于：采用与所述作者匹配类型对应的算法，从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
本发明第四方面提供一种服务器，包括：
接收模块，用于接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法
的标识；
获取模块，用于根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；
匹配模块，用于将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像；
发送模块，用于获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
结合本发明第四方面，在本发明第四方面的第一种可能的实现方式中，当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征；
所述匹配模块具体用于：将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第四方面，在本发明第四方面的第二种可能的实现方式中，当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像的背景的颜色特征；
所述匹配模块具体用于：将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第四方面的第二种可能的实现方式，在本发明第四方面的第三种可能的实现方式中，所述发送模块具体用于：
获取所述目标图像所属的用户的信息；
判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的
图像个数是否大于预先设置的阈值；
若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则将所述目标图像所属的用户的信息添加到所述匹配结果中。
结合本发明第四方面，在本发明第四方面的第四种可能的实现方式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征；
所述匹配模块具体用于：将所述待匹配图像的纹理特征与所述图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第四方面，在本发明第四方面的第五种可能的实现方式中，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息；
所述匹配模块具体用于：将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
结合本发明第四方面，在本发明第四方面的第六种可能的实现方式中，当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息；
所述匹配模块具体用于：将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像
作为所述目标图像。
本发明实施例提供的图像匹配发现好友的方法和装置，客户端通过接收用户输入的待匹配图像的匹配类型，采用与待匹配图像的匹配类型对应的匹配算法获取待匹配图像的匹配参数，然后，将待匹配图像的匹配参数、匹配类型和匹配算法的标识发送给服务器，服务器根据待匹配图像的匹配参数、匹配类型和匹配算法的标识与图像库中的图像进行匹配，找到与待匹配图像匹配的目标图像，并向客户端返回的匹配结果，匹配结果中包括匹配到的目标图像所属的用户的信息，目标图像所属的用户即为好友。上述方法通过利用用户已有的图像资源进行图像匹配找到好友，方便用户发现好友。
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例一提供的图像匹配发现好友的方法的流程图；
图2为本发明实施例二提供的图像匹配发现好友的方法的流程图；
图3为本发明实施例三提供的一种客户端的结构示意图；
图4为本发明实施例四提供的一种服务器的结构示意图；
图5为本发明实施例五提供的一种终端的结构示意图；
图6为本发明实施例六提供的一种服务器的结构示意图。
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是
全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
图1为本发明实施例一提供的图像匹配发现好友的方法的流程图，本实施例的提供的方法由客户端执行，该客户端具体可以为终端上安装的应用(Application)，如图1所示，本实施例的方法可以包括以下步骤：
步骤101、客户端接收用户输入的待匹配图像和待匹配图像的匹配类型。
用户可以从客户端所在的终端的本地图像库中选择一张图像作为待匹配的图像，或者，启动照相机拍摄一张照片作为待匹配的图像。用户可以通过用户界面上的选择按钮选择待匹配图像的匹配类型，待匹配图像的匹配类型包括：人脸匹配类型、背景匹配类型、地点匹配类型和作者匹配类型等。
步骤102、客户端采用与待匹配图像的匹配类型对应的匹配算法获取待匹配图像的匹配参数。
本实施例中，每种匹配类型都对应不同的匹配算法，客户端根据待匹配图像的匹配类型，选择与匹配类型对应的匹配算法获取待匹配图像的匹配参数，以下将具体说明：
当待匹配图像的匹配类型为人脸匹配类型时，客户端采用与人脸匹配类型对应的匹配算法，提取待匹配图像的人脸特征。人脸匹配类型对应的匹配算法是指提取人脸特征使用的算法，提取人脸特征常用的方法包括：基于模板匹配的方法、基于奇异值特征方法、基于奇异值特征方法、局部保持投影方法、主成分分方法、弹性匹配方法、特征脸法(基于KL变换)、人工神经网络法、支持向量机法、基于积分图像特征法和基于概率模型法等。
当待匹配图像的匹配类型为背景匹配类型时，客户端采用与背景匹配类型对应的算法，提取待匹配图像的背景的颜色特征。图像的背景是指图像的主色，图像的颜色特征是指对图像的整体色调，按照指定的算法混合得到一个主色值。背景匹配类型对应的算法是指提取图像的背景特征所使用的算法，常用的提取背景特征的方法包括：按像
素颜色值聚类、颜色直方图取峰值等。
