WO2017197959A1 - 一种图片处理方法、装置及设备 - Google Patents

一种图片处理方法、装置及设备 Download PDF

Info

Publication number
WO2017197959A1
WO2017197959A1 PCT/CN2017/075748 CN2017075748W WO2017197959A1 WO 2017197959 A1 WO2017197959 A1 WO 2017197959A1 CN 2017075748 W CN2017075748 W CN 2017075748W WO 2017197959 A1 WO2017197959 A1 WO 2017197959A1
Authority
WO
WIPO (PCT)
Prior art keywords
picture
recommended
pictures
target
information
Prior art date
Application number
PCT/CN2017/075748
Other languages
English (en)
French (fr)
Inventor
陈成
Original Assignee
北京金山安全软件有限公司
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 北京金山安全软件有限公司 filed Critical 北京金山安全软件有限公司
Publication of WO2017197959A1 publication Critical patent/WO2017197959A1/zh

Links

Images

Classifications

    • 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
    • G06F16/50Information 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
    • G06F16/5866Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information

Definitions

  • the present application relates to the field of data processing technologies, and in particular, to a picture processing method, apparatus, and device.
  • the first way is that the user randomly sends a set of pictures acquired by himself, and a set of pictures includes at least one picture, such as a photo currently taken by the user, or a favorite picture downloaded by the user, etc., which are all casual images.
  • the second way is for a user or platform to send a set of the same subject images through a clear theme.
  • the same theme image is a different image that can show the same information.
  • the database is manually filtered.
  • the picture in the picture to get the same theme picture of the group, and it is also subjective judgment for whether each piece is selected as the same subject picture.
  • the efficiency of manual filtering is getting lower and lower, which is not conducive to the interaction between users in the social platform.
  • the embodiment of the present invention provides a picture processing method, device, and device, which can solve the problem of how to improve the efficiency of picture screening.
  • a first aspect of the embodiments of the present application provides a picture processing method, including:
  • target information is information indicating a theme of the picture to be recommended
  • the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • the method before the filtering the image in the database according to the target information to obtain the to-be-recommended image, the method further includes:
  • the picture to be recommended is determined according to the matching result.
  • the determining, by the matching result, the step of determining the picture to be recommended includes:
  • the to-be-selected picture is used as the picture to be recommended;
  • the to-be-selected picture of the predetermined number of pictures is selected as the picture to be recommended according to the order of matching degree from high to low.
  • the determining, by the matching result, the step of determining the picture to be recommended includes:
  • the to-be-selected picture is used as the picture to be recommended;
  • the picture to be recommended is selected from the to-be-selected pictures whose corresponding image quality reaches the preset image quality.
  • the determining, by the matching result, the step of determining the picture to be recommended includes:
  • the to-be-selected picture is used as the picture to be recommended;
  • the picture to be recommended is selected from the to-be-selected pictures that meet the comprehensive standard, wherein the comprehensive standard is related to the matching degree and the image quality. Standard.
  • the image to be recommended is put into the target image filling template, and one is generated.
  • the method further includes:
  • the target picture padding template includes at least one frame information
  • the step of placing the to-be-recommended picture into the target picture-filling template to generate a set of the same-themed picture set to be recommended includes:
  • the corresponding picture to be recommended is placed in the frame to obtain a set of the same theme picture to be recommended.
  • a second aspect of the embodiments of the present application provides a picture processing apparatus, including:
  • An acquiring unit configured to acquire target information, and provide the target information to a determining unit, where the target information is information indicating a theme of the picture to be recommended;
  • the determining unit is configured to filter the picture stored in the storage unit according to the target information, determine the picture to be recommended, and provide the picture to be recommended to the generating unit;
  • the generating unit is configured to put the picture to be recommended into a target picture filling template, and generate a set of the same theme picture set to be recommended.
  • the acquiring unit is further configured to: acquire a user-uploaded image, and provide the user-uploaded image to the storage unit; The picture information carried in the picture uploaded by the user, where the picture information is information indicating the attribute of the picture;
  • the generating unit is further configured to generate, according to the picture information, a label of the picture corresponding to the picture information, and provide a label of the generated picture to the storage unit;
  • the storage unit is configured to map and store a picture uploaded by the user and a label corresponding to the picture uploaded by the user.
  • the device further includes: a matching unit;
  • the matching unit is configured to match the target information with a label corresponding to the picture in the database
  • the determining unit is further configured to determine the picture to be recommended according to the matching result.
  • the determining unit includes: a first selecting module and a first determining module;
  • the first selection module is configured to select a picture whose matching degree reaches a predetermined matching degree as a to-be-selected picture
  • the first determining module is configured to determine the to-be-selected picture as the to-be-recommended picture when the number of the to-be-selected pictures does not exceed the predetermined number of pictures; when the number of the to-be-selected pictures exceeds the predetermined number When the number of pictures is selected, the to-be-selected picture of the predetermined number of pictures is selected as the picture to be recommended according to the order of matching degree from high to low.
  • the determining unit further includes: a second selecting module, a second determining module, and a first acquiring module;
  • the second selection module is configured to select a picture whose matching degree reaches a predetermined matching degree as a to-be-selected picture
  • the first acquiring module is configured to acquire an image quality degree corresponding to the to-be-selected picture
  • a second determining module configured to determine the to-be-selected picture as the to-be-recommended picture when the number of the to-be-selected pictures does not exceed the predetermined number of pictures; when the number of the to-be-selected pictures exceeds the predetermined number of pictures
  • the picture to be recommended is selected from the to-be-selected pictures whose corresponding image quality reaches the preset image quality.
  • the determining unit further includes: a third selecting module, a third determining module, and a second acquiring module;
  • the third selection module is configured to select a picture whose matching degree reaches a predetermined matching degree as a to-be-selected picture
  • the second acquiring module is configured to acquire an image quality degree corresponding to the to-be-selected picture
  • the third determining module is configured to: when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, determine the to-be-selected picture as the picture to be recommended; when the number of the to-be-selected pictures exceeds When the number of predetermined pictures is described, the picture to be recommended is selected from the to-be-selected pictures that meet the comprehensive standard, wherein the comprehensive standard is a criterion related to both the matching degree and the image quality.