当待匹配图像的匹配类型为地点匹配类型时，客户端采用与地点匹配类型对应的算法，提取待匹配图像的纹理特征。纹理特征是一种不依赖于颜色或亮度的反映图像中同质现象的视觉特征。地点匹配类型对应的算法是指提取图像的纹理特征所使用的方法，提取纹理特征常用的方法包括：自相关函数、傅里叶变换、行程长度分析、灰度差分分析和灰度共生矩阵分析等。
可选地，当待匹配图像的匹配类型为地点匹配类型时，待匹配图像的匹配参数不仅包括待匹配图像的纹理特征，还包括待匹配图像的拍摄地点信息，则客户端从待匹配图像的文件头信息中获取待匹配图像的拍摄地点信息。图像的文件头信息中存储有图像的拍摄地点的信息以及图像的拍摄作者的信息，文件头信息中还可以包括拍摄人时间、拍摄图像的相机的品牌型号等信息。例如，当待匹配图像的文件格式为可交换文件格式(Exchangeable Image File，简称Exif)时，Exif格式图像的数据存储与JPEG格式是完全相同的，实际上Exif格式就是在JPEG格式头部插入了图像的信息，包括拍摄时的光圈、快门、白平衡、ISO、焦距、日期时间、拍摄条件以及相机品牌、型号、色彩编码、拍摄时录制的声音以及缩略图等。简单地说，Exif＝JPEG+拍摄参数。
当待匹配图像的匹配类型为作者匹配类型时，客户端采用与作者匹配类型对应的算法，从待匹配图像的文件头信息中获取待匹配图像的拍摄作者的信息。
步骤103、客户端将待匹配图像的匹配参数、待匹配图像的匹配类型和匹配算法的标识发送给服务器，以使服务器根据待匹配图像的匹配参数、待匹配图像的匹配类型和匹配算法的标识与图像库中的图像进行匹配，找到与待匹配图像匹配的目标图像。
客户端在获取到待匹配图像的匹配参数之后，将待匹配图像的匹配参数、待匹配图像的匹配类型和匹配算法的标识发送给服务器。客户端具体可以通过如下报文格式发送待匹配图像的匹配参数、待匹配图像的匹配类型和匹配算法的标识：应用协议头+匹配类型+上传数据类型+匹配参数+匹配算法的标识+End or Not，其中，应用协议头包括
但不限于超文本传输协议(HyperText Transfer Protocol，简称HTTP)、基于安全套接层之上的超文本传输协议)Hyper Text Transfer Protocol over Secure Socket Layer，简称HTTPS)等。上传数据类型用于定义上传的匹配参数的类型。
本实施例中，当待匹配图像的匹配类型为人脸匹配类型时，待匹配图像的匹配参数为待匹配图像的人脸特征。当待匹配图像的匹配类型为背景匹配类型时，待匹配图像的匹配参数为待匹配图像的背景特征。当待匹配图像的匹配类型为地点匹配类型时，待匹配图像的匹配参数为待匹配图像的纹理特征，或者，待匹配图像的匹配参数为待匹配图像的纹理特征和拍摄地点信息。当待匹配图像的匹配类型为作者匹配类型时，待匹配图像的匹配参数为待匹配图像的拍摄作者的信息。当待匹配图像的匹配类型为其他类型时，待匹配图像的匹配参数为整幅图像。
服务器收到待匹配图像的匹配参数、待匹配图像的匹配类型和匹配算法的标识之后，根据待匹配图像的匹配类型和匹配算法的标识选择与客户端相同的匹配算法提取图像库中的图像的匹配参数，然后，将待匹配图像的匹配参数与图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为目标图像。
本实施例的方法中，通过根据匹配类型提取待匹配图像的匹配参数，大多数情况下，客户端只需要将待匹配图像的匹配参数发送给服务器，由服务器根据待匹配图像的匹配参数进行图像匹配，而不需要将整幅图像发送给服务器，由于待匹配图像的匹配参数比整幅图像小，从而可以节省占用的网络资源。
步骤104、客户端接收服务器返回的匹配结果，匹配结果中包括匹配到的目标图像所属的用户的信息。
服务器向客户端返回的匹配结果中包括匹配到的目标图像所属的用户的信息，目标图像所属的用户即为好友，目标图像所属的用户的信息包括：用户的账号、昵称和用户的图像等。当目标图像为多个时，服务器会生成用户信息列表，将用户信息列表发送给客户端。客户端收到匹配结果后，以列表的形式或其他形式展现给用户，用户可以通过选择添加按钮将需要的用户添加为好友。
本实施例中，客户端通过接收用户输入的待匹配图像的匹配类型，采用与待匹配图像的匹配类型对应的匹配算法获取待匹配图像的匹配参数，然后，将待匹配图像的匹配参数、匹配类型和匹配算法的标识发送给服务器，以使服务器根据待匹配图像的匹配参数、匹配类型和匹配算法的标识与图像库中的图像进行匹配，找到与待匹配图像匹配的目标图像，并向客户端返回的匹配结果，匹配结果中包括匹配到的目标图像所属的用户的信息，目标图像所属的用户即为好友。上述方法通过利用用户已有的图像资源进行图像匹配找到好友，方便用户发现好友。
图2为本发明实施例二提供的图像匹配发现好友的方法的流程图，本实施例从服务器的角度描述，如图2所示，本实施例提供的方法可以包括以下步骤：
步骤201、服务器接收客户端发送的待匹配图像的匹配参数、待匹配图像的匹配类型和待匹配图像的匹配类型对应的匹配算法的标识。
步骤202、服务器根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数。
客户端将待匹配图像的匹配类型和待匹配图像的匹配类型对应的匹配算法的标识发送给服务器，是为了使服务器采用相同的匹配算法提取图像库中的图像的匹配参数。
当待匹配图像的匹配类型为人脸匹配类型时，匹配算法的标识为人脸匹配类型对应的匹配算法的标识，服务器根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数，具体为：服务器根据待匹配图像的匹配类型和匹配算法的标识，采用人脸匹配类型对应的匹配算法提取图像库中的图像的人脸特征。
当待匹配图像的匹配类型为背景匹配类型时，匹配算法的标识为背景匹配类型对应的匹配算法的标识，服务器根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数，具体为：服务器根据待匹配图像的匹配类型和匹配算法的标识，采用背景匹配类型对应的匹配算法提取图像库中的图像的背景的颜色特征。
当待匹配图像的匹配类型为地点匹配类型时，匹配算法的标识为
地点匹配类型对应的匹配算法的标识，服务器根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数，具体为：服务器根据待匹配图像的匹配类型和匹配算法的标识，采用与地点匹配类型对应的算法提取图像库中的图像的纹理。或者，服务器根据待匹配图像的匹配类型和匹配算法的标识，采用地点匹配类型对应的算法提取图像库中的图像的纹理，并从图像库中的图像的文件头信息中获取图像库中的图像的拍摄地点信息。