  • the image to be recommended is put into the target image filling template, and a set of the same to be recommended is generated.
  • the device further includes:
  • the determining unit is further configured to determine the target picture filling template according to the predetermined number of pictures; or determine the target picture filling template according to the target information and the predetermined number of pictures; or, according to the target information And the actual number of pictures determines the target picture fill template.
  • the target picture fill template includes at least one frame information
  • the generating unit is configured to fill each frame information included in the template according to the target picture, and put the picture corresponding to the recommended picture into a frame to obtain a set of the same theme picture to be recommended.
  • a third aspect of the embodiments of the present application provides a picture processing device, including: a processor, a memory, a communication interface, and a bus;
  • the processor, the memory, and the communication interface are connected by the bus and complete communication with each other;
  • the memory stores executable program code
  • the processor executes a program corresponding to the executable program code by reading executable program code stored in the memory for executing a picture processing method; wherein the image processing method includes:
  • target information is information indicating a theme of the picture to be recommended
  • the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • a fourth aspect of the present application provides a storage medium, where the storage medium is used to store executable program code, and the executable program code is executed to execute a picture processing method according to an embodiment of the present application.
  • the fifth aspect of the embodiment of the present application provides an application program, where the application is used to execute a picture processing method according to an embodiment of the present application at runtime.
  • the picture to be recommended is placed in the target picture filling template.
  • Generating a set of the same theme image to be recommended can solve the steps of avoiding manual screening of images, and avoid artificially generating the same theme image set to be recommended, thereby improving the efficiency of image screening and reducing certain artificial resources.
  • FIG. 1 is a schematic diagram of a network architecture provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a picture processing method according to an embodiment of the present application.
  • FIG. 3 is a schematic flowchart diagram of another image processing method according to an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of still another image processing method according to an embodiment of the present application.
  • FIG. 5 is a schematic flowchart diagram of still another image processing method according to an embodiment of the present application.
  • FIG. 6 is a schematic flowchart diagram of still another image processing method according to an embodiment of the present application.
  • FIG. 7 is a schematic flowchart diagram of still another image processing method according to an embodiment of the present application.
  • FIG. 8(a) is a simplified structural diagram of a picture filling template in a picture processing method according to an embodiment of the present application.
  • FIG. 8(b) is a simplified structural diagram of another picture filling template in the picture processing method provided by the embodiment of the present application.
  • FIG. 8(c) is a simplified structural diagram of another picture filling template in the picture processing method provided by the embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a picture processing apparatus according to an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of another image processing apparatus according to an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of still another image processing apparatus according to an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of still another image processing apparatus according to an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of still another image processing apparatus according to an embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of a picture processing device according to an embodiment of the present application.
  • the embodiment of the present invention provides a picture processing method, device, and device, which can solve the problem of how to improve the efficiency of picture screening.
  • An image processing method provided by the embodiment of the present application may include: acquiring target information, where the target information is information indicating a theme of a picture to be recommended; screening a picture in the database according to the target information to obtain a picture to be recommended; Put a target image to fill the template to generate a set of the same theme collection to be recommended.
  • FIG. 1 is a network architecture that may be used to implement the solution of the embodiment of the present application.
  • the network architecture shown in FIG. 1 includes: a terminal for uploading a picture; a cloud server that stores a picture, generates a same theme picture set to be recommended; a network that can be used for data transmission, and a plurality of authorized ones that can view the cloud The terminal of the same theme set to be recommended in the server.
  • the terminal for uploading the image shares the image to be shared to the social platform through the network
  • the cloud server serving the social platform saves the shared image, and after obtaining the target information indicating the theme of the image to be recommended, the target is passed.
  • the information is saved in a database of images to be shared, and the image to be recommended is obtained, and then the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • the terminal in the embodiment of the present application may be an electronic device that has a picture processing function and can access a network, such as a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), and a PMP (portable multimedia player).
  • a network such as a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), and a PMP (portable multimedia player).
  • the application examples are not limited.
  • the image saved in the cloud server serving the social platform is not limited to the image to be shared uploaded by the terminal for uploading the image, for example, the cloud server can also be crawled through the web crawler. Pictures, and so on.
  • a group of pictures to be recommended in the same topic picture group may belong to the same picture shared by the terminal for uploading pictures, or may belong to different pictures shared by the terminal for uploading pictures, which are all reasonable. of.
  • the cloud server in the embodiment of the present application may be a device that provides a computing service.
  • the server is configured to include a processor, a hard disk, a memory, a system bus, and the like.
  • the server is similar to a general computer architecture, but needs to provide a highly reliable service. High processing power, stability, reliability, security, scalability, manageability, etc. are required.
  • FIG. 2 is a schematic flowchart of a picture processing method according to an embodiment of the present application.
  • a picture processing method provided by an embodiment of the present application may include the following content:
  • the information indicating the subject of the picture to be recommended is information for selecting a picture, such as person A (photograph about the mother), activity B (photograph about the Songkran Festival), and scenery area C (photograph about Jiuzhaigou).
  • the information indicating the subject of the picture to be recommended includes the picture type - woman, Picture time: 2016/5/8.
  • the subject information also includes image attention: the number of praises is more than 30 times, the browsing rate is more than 100 times, and the number of forwardings is more than 50 times.
  • the target information can be information specified by the user or information specified by the platform, which is reasonable.
  • the picture to be recommended includes at least one picture.
  • the image processing method may further include:
  • the image uploaded by the user here is the image that the user wants to share, wherein the image may be a picture uploaded by the user to the social platform, so as to be shared with others. Or the picture is directly uploaded to the picture sharing area by the user, where the picture sharing area may be a database dedicated to storing pictures that the user wants to share.
  • the user uploads the image to the image sharing area, and waits for the third party to filter and then can share the uploaded image to the social platform.
  • the picture information is information indicating a picture attribute.
  • the picture attribute includes a type, a color tone, a source, a degree of attention, and the like.
  • the picture information includes at least but not limited to the following information: picture type, picture color tone, picture owner, picture attention degree. Understandably, the color tone of a picture can usually be divided into five types, namely: warm color, cool color, monotone, light color, strong contrast color.
  • the cloud server can identify by the algorithm, identify the uploaded picture, and obtain the first part of the picture information in the picture.
  • the algorithm for identifying pictures can be color recognition algorithm, shape recognition calculation Method, face recognition algorithm.
  • the first part of the picture information includes information such as picture color tone and picture type, which are obtained through algorithm identification.
  • the user can edit the profile of the picture and upload the edit information along with the picture, so the cloud server can also extract the edit information to obtain the second part of the picture information, wherein the second part of the picture information includes the picture owner and picture.
  • Type picture theme (a certain event, a picture of a certain scenery).
  • the attention degree of the picture (the number of likes, the click rate of browsing, the number of times of forwarding, etc.) can be obtained, the attention degree of the picture is taken as the third part of the picture information, and so on. You can also get image information for other parts of the image. Furthermore, finally, the first partial picture information, the second partial picture information, the third partial picture information, the Nth part of the picture information may be aggregated to obtain picture information.
  • the label of the image is used to classify the image and to identify the general information of the image, so as to facilitate the subsequent screening of the desired image according to the label.
  • the picture uploaded by the user and the label corresponding to the picture uploaded by the user are provided to the database.
  • S301 to S304 may be executed before S201, or may be performed before S202.
  • the present application is not limited.
  • FIG. 3 shows a flowchart executed before S201.
  • the step of filtering the image in the database according to the target information, and obtaining the image to be recommended may include: S2021, the target The information is matched with the label corresponding to the picture in the database; in S2022, the picture with the matching success is used as the picture to be recommended.
  • the picture to be recommended may be determined according to the matching result. Specifically, the picture whose matching degree reaches the predetermined matching degree may be directly used as the picture to be recommended, or In the picture whose matching degree reaches the predetermined matching degree, the part is selected as the picture to be recommended.
  • S2022 there are many specific implementations of S2022, and four methods are listed here.
  • the picture whose matching degree reaches the predetermined matching degree is selected as the candidate picture.
  • the predetermined match may be 55%.
  • the target information includes the picture type, the picture color tone, and the picture attention degree.
  • the parameter settings included in the target information have a weight ratio, for example, the picture type accounts for 0.5, the picture color tone accounts for 0.3, and the picture attention accounts for 0.2.
  • the target information is matched with the label corresponding to the picture in the database. For example, when the picture type and the color tone of the picture are found to be consistent with the parameter requirements in the target information, the matching degree of the two is 80%.
  • the to-be-selected picture is used as the picture to be recommended.
  • the requirement is that when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, the to-be-selected picture is taken as the picture to be recommended, and further, after the picture to be recommended is determined, the recommended picture may be placed in the target picture filling template. Generate a set of the same theme collections to be recommended.
  • the recommended picture is generally required, and the number of predetermined pictures can be obtained from the target picture fill template.
  • the predetermined number of pictures may be a randomly set value, an empirical value, or the like, which is reasonable.
  • the to-be-selected picture of the predetermined number of pictures is selected as the picture to be recommended according to the order of matching degree from high to low.
  • the number of pictures to be recommended selected by the first manner is less than or equal to the predetermined number of pictures.
  • the second implementation is shown in Figure 5.
  • the picture whose matching degree reaches the predetermined matching degree is selected as the candidate picture.
  • the image quality parameters may include finish, sharpness, color saturation, and the like.
  • the parameters included in the target information can be set to have a weight ratio, such as a gloss ratio of 0.3, a resolution of 0.35, and a color saturation of 0.35.
  • a weight ratio such as a gloss ratio of 0.3, a resolution of 0.35, and a color saturation of 0.35.
  • the requirement is that when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, the to-be-selected picture is taken as the picture to be recommended, and further, after the picture to be recommended is determined, the recommended picture may be placed in the target picture filling template. Generate a set of the same theme collections to be recommended. S504: When the number of the to-be-selected pictures exceeds the predetermined number of pictures, select the to-be-selected picture whose image quality is up to the preset image quality as the picture to be recommended.
  • the picture to be recommended is selected from the to-be-selected pictures whose corresponding image quality reaches the preset image quality.
  • the present application does not limit the specific value of the predetermined image quality.
  • the picture to be recommended is selected from the to-be-selected pictures whose corresponding image quality reaches the preset image quality, so that there are three cases, first The number of to-be-selected pictures whose image quality reaches the preset image quality is less than the predetermined number of pictures; in the second case, the number of to-be-selected pictures whose image quality reaches the preset image quality is equal to the predetermined number of pictures; In this case, the number of to-be-selected pictures whose image quality reaches the preset image quality is greater than the predetermined number of pictures.
  • the actual number of pictures is taken as the standard.
  • the actual number of pictures is the number of predetermined pictures.
  • the to-be-selected picture of the predetermined number of pictures is selected as the picture to be recommended according to the order of the picture quality of the picture, so that the actual number of pictures is the predetermined number of pictures, that is, from the corresponding image quality.
  • the to-be-selected picture whose degree reaches the preset image quality, a part of the picture is selected as the picture to be recommended.
  • the picture with the matching degree reaching the predetermined matching degree is the candidate picture.
  • the requirement is that when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, the to-be-selected picture is taken as the picture to be recommended, and further, after the picture to be recommended is determined, the recommended picture may be placed in the target picture filling template. Generate a set of the same theme collections to be recommended.
  • the to-be-selected picture that meets the comprehensive standard is selected according to the comprehensive standard of the matching degree and the image quality.
  • the picture to be recommended is selected from the to-be-selected pictures that meet the comprehensive standard, wherein the comprehensive standard is a standard related to the matching degree and the image quality. .
  • the parameters included in the image quality degree can also be weighted, and secondly, the degree of matching and the image quality are also weighted.
  • the comprehensive standard here includes a comprehensive standard value that is used to measure whether the candidate picture can be used as the standard value of the picture to be recommended.
  • the matching degree corresponding to the picture is multiplied by the matching degree weight value plus the image quality degree corresponding to the picture multiplied by the image quality degree weight value to obtain a comprehensive value, and the integrated value is compared with the comprehensive standard value, when the comprehensive When the value is not lower than the comprehensive standard value, it means that it meets the comprehensive standard.
  • the picture to be recommended obtained in the third implementation manner has a problem similar to that of the second implementation manner, that is, the problem of the relationship between the number of pictures to be selected and the number of predetermined pictures in accordance with the comprehensive standard, and reference may be made to the second implementation. The way the solution is implemented.