当待匹配图像的匹配类型为作者匹配类型时，匹配算法的标识为作者匹配类型对应的匹配算法的标识，服务器根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数，具体为：服务器根据待匹配图像的匹配类型和匹配算法的标识，采用作者匹配类型对应的算法，从图像库中的图像的文件头信息中获取图像库中的图像的拍摄作者的信息。
步骤203、服务器将待匹配图像的匹配参数与图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像。
当待匹配图像的匹配类型为人脸匹配类型时，服务器将待匹配图像的人脸特征与图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为目标图像。
当待匹配图像的匹配类型为背景匹配类型时，服务器将待匹配图像的背景的颜色特征与图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为目标图像。
当待匹配图像的匹配类型为地点匹配类型时，服务器将待匹配图像的纹理特征与图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为目标图像。或者，服务器将待匹配图像中的纹理特征和拍摄地点信息，与图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为目标图像。
当待匹配图像的匹配类型为作者匹配类型时，服务器将待匹配图像的拍摄作者的信息与图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为目标图像。
步骤204、服务器获取目标图像所属的用户的信息，根据目标图像所属的用户的信息生成匹配结果，并将匹配结果发送给客户端。
服务器在匹配到目标图像之后，获取目标图像所属的用户的信息，当匹配类型为人脸匹配类型、地点匹配类型和作者匹配类型时，服务器之间将目标图像所属的用户的信息发送给客户端。当匹配类型为背景匹配类型时，服务器获取到目标图像所属的用户的信息之后，判断目标图像所属的用户的图像中与待匹配图像匹配的图像个数是否大于预先设置的阈值，若目标图像所属的用户的图像中与待匹配图像匹配的图像个数大于该阈值，则服务器将目标图像所属的用户的信息添加到匹配结果中，也就是说目标图像所属的用户与有多张图像与待匹配图像匹配时，服务器才将该用户作为好友。例如，该阈值为10，那么某个用户上传的图像中，有10张以上图像的颜色特征和待匹配图像的颜色特征相差在正负3以内，则确定该用户为好友，将该用户的信息添加到匹配结果中。按照这个规则，将所有满足条件的用户找出来。
本实施例中，服务器接收客户端发送的待匹配图像的匹配参数、匹配类型和待匹配图像的匹配类型对应的匹配算法的标识，根据待匹配图像的匹配类型和匹配算法的标识，获取图像库中的图像的匹配参数，将待匹配图像的匹配参数与图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为目标图像，最后获取目标图像所属的用户的信息，根据目标图像所属的用户的信息生成匹配结果，并将匹配结果发送给客户端。上述方法通过利用用户已有的图像资源进行图像匹配找到好友，方便用户发现好友。
图3为本发明实施例三提供的一种客户端的结构示意图，如图3所示，本实施例提供的客户端包括：接收模块11、获取模块12和发送模块13。
其中，接收模块11，用于接收用户输入的待匹配图像和所述待匹配图像的匹配类型；
获取模块12，用于采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数；
发送模块13，用于将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像
匹配的目标图像；
所述接收模块11，还用于接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
当所述待匹配图像的匹配类型为人脸匹配类型时，所述获取模块12具体用于：采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
当所述待匹配图像的匹配类型为背景匹配类型时，所述获取模块12具体用于：采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
当所述待匹配图像的匹配类型为地点匹配类型时，所述获取模块12具体用于：采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。可选的，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，所述获取模块12还用于：从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
当所述待匹配图像的匹配类型为作者匹配类型时，所述获取模块12具体用于：采用与所述作者匹配类型对应的算法，从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
本实施例的客户端，可用于执行实施例一的方法，具体实现方式和技术效果类似，这里不再赘述。
图4为本发明实施例四提供的一种服务器的结构示意图，如图4所示，本实施例提供的服务器包括：接收模块21、获取模块22、匹配模块23和发送模块23。
其中，接收模块21，用于接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法的标识；
获取模块22，用于根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；
匹配模块23，用于将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像；
发送模块24，用于获取所述目标图像所属的用户的信息，根据所