  • the picture whose matching degree reaches the predetermined matching degree is selected as the candidate picture.
  • the candidate picture is displayed in the display area so that the user can select the picture.
  • S704 Take a picture with a selection flag as a picture to be recommended.
  • the number of pictures to be recommended there are two ways for the number of pictures to be recommended.
  • a predetermined number of pictures is set to constrain the number of pictures selected by the user.
  • the number of pictures selected by the user is determined by the user. .
  • the user here refers to the person who has the right to image screening, that is, when user A wants to share a group of the same theme picture, the user A can decide the number of pictures to be selected, and hope to share one on a certain platform.
  • the administrator of the platform can decide the number of pictures to choose, which is reasonable.
  • the present application can intelligently select a picture to be recommended by matching the label corresponding to the picture in the database with the target information, and avoid manually and subjectively filtering the picture.
  • the picture to be recommended obtained through the target information can be displayed as follows:
  • the image processing method before the image to be recommended is put into the target image filling template to generate a set of the same theme image to be recommended, the image processing method further includes: determining the target image filling template:
  • the target image fill template is determined according to the predetermined number of pictures.
  • the target image fill template is determined according to the target information and the predetermined number of pictures.
  • the target image filling template is determined according to the target information and the actual number of pictures.
  • the predetermined number of pictures when used as the basis for selecting the target picture to fill the template, the predetermined number of pictures may be a randomly set value or an empirical value or the like. And, the actual number of pictures is the determined number of pictures to be recommended.
  • the information included in the target information such as picture type, picture color tone, picture attention degree.
  • the image fills the template. It is a well-regulated square.
  • the picture fill template is a circular module.
  • the picture fill template is a template having a division of a horizontal picture and a vertical picture.
  • the templates shown in FIG. 8(a) and FIG. 8(b) are preferentially applied, and the horizontal picture is included in the picture to be recommended.
  • the template shown in Fig. 8(c) is preferably applied.
  • the image to be recommended is put into the target image filling template, and a set of the same theme image to be recommended is generated, including:
  • the corresponding picture to be recommended is filled into the frame according to each frame information included in the template.
  • the target picture fill template includes at least one frame information.
  • the frame information may be chronological, may be the size of the image, may be the order of attention of the image, may be the intensity of the light of the picture, the proportion of the picture in the picture of the character, or the degree of color gradation of the picture.
  • the position of the picture can be determined according to the acquisition time (photographing time, download time, etc.) of the picture.
  • the position of the picture can be determined according to the level of attention of the picture, and the picture with high degree of attention is placed in a conspicuous position, such as the C area, the picture
  • the position of attention from high to low can be: C>A>B>D>E.
  • the picture after determining four pictures to be recommended, when two horizontal pictures and two vertical pictures appear, the picture can be placed according to the size of the picture, of course, the picture attention degree A>D; B>C, two pictures of the same size can be determined according to the degree of attention.
  • This application can effectively solve the manpower generated by the software operator in the cloud server database. Identify specific imagery by automating algorithms to identify image features. It is convenient for images to be displayed accurately and filtered out unwanted images.
  • the invention will solve the error of human subjective screening by screening the disorganized pictures through a unified definition of multiple dimensions. After filtering the picture to obtain the picture to be recommended, the picture template can be intelligently determined according to the picture type, the picture attention degree and the like to combine the picture to be recommended into a set of the same theme picture set, thereby improving the efficiency of generating the same theme picture set and the picture quality.
  • the present application further provides a picture processing apparatus 90.
  • the apparatus 90 includes an obtaining unit 901, a determining unit 902, a generating unit 903, and a storage unit 904.
  • the obtaining unit 901 is configured to acquire target information, and provide the target information to the determining unit 902, where the target information is information indicating a theme of the picture to be recommended.
  • the determining unit 902 is configured to filter the picture stored in the storage unit 904 according to the target information, determine the picture to be recommended, and provide the picture to be recommended to the generating unit 903.
  • the generating unit 903 is configured to put the picture to be recommended into the target picture filling template, and generate a set of the same theme picture set to be recommended.
  • the storage unit 904 is configured to store a picture, so that the determining unit 902 selects a picture to be recommended.
  • the obtaining unit 901 is further configured to obtain a picture uploaded by the user, and upload the user.
  • the picture is provided to the storage unit 904; the picture information carried in the picture uploaded by the user is obtained, and the picture information is information indicating the attribute of the picture.
  • the generating unit 903 is further configured to generate a label of the picture corresponding to the picture according to the picture information, and provide the generated picture label to the storage unit 904.
  • the storage unit 904 is configured to upload a picture uploaded by the user and a label corresponding to the picture uploaded by the user. Sign the map storage.
  • the determining unit 902 is further configured to Determining the target picture fill template by the predetermined number of pictures; or determining the target picture fill template according to the target information and the predetermined number of pictures; or determining the target picture fill template according to the target information and the actual number of pictures.
  • the generating unit 903 is configured to fill each frame information included in the template according to the target image, and put the picture to be recommended into the frame to obtain a group to be Recommended theme collections.
  • the target image fill template includes at least one frame information.
  • the present application further provides a picture processing apparatus 100.
  • the apparatus 100 further includes a matching unit 905.
  • the matching unit 905 is configured to match the target information with the label corresponding to the picture in the database. Then, the determining unit 902 is configured to determine the picture that the matching is successful as the picture to be recommended. That is, the determining unit 902 is configured to determine a picture to be recommended according to the matching result.
  • the present application further provides a picture processing apparatus 110.
  • the determining unit 902 in the apparatus 110 includes a first selecting module 9021 and a first determining module 9022.
  • the first selection module 9021 is configured to select, when the matching degree reaches a predetermined matching degree, a picture that reaches a predetermined matching degree as a candidate picture. That is, the first selection module 9021 is configured to select a picture whose matching degree reaches a predetermined matching degree as a candidate picture.
  • the first determining module 9022 is configured to: when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, determine the to-be-selected picture as the picture to be recommended; when the number of the to-be-selected pictures exceeds the predetermined number of pictures, according to the matching degree from high to low The order in which the predetermined number of pictures is selected is determined as the picture to be recommended.
  • the present application further provides a picture processing apparatus 120.
  • the determining unit 902 in the apparatus 120 includes a second selecting module 9023, a second determining module 9024, and a first obtaining module 9025.
  • the second selecting module 9023 is configured to select, when the matching degree reaches a predetermined matching degree, a picture that reaches a predetermined matching degree as a to-be-selected picture. That is, the second selection module 9023 is configured to select a picture whose matching degree reaches a predetermined matching degree as a candidate picture.
  • the first obtaining module 9025 is configured to obtain an image quality degree corresponding to the to-be-selected picture.
  • the second determining module 9024 is configured to: when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, determine the to-be-selected picture as the picture to be recommended; when the number of the to-be-selected pictures exceeds the predetermined number of pictures, select the image quality to reach the preset. The image to be selected of the image quality is determined as the picture to be recommended.
  • the second determining module 9024 is configured to: when the number of to-be-selected pictures does not exceed the predetermined number of pictures, determine the to-be-selected picture as the picture to be recommended; when the number of the to-be-selected pictures exceeds the predetermined number of pictures Selecting a picture to be recommended from the to-be-selected picture whose corresponding image quality reaches the preset image quality.
  • the present application further provides a picture processing apparatus 130.
  • the determining unit 902 in the apparatus 130 includes a third selecting module 9026, a third determining module 9027, and a second obtaining module 9028.
  • the third selection module 9026 is configured to select a picture that reaches the predetermined matching degree as the to-be-selected picture when the matching degree reaches the predetermined matching degree; that is, the third selecting module 9026 is configured to select the matching degree to reach the predetermined matching degree.
  • the picture is the candidate picture;
  • the second obtaining module 9028 is configured to obtain an image quality degree corresponding to the to-be-selected picture.
  • the third determining module 9027 is configured to: when the number of the to-be-selected pictures does not exceed the predetermined number of pictures, determine the to-be-selected picture as the picture to be recommended; when the number of the to-be-selected pictures exceeds the predetermined number of pictures, according to the matching degree and the image quality The comprehensive standard selection of the candidate image that meets the comprehensive criteria is determined as the picture to be recommended.
  • the third determining module 9027 is configured to determine the to-be-selected picture as the picture to be recommended when the number of the to-be-selected pictures does not exceed the predetermined number of pictures; when the number of the to-be-selected pictures exceeds the predetermined number of pictures, the matching In the comprehensive standard candidate picture, the picture to be recommended is selected, wherein the comprehensive standard is a standard related to the matching degree and the image quality.
  • each module included in the determining unit 902 and an implementation function corresponding to each module are provided.
  • the present application may further include a picture processing device, and the determining unit in the image processing device.
  • the 902 may include a first selection module 9021, a second selection module 9023, a third selection module 9026, a first determination module 9022, a second determination module 9024, a third determination module 9027, a first acquisition module 9025, and a second acquisition module 9028.
  • the present application further provides a picture processing device 140.
  • the picture processing device 140 may include: a processor 1401, a memory 1402, a communication interface 1403, and a bus 1404;
  • the processor 1401, the memory 1402, and the communication interface 1403 are connected by the bus 1404 and complete communication with each other;
  • the memory 1402 stores executable program code
  • the processor 1401 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 1402 for executing a picture processing method.
  • the image processing method includes:
  • target information is information indicating a theme of the picture to be recommended
  • the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • the image processing device in the present application may be a cloud server, which is of course not limited thereto, and may be, for example, various types of terminal devices.
  • the embodiment of the present application further provides a storage medium, where the storage medium is used to store executable program code, and the executable program code is executed to execute the embodiment of the present application.
  • a picture processing method; wherein the picture processing method includes:
  • target information is information indicating a theme of the picture to be recommended
  • the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • the storage medium stores the image provided by the embodiment of the present application at runtime.
  • the executable program code of the processing method can realize: avoiding the steps of manually filtering the image, and avoiding artificially generating the same theme image set to be recommended, improving the screening efficiency of the image, and reducing certain artificial resources.
  • the embodiment of the present application further provides an application program, where the application is used to execute a picture processing method according to an embodiment of the present application at runtime; wherein the image processing Methods include:
  • target information is information indicating a theme of the picture to be recommended
  • the image to be recommended is placed in the target image filling template to generate a set of the same theme image to be recommended.
  • the application performs the image processing method provided by the embodiment of the present application at runtime, which can implement: avoiding the steps of manually filtering the image, and avoid manually generating the same theme image set to be recommended, and improving the image filtering. At the same time of efficiency, it can also reduce certain artificial resources.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division, and the actual implementation may have another division.
  • multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

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)
  • Library & Information Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

一种图片处理方法、装置及设备,该方法包括:获取目标信息,该目标信息为表示待推荐图片的主题的信息(S201);根据该目标信息筛选数据库中的图片,得到待推荐图片(S202);将上述得到的待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集(S203)。上述方法可以避免人工筛选图片,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。

Description

一种图片处理方法、装置及设备
本申请要求于2016年05月18日提交中国专利局、申请号为201610331774.1发明名称为“一种图片处理方法、装置及设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理技术领域,尤其涉及一种图片处理方法、装置及设备。
背景技术
随着手机、计算机、平板电脑等电子设备的不断发展,图片已经成为社交平台中传递信息的主要方式,用户通过电子设备中的图片来发送或者获取信息,都是一种直观的、方便的传递方式。目前,社交平台中发送图片的方式有两种。第一种方式是用户随性的发送自己获取到的一组图片,一组图片中包括至少一个图片,如用户当前拍摄的照片,或者用户下载到的自己喜欢的图片等都属于随性图片。第二种方式是用户或者平台通过一个明确的主题来发送一组同主题图片。同主题图片为能够表现出同一信息的不同图片。
针对第二种方式来说,用户或者平台发送一组同主题图片时,如最热门话题图片集、某一活动图片集、某一风景图片集、某一人物图片集等,是通过人工筛选数据库中的图片来得到该组同主题图片,而针对各张是否入选为同主题图片也是人为主观判断。对于社交平台上数据量不断增长的图片,人工进行筛选的效率越来越低,不利于社交平台中用户之间的交互。
发明内容
本申请实施例提供了一种图片处理方法、装置及设备,可以解决如何提高图片筛选效率的问题。
本申请实施例第一方面提供一种图片处理方法,包括:
获取目标信息,所述目标信息为表示待推荐图片的主题的信息;
根据所述目标信息筛选数据库中的图片,得到所述待推荐图片;
将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
结合第一方面,在第一方面的第一种可能的实施方式中,在所述根据所述目标信息筛选数据库中的图片,得到所述待推荐图片之前,所述方法还包括:
获取用户上传的图片;
获取所述用户上传的图片中携带的图片信息,所述图片信息为表示图片属性的信息;
根据所述图片信息,生成所述图片信息对应图片的标签;
将所述用户上传的图片以及与所述用户上传的图片对应的标签提供给所述数据库。
结合第一方面的第一种可能的实施方式,在第一方面的第二种可能的实施方式中,所述根据所述目标信息筛选数据库中的图片,得到所述待推荐图片的步骤,包括:
将所述目标信息与所述数据库中的图片对应的标签进行匹配;
根据匹配结果,确定所述待推荐图片。
结合第一方面的第二种可能的实施方式,在第一方面的第三种可能的实施方式中,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
选择匹配度达到预定匹配度的图片为待选图片;
当所述待选图片的数目未超过预定图片数目时,将所述待选图片作为所述待推荐图片;
当所述待选图片的数目超过所述预定图片数目时,根据匹配度由高到低的顺序选择所述预定图片数目的待选图片作为所述待推荐图片。
结合第一方面的第二种可能的实施方式,在第一方面的第四种可能的实施方式中,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
选择匹配度达到预定匹配度的图片为待选图片;
获取所述待选图片对应的图像质量度;
当所述待选图片的数目未超过预定图片数目时,将所述待选图片作为所述待推荐图片;
当所述待选图片的数目超过所述预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取所述待推荐图片。
结合第一方面的第二种可能的实施方式,在第一方面的第五种可能的实施方式中,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
选择匹配度达到预定匹配度的图片为待选图片;
获取所述待选图片对应的图像质量度;
当所述待选图片的数目未超过所述预定图片数目时,将所述待选图片作为所述待推荐图片;
当所述待选图片的数目超过所述预定图片数目时,从符合综合标准的待选图片中,选取所述待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
结合第一方面的第三种可能至第五种可能的实施方式,在第一方面的第六种可能的实施方式中,在所述将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集之前,所述方法还包括:
根据所述预定图片数目确定所述目标图片填充模板;或者,
根据所述目标信息和所述预定图片数目确定所述目标图片填充模板;或者,
根据所述目标信息和实际图片数目确定所述目标图片填充模板。
结合第一方面,在第一方面的第七种可能的实施方式中,所述目标图片填充模板包括至少一个框架信息;
所述将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集的步骤,包括:
按照所述目标图片填充模板中包括的每个框架信息,将所述待推荐图片对应的放入框架中,得到一组待推荐的同主题图片集。
本申请实施例第二方面提供一种图片处理装置,包括:
获取单元,用于获取目标信息,并将所述目标信息提供给确定单元,所述目标信息为表示待推荐图片的主题的信息;
所述确定单元,用于根据所述目标信息筛选存储单元中存储的图片,确定所述待推荐图片,并将所述待推荐图片提供给生成单元;
所述生成单元,用于将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
结合第二方面,在第二方面的第一种可能的实施方式中,所述获取单元,还用于获取用户上传的图片,将所述用户上传的图片提供给所述存储单元;获取所述用户上传的图片中携带的图片信息,所述图片信息为表示图片属性的信息;
所述生成单元,还用于根据所述图片信息,生成所述图片信息对应图片的标签,并将生成的图片的标签提供给所述存储单元;
所述存储单元,用于将所述用户上传的图片以及与所述用户上传的图片对应的标签进行映射存储。
结合第二方面的第一种可能的实施方式,在第二方面的第二种可能的实施方式中,所述装置还包括:匹配单元;
所述匹配单元,用于将所述目标信息与所述数据库中的图片对应的标签进行匹配;
所述确定单元,还用于根据匹配结果,确定所述待推荐图片。
结合第二方面的第二种可能的实施方式,在第二方面的第三种可能的实施方式中,所述确定单元包括:第一选择模块和第一确定模块;
所述第一选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
所述第一确定模块,用于当所述待选图片的数目未超过预定图片数目时,将所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,根据匹配度由高到低的顺序选择所述预定图片数目的待选图片确定为所述待推荐图片。
结合第二方面的第三种可能的实施方式,在第二方面的第四种可能的实施方式中,所述确定单元还包括:第二选择模块,第二确定模块和第一获取模块;
所述第二选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
所述第一获取模块,用于获取所述待选图片对应的图像质量度;
第二确定模块,用于当所述待选图片的数目未超过预定图片数目时,将所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取所述待推荐图片。
结合第二方面的第四种可能的实施方式,在第二方面的第五种可能的实施方式中,所述确定单元还包括:第三选择模块,第三确定模块和第二获取模块;