述目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识，所述获取模块22具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征。相应的，所述匹配模块23具体用于：将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识，所述获取模块22具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像的背景的颜色特征。相应的，所述匹配模块23具体用于：将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为背景匹配类型时，可选的，所述发送模块24具体用于：获取所述目标图像所属的用户的信息；判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数是否大于预先设置的阈值；若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则将所述目标图像所属的用户的信息添加到所述匹配结果中。
当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块22具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征。相应的，所述匹配模块23具体用于：将所述待匹配图像的纹理特征与所述图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块22
具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息。相应的，所述匹配模块23具体用于：将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识，所述获取模块22具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息。相应的，所述匹配模块23具体用于：将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为所述目标图像。
本实施例的服务器，可用于执行实施例二的方法，具体实现方式和技术效果类似，这里不再赘述。
图5为本发明实施例五提供的一种终端的结构示意图，如图5所示，本实施例提供的终端300包括：处理器31、存储器32、通信接口33和通信总线34，其中，存储器32和通信接口33通过通信总线34与处理器31连接，存储器32用于存储计算机指令，通信接33口用于与其他设备通信，处理器31用于执行存储器32中存储的计算机指令，以执行如下所述的方法：
接收用户输入的待匹配图像和所述待匹配图像的匹配类型；
采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数；
将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像匹配的目标图像；
接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
当所述待匹配图像的匹配类型为人脸匹配类型时，所述采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
当所述待匹配图像的匹配类型为背景匹配类型时，所述采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
当所述待匹配图像的匹配类型为地点匹配类型时，所述采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。可选的，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，则所述处理器31还用于：从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
当所述待匹配图像的匹配类型为作者匹配类型时，所述采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：采用与所述作者匹配类型对应的算法，从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
本实施例的终端，可用于执行实施例一的方法，具体实现方式和技术效果类似，这里不再赘述。
图6为本发明实施例六提供的一种服务器的结构示意图，如图6所示，本实施例提供的服务器400包括：处理器41、存储器42、通信接口43和通信总线44，其中，存储器42和通信接口43通过通信总线44与处理器41连接，存储器42用于存储计算机指令，通信接43口用于与其他设备通信，处理器41用于执行存储器42中存储的计算机指令，以执行如下所述的方法：
接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法的标识；
根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；
将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数
进行匹配，将匹配成功的图像作为所述目标图像；
获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识。所述根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征。所述将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识。所述根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像的背景的颜色特征。所述将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为背景匹配类型时，所述获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，将所述匹配结果发送给所述客户端，包括：获取所述目标图像所属的用户的信息；判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数是否大于预先设置的阈值；若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则将所述目标图像所属的用户的信息添加到所述匹配结果中。