所述第三选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
所述第二获取模块,用于获取所述待选图片对应的图像质量度;
所述第三确定模块,用于当所述待选图片的数目未超过所述预定图片数目时,将所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,从符合综合标准的待选图片中,选取所述待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
结合第二方面的第五种可能的实施方式,在第二方面的第六种可能的实施方式中,在所述将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集之前,所述装置还包括:
所述确定单元,还用于根据所述预定图片数目确定所述目标图片填充模板;或者,根据所述目标信息和所述预定图片数目确定所述目标图片填充模板;或者,根据所述目标信息和实际图片数目确定所述目标图片填充模板。
结合第二方面,所述目标图片填充模板包括至少一个框架信息;
所述生成单元,具有用于按照所述目标图片填充模板中包括的每个框架信息,将所述待推荐图片对应的放入框架中,得到一组待推荐的同主题图片集。
本申请实施例第三方面提供一种图片处理设备,包括:处理器、存储器、通信接口和总线;
所述处理器、所述存储器和所述通信接口通过所述总线连接并完成相互间的通信;
所述存储器存储可执行程序代码;
所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程序,以用于执行一种图片处理方法;其中,所述图片处理方法包括:
获取目标信息,所述目标信息为表示待推荐图片的主题的信息;
根据所述目标信息筛选数据库中的图片,得到所述待推荐图片;
将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
本申请实施例第四方面提供一种存储介质,其中,该存储介质用于存储可执行程序代码,所述可执行程序代码被运行以执行本申请实施例所述的一种图片处理方法。
本申请实施例第五方面提供一种应用程序,其中,该应用程序用于在运行时执行本申请实施例所述的一种图片处理方法。
可以看出,采用本申请实施例提供的技术方案,在获取到表示待推荐图片的主题的目标信息,以及根据主题信息获取到待推荐图片之后,将待推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集,可以解决避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
附图说明
为了更清楚地说明本申请实施例和现有技术的技术方案,下面对实施例和现有技术中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种网络架构的示意图;
图2是本申请的实施例提供的一种图片处理方法的流程示意图;
图3是本申请的实施例提供的另一种图片处理方法的流程示意图;
图4是本申请的实施例提供的又一种图片处理方法的流程示意图;
图5是本申请的实施例提供的再一种图片处理方法的流程示意图;
图6是本申请的实施例提供的还一种图片处理方法的流程示意图;
图7是本申请的实施例提供的还又一种图片处理方法的流程示意图;
图8(a)是本申请的实施例提供的图片处理方法中一种图片填充模板简易结构图;
图8(b)是本申请的实施例提供的图片处理方法中另一种图片填充模板简易结构图;
图8(c)是本申请的实施例提供的图片处理方法中又一种图片填充模板简易结构图;
图9是本申请的实施例提供的一种图片处理装置的结构示意图;
图10是本申请的实施例提供的另一种图片处理装置的结构示意图;
图11是本申请的实施例提供的又一种图片处理装置的结构示意图;
图12是本申请的实施例提供的再一种图片处理装置的结构示意图;
图13是本申请的实施例提供的还一种图片处理装置的结构示意图;
图14是本申请的实施例提供的一种图片处理设备的结构示意图。
具体实施方式
本申请实施例提供了一种图片处理方法、装置及设备,可以解决如何提高图片筛选效率的问题。
为了使本技术领域的技术人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请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申请一部分的实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都应当属于本申请保护的范围。
以下分别进行详细说明。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象,而不是用于描述特定顺序。此外,术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
本申请实施例所提供的一种图片处理方法,可以包括:获取目标信息,目标信息为表示待推荐图片的主题的信息;根据目标信息筛选数据库中的图片,得到待推荐图片;将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
为了便于理解方案,下面对本申请所提供方案所适用的网络架构进行举例介绍。
请参阅图1,图1是一种可能用于实施本申请实施例方案的网络架构。在图1所示的网络架构中,包括:上传图片的终端;存储图片、生成待推荐的同主题图片集的云服务器;能够用于数据传输的网络、和若干个被授权的能够观看该云服务器中的待推荐的同主题图片集的终端。
用于上传图片的终端将想分享的图片通过网络分享到社交平台,为该社交平台服务的云服务器将分享的图片进行保存,当获取到表示待推荐图片的主题的目标信息后,通过该目标信息去保存有待分享的图片的数据库中进行筛选,得到待推荐图片,然后将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
其中,本申请实施例的终端可为智能手机、笔记本电脑、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)等具备处理图片功能且能够访问网络的电子装置,本申请实施例不作限定。另外,需要强调的是,为该社交平台服务的云服务器中保存的图片并不局限于用于上传图片的终端所上传的待分享的图片,例如:还可以为云服务器通过网络爬虫爬取到的图片,等等。并且,一组待推荐的同主题图片集中的图片可以均属于同一用于上传图片的终端所分享出的图片,也可以属于不同的用于上传图片的终端所分享出的图片,这都是合理的。
本申请实施例中的云服务器可以是提供计算服务的设备,服务器的构成包括处理器、硬盘、内存、系统总线等,服务器和通用的计算机架构类似,但是由于需要提供高可靠的服务,因此在处理能力、稳定性、可靠性、安全性、可扩展性、可管理性等方面要求较高。
下面结合附图对申请实施例所提供的一种图片处理方法进行介绍。
请参阅图2,图2是本申请的一个实施例提供的一种图片处理方法的流程示意图,如图2所示,本申请的一个实施例提供的一种图片处理方法可以包括以下内容:
S201,获取目标信息,该目标信息为表示待推荐图片的主题的信息。
其中,表示待推荐图片的主题的信息为用于挑选图片的信息,比如人物A(有关母亲的照片),活动B(有关泼水节的照片),风景区C(有关九寨沟的照片)。以人物A来举例,表示待推荐图片的主题的信息包括图片类型-女人, 图片时间:2016/5/8。可选的,主体信息还包括图片关注度:点赞次数达30次以上/浏览点击率达100次以上/转发次数达50次以上等。需要强调的是,由于用户或平台都可以有发送一组同主题图片的需求,因此,目标信息可以为用户指定的信息,也可以为平台指定的信息,这都是合理的。
S202,根据该目标信息筛选数据库中的图片,得到待推荐图片。
可以理解的是,待推荐图片包括至少一张图片。
S203,将该待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
可以看出,采用本申请实施例提供的技术方案,在获取到表示待推荐图片的主题的目标信息,以及根据目标信息获取到待推荐图片之后,将待推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集,可以解决避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