当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识。所述根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的
匹配参数，包括：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征。所述将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将所述图像库中的匹配成功的图像作为所述目标图像，包括：将所述待匹配图像的纹理特征与所述图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识。所述根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息。所述将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识。所述根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息。将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为所述目标图像。
本实施例的服务器，可用于执行实施例二的方法，具体实现方式和技术效果类似，这里不再赘述。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储
于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。
Claims (26)
- 一种图像匹配发现好友的方法，其特征在于，包括：客户端接收用户输入的待匹配图像和所述待匹配图像的匹配类型；所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数；所述客户端将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像匹配的目标图像；所述客户端接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
- 根据权利要求1所述的方法，其特征在于，当所述待匹配图像的匹配类型为人脸匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：所述客户端采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
- 根据权利要求1所述的方法，其特征在于，当所述待匹配图像的匹配类型为背景匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：所述客户端采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
- 根据权利要求1所述的方法，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：所述客户端采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。
- 根据权利要求4所述的方法，其特征在于，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，则所述方法还包括：所述客户端从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
- 根据权利要求1所述的方法，其特征在于，当所述待匹配图像的匹配类型为作者匹配类型时，所述客户端采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数，包括：所述客户端采用与所述作者匹配类型对应的算法，从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
- 一种图像匹配发现好友的方法，其特征在于，包括：服务器接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像；所述服务器获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
- 根据权利要求7所述的方法，其特征在于，当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：所述服务器将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求7所述的方法，其特征在于，当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像的背景的颜色特征；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：所述服务器将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求9所述的方法，其特征在于，所述服务器获取所述目标图像所属的用户的信息，根据所述目标图像所属的用户的信息生成匹配结果，将所述匹配结果发送给所述客户端，包括：所述服务器获取所述目标图像所属的用户的信息；所述服务器判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数是否大于预先设置的阈值；若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则所述服务器将所述目标图像所属的用户的信息添加到所述匹配结果中。
- 根据权利要求7所述的方法，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将所述图像库中的匹配成功的图像作为所述目标图像，包括：所述服务器将所述待匹配图像的纹理特征与所述图像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求7所述的方法，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹 配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：所述服务器将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求7所述的方法，其特征在于，当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识；所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数，包括：所述服务器根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息；所述服务器将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像，包括：所述服务器将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为所述目标图像。
- 一种客户端，其特征在于，包括：接收模块，用于接收用户输入的待匹配图像和所述待匹配图像的匹配类型；获取模块，用于采用与所述待匹配图像的匹配类型对应的匹配算法获取所述待匹配图像的匹配参数；发送模块，用于将所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识发送给服务器，以使所述服务器根 据所述待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述匹配算法的标识与图像库中的图像进行匹配，找到与所述待匹配图像匹配的目标图像；所述接收模块，还用于接收所述服务器返回的匹配结果，所述匹配结果中包括匹配到的所述目标图像所属的用户的信息。
- 根据权利要求14所述的客户端，其特征在于，当所述待匹配图像的匹配类型为人脸匹配类型时，所述获取模块具体用于：采用与所述人脸匹配类型对应的匹配算法，提取所述待匹配图像的人脸特征。
- 根据权利要求14所述的客户端，其特征在于，当所述待匹配图像的匹配类型为背景匹配类型时，所述获取模块具体用于：采用与所述背景匹配类型对应的算法，提取所述待匹配图像的背景的颜色特征。
- 根据权利要求14所述的客户端，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述获取模块具体用于：采用与所述地点匹配类型对应的算法，提取所述待匹配图像的纹理特征。
- 根据权利要求17所述的客户端，其特征在于，所述待匹配图像的匹配参数还包括所述待匹配图像的拍摄地点信息，所述获取模块还用于：从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄地点信息。
- 根据权利要求14所述的客户端，其特征在于，当所述待匹配图像的匹配类型为作者匹配类型时，所述获取模块具体用于：采用与所述作者匹配类型对应的算法，从所述待匹配图像的文件头信息中获取所述待匹配图像的拍摄作者的信息。
- 一种服务器，其特征在于，包括：接收模块，用于接收客户端发送的待匹配图像的匹配参数、所述待匹配图像的匹配类型和所述待匹配图像的匹配类型对应的匹配算法的标识；获取模块，用于根据所述待匹配图像的匹配类型和所述匹配算法的标识，获取图像库中的图像的匹配参数；匹配模块，用于将所述待匹配图像的匹配参数与所述图像库中的图像的匹配参数进行匹配，将匹配成功的图像作为所述目标图像；发送模块，用于获取所述目标图像所属的用户的信息，根据所述 目标图像所属的用户的信息生成匹配结果，并将所述匹配结果发送给所述客户端。
- 根据权利要求20所述的服务器，其特征在于，当所述待匹配图像的匹配类型为人脸匹配类型时，所述匹配算法的标识为所述人脸匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述人脸匹配类型对应的匹配算法提取所述图像库中的图像的人脸特征；所述匹配模块具体用于：将所述待匹配图像的人脸特征与所述图像库中的图像的人脸特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求20所述的服务器，其特征在于，当所述待匹配图像的匹配类型为背景匹配类型时，所述匹配算法的标识为所述背景匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述背景匹配类型对应的匹配算法提取所述图像库中的图像的背景的颜色特征；所述匹配模块具体用于：将所述待匹配图像的背景的颜色特征与所述图像库中的图像的背景的颜色特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求22所述的服务器，其特征在于，所述发送模块具体用于：获取所述目标图像所属的用户的信息；判断所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数是否大于预先设置的阈值；若所述目标图像所属的用户的图像中与所述待匹配图像匹配的图像个数大于所述阈值，则将所述目标图像所属的用户的信息添加到所述匹配结果中。
- 根据权利要求20所述的服务器，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用与所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征；所述匹配模块具体用于：将所述待匹配图像的纹理特征与所述图 像库中的图像的纹理特征进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求20所述的服务器，其特征在于，当所述待匹配图像的匹配类型为地点匹配类型时，所述匹配算法的标识为所述地点匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述地点匹配类型对应的算法提取所述图像库中的图像的纹理特征，并从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄地点信息；所述匹配模块具体用于：将所述待匹配图像中的纹理特征和拍摄地点信息，与所述图像库中的图像的纹理特征和拍摄地点信息进行匹配，将匹配成功的图像作为所述目标图像。
- 根据权利要求20所述的服务器，其特征在于，当所述待匹配图像的匹配类型为作者匹配类型时，所述匹配算法的标识为所述作者匹配类型对应的匹配算法的标识，所述获取模块具体用于：根据所述待匹配图像的匹配类型和所述匹配算法的标识，采用所述作者匹配类型对应的算法，从所述图像库中的图像的文件头信息中获取所述图像库中的图像的拍摄作者的信息；所述匹配模块具体用于：将所述待匹配图像的拍摄作者的信息与所述图像库中的图像的拍摄作者的信息进行匹配，将匹配成功的图像作为所述目标图像。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510090499.4A CN105989345A (zh) | 2015-02-28 | 2015-02-28 | 图像匹配发现好友的方法和装置 |
| CN201510090499.4 | 2015-02-28 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016134666A1 true WO2016134666A1 (zh) | 2016-09-01 |
Family
ID=56787879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/074650 WO2016134666A1 (zh) | 2015-02-28 | 2016-02-26 | 图像匹配发现好友的方法和装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105989345A (zh) |
| WO (1) | WO2016134666A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723767A (zh) * | 2020-06-29 | 2020-09-29 | 杭州海康威视数字技术股份有限公司 | 一种图像处理方法、装置及计算机存储介质 |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334522B (zh) * | 2017-01-20 | 2021-12-14 | 阿里巴巴集团控股有限公司 | 确定海关编码的方法，以及确定类型信息的方法和系统 |
| CN106980688A (zh) * | 2017-03-31 | 2017-07-25 | 上海掌门科技有限公司 | 一种用于提供交友对象的方法、设备及系统 |
| CN110139025A (zh) * | 2018-09-29 | 2019-08-16 | 广东小天才科技有限公司 | 一种基于拍照行为的社交用户推荐方法及可穿戴设备 |
| CN110955841A (zh) * | 2019-11-28 | 2020-04-03 | 维沃移动通信有限公司 | 社交关系建立方法和电子设备 |
| CN112163168A (zh) * | 2020-09-15 | 2021-01-01 | 济南雪景网络技术有限公司 | 一种基于计算机视觉的匹配交友方法 |
| CN117321586A (zh) * | 2022-04-29 | 2023-12-29 | 北京小米移动软件有限公司 | 图像处理方法及装置 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103024118A (zh) * | 2012-11-23 | 2013-04-03 | 东莞宇龙通信科技有限公司 | 联系人查找方法及通信终端 |
| CN103116751A (zh) * | 2013-01-24 | 2013-05-22 | 河海大学 | 一种车牌字符自动识别方法 |
| CN103327163A (zh) * | 2012-03-22 | 2013-09-25 | 宇龙计算机通信科技(深圳)有限公司 | 查找联系人信息的方法及其通信终端 |
| US20140025707A1 (en) * | 2012-07-17 | 2014-01-23 | Verizon Patent And Licensing Inc. | Method and apparatus for establishing a connection with known individuals |
| CN103970771A (zh) * | 2013-01-29 | 2014-08-06 | 中国科学院计算技术研究所 | 一种人体的检索方法和系统 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077574A1 (en) * | 2006-09-22 | 2008-03-27 | John Nicholas Gross | Topic Based Recommender System & Methods |
| CN102831176B (zh) * | 2012-07-30 | 2016-12-21 | 东莞宇龙通信科技有限公司 | 推荐好友的方法及服务器 |
| US9639608B2 (en) * | 2013-03-15 | 2017-05-02 | Daniel Freeman | Comprehensive user/event matching or recommendations based on awareness of entities, activities, interests, desires, location |
| CN104102656B (zh) * | 2013-04-09 | 2016-08-03 | 腾讯科技（深圳）有限公司 | 好友推荐方法、装置、系统及服务器 |
| CN103514286A (zh) * | 2013-09-30 | 2014-01-15 | 鸿富锦精密工业（深圳）有限公司 | 好友推荐系统及方法 |
| CN104333506A (zh) * | 2014-10-24 | 2015-02-04 | 北京兴远永网络科技有限公司 | 一种通讯端联系方法及装置 |
| CN104317932B (zh) * | 2014-10-31 | 2018-04-27 | 小米科技有限责任公司 | 照片分享方法及装置 |
-
2015
- 2015-02-28 CN CN201510090499.4A patent/CN105989345A/zh active Pending
-
2016
- 2016-02-26 WO PCT/CN2016/074650 patent/WO2016134666A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103327163A (zh) * | 2012-03-22 | 2013-09-25 | 宇龙计算机通信科技(深圳)有限公司 | 查找联系人信息的方法及其通信终端 |
| US20140025707A1 (en) * | 2012-07-17 | 2014-01-23 | Verizon Patent And Licensing Inc. | Method and apparatus for establishing a connection with known individuals |
| CN103024118A (zh) * | 2012-11-23 | 2013-04-03 | 东莞宇龙通信科技有限公司 | 联系人查找方法及通信终端 |
| CN103116751A (zh) * | 2013-01-24 | 2013-05-22 | 河海大学 | 一种车牌字符自动识别方法 |
| CN103970771A (zh) * | 2013-01-29 | 2014-08-06 | 中国科学院计算技术研究所 | 一种人体的检索方法和系统 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723767A (zh) * | 2020-06-29 | 2020-09-29 | 杭州海康威视数字技术股份有限公司 | 一种图像处理方法、装置及计算机存储介质 |
| CN111723767B (zh) * | 2020-06-29 | 2023-08-08 | 杭州海康威视数字技术股份有限公司 | 一种图像处理方法、装置及计算机存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105989345A (zh) | 2016-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016134666A1 (zh) | 图像匹配发现好友的方法和装置 | |
| US9996735B2 (en) | Facial recognition | |
| US11381556B2 (en) | Method and device for information interaction and association between human biological feature data and account | |
| RU2654168C2 (ru) | Способ и устройство для совместного использования фотографий | |
| WO2019153504A1 (zh) | 一种群组创建的方法及其终端 | |
| WO2016173443A1 (zh) | 账户信息获取的方法、终端、服务器和系统 | |
| WO2016146060A1 (zh) | 照片的分享方法及装置 | |
| CN109117778B (zh) | 信息处理方法、装置、服务器及存储介质 | |
| WO2017071086A1 (zh) | 用于视频播放的方法及装置 | |
| US11501564B2 (en) | Mediating apparatus and method, and computer-readable recording medium thereof | |
| CN108198177A (zh) | 图像获取方法、装置、终端及存储介质 | |
| US20140169702A1 (en) | Photo Chapters Organization | |
| WO2018133354A1 (zh) | 一种信息获取方法及获取设备 | |
| TWI518602B (zh) | 圖像識別方法、裝置、終端設備及伺服器 | |
| WO2015192615A1 (zh) | 一种图像文件共享方法、装置和计算机存储介质 | |
| CN111147766A (zh) | 特效视频合成方法、装置、计算机设备和存储介质 | |
| KR101715708B1 (ko) | 이미지 분석기반의 자동화된 관계형 태그 생성 시스템과 이를 이용한 서비스 제공방법 | |
| US20180137661A1 (en) | Picture processing method, sending method, processing apparatus and sending apparatus | |
| CN107733874B (zh) | 信息处理方法、装置、计算机设备和存储介质 | |
| CN110415318B (zh) | 图像处理方法和装置 | |
| US20120179676A1 (en) | Method and apparatus for annotating image in digital camera | |
| US9710927B2 (en) | Method and apparatus for determining data enabling generation of a user profile | |
| CN113179358B (zh) | 一种题目解答的防作弊方法、装置及电子设备 | |
| CN112752016B (zh) | 一种拍摄方法、装置、计算机设备和存储介质 | |
| CN113784039B (zh) | 头像处理方法、装置、电子设备及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: 16754775 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: 16754775 Country of ref document: EP Kind code of ref document: A1 |