可选的,在本申请的一种具体实现方式中,在根据目标信息筛选数据库中的图片,得到待推荐图片之前,如图3所示,图片处理方法可以还包括:
S301,获取用户上传的图片。
这里用户上传的图片为用户想分享的图片,其中,该图片可以是用户上传至社交平台的图片,以便于与他人进行分享。或者该图片为用户直接上传到图片分享区域,其中图片分享区域可以是专门用于存储用户想分享的图片的数据库。通常用户将图片上传到图片分享区域,是等待第三方筛选后能够将自己上传的图片分享到社交平台。
S302,获取该用户上传的图片中携带的图片信息。
图片信息为表示图片属性的信息,举例而言,图片属性包括类型、颜色基调、来源、关注度等。可以理解的是,图片信息至少包括但不限于以下一种信息:图片类型、图片颜色基调、图片所属人、图片关注度。可以理解的是,图片颜色基调通常可以分为五种,具体为:暖色调、冷色调、单色调、浅色调、强对比色。
云服务器可以通过算法识别,对上传的图片进行识别,得到图片中的第一部分图片信息。其中,识别图片的算法可以为颜色识别算法、形态识别算 法、人脸识别算法。其中第一部分图片信息包括图片颜色基调、图片类型等通过算法识别得到的信息。另外,用户可以对图片的简介进行编辑,并将该编辑信息随同图片一同进行上传,因此云服务器还可以提取编辑信息,得到第二部分图片信息,其中第二部分图片信息包括图片所属人、图片类型、图片主题(某某活动、某某风景的图片)。此外,当图片为已上传到社交平台的图片时,可以获取到该图片的关注度(点赞次数、浏览点击率、转发次数等),将图片关注度作为第三部分图片信息,以此类推,还可以获取图片的其他部分的图片信息。进而,最后可以将第一部分图片信息、第二部分图片信息、第三部分图片信息……第N部分图片信息汇总,得到图片信息。
S303,根据图片信息生成所述图片信息对应图片的标签。
图片的标签用于对图片进行分类以及标识图片的大致信息,以便于后续方便根据标签来较高效率的筛选到需要的图片。
S304,将用户上传的图片以及与用户上传的图片对应的标签提供给数据库。
值得说明的是,S301至S304可以在S201之前执行,也可以在S202之前执行,本申请不做限制,为了方便说明,图3示出的是在S201之前执行的流程图。
在数据库中存在图片与标签对应关系的情况下,可选的,在本申请的一种具体实现方式中,根据目标信息筛选数据库中的图片,得到待推荐图片的步骤可以包括:S2021,将目标信息与数据库中的图片对应的标签进行匹配;S2022,将匹配成功的图片作为待推荐图片。也就是说,将目标信息与数据库中的图片对应的标签进行匹配之后,可以根据匹配结果,确定待推荐图片,具体的,可以将匹配度达到预定匹配度的图片均直接作为待推荐图片,或者,在匹配度达到预定匹配度的图片中,筛选出部分来作为待推荐图片。其中,S2022的具体实现可以有多种,在此列举其中四种方法。
第一种实现方式中,如图4所示。
S401,当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。
也就是说,在将目标信息与数据库中的图片对应的标签进行匹配后,选择匹配度达到预定匹配度的图片为待选图片。
本申请不限制预定匹配度的具体值。举例来说,预定匹配度可以为55%。如目标信息包括图片类型、图片颜色基调、图片关注度。同时目标信息中包括的参数设置有权重比例,比如图片类型占比重0.5,图片颜色基调占比重0.3,图片关注度占比重0.2。
将目标信息与数据库中的图片对应的标签进行匹配,如当发现图片类型、图片颜色基调与目标信息中参数要求的一致,则两者匹配度为80%。
S402,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片。
需求强调的是,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片,进而,在确定出待推荐图片后,可以将该推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集。
一般推荐的图片是有数目要求的,可以从目标图片填充模板中获取预定图片数目。当然,在目标图片填充模板未预先被确定的情况下,预定图片数目可以为随机设定的值、经验值等等,这都是合理的。
S403,当待选图片的数目超过预定图片数目时,根据匹配度由高到低的顺序选择预定图片数目的待选图片作为待推荐图片。
可以看出,通过第一种方式选择的待推荐图片的数目小于等于预定图片数目。
第二种实现方式,如图5所示。
S501,当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。
也就是说,在将目标信息与数据库中的图片对应的标签进行匹配后,选择匹配度达到预定匹配度的图片为待选图片。
S502,获取待选图片对应的图像质量度。
其中,图像质量参数可以包括光洁度、清晰度、色彩饱和度等。
同时目标信息中包括的参数可以设置有权重比例,比如光洁度占比重0.3,清晰度占比重0.35,色彩饱和度占比重0.35。通过获取待选图片中的光洁度、 清晰度、色彩饱和度,以及将待选图片中的光洁度、清晰度、色彩饱和度乘以各自权重占比,并求和,得到图片对应的图像质量度。
S503,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片。
需求强调的是,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片,进而,在确定出待推荐图片后,可以将该推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集。S504,当待选图片的数目超过预定图片数目时,选择图像质量度达到预设图像质量度的待选图片作为待推荐图片。
也就是说,当待选图片的数目超过预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取待推荐图片。
同理,本申请不限制预定图像质量度的具体值。
可以看出,在S504中,当待选图片的数目超过预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中选取待推荐图片,这样存在三种情况,第一种情况,图像质量度达到预设图像质量度的待选图片的数目小于预定图片数目;第二种情况,图像质量度达到预设图像质量度的待选图片的数目等于预定图片数目;第三种情况,图像质量度达到预设图像质量度的待选图片的数目大于预定图片数目。
对于第一种情况,最终得到的待推荐图片的数目(即实际图片数目)小于预定图片数目时,以实际图片数目为准。
对于第二种情况,实际图片数目就是预定图片数目。
对于第三种情况,根据图片的图片质量度由高到低的顺序选择所述预定图片数目的待选图片作为待推荐图片,这样实际图片数目就是预定图片数目,也就是,从所对应图像质量度达到预设图像质量度的待选图片中,选择一部分图片作为待推荐图片。
第三种实现方式,如图6所示。
S601,当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。
也就是说,在将目标信息与数据库中的图片对应的标签进行匹配后,选 择匹配度达到预定匹配度的图片为待选图片。
S602,获取待选图片对应的图像质量度。
S603,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片。
需求强调的是,当待选图片的数目未超过预定图片数目时,将待选图片作为待推荐图片,进而,在确定出待推荐图片后,可以将该推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集。
S604,当待选图片的数目超过预定图片数目时,根据匹配度和图像质量度的综合标准选择符合综合标准的待选图片作为待推荐图片。
也就是说,当待选图片的数目超过预定图片数目时,从符合综合标准的待选图片中,选取待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
首先,图像质量度包括的参数也可以有权重比重,其次,匹配度和图像质量度之间也有权重比例值。
这里的综合标准包括一个综合标准值,用于衡量待选图片是否能够作为待推荐图片的标准值。其中,将图片对应的匹配度乘以匹配度权重值加上该图片对应的图像质量度乘以图像质量度权重值,得到一个综合值,用该综合值与综合标准值进行比较,当该综合值不低于该综合标准值时,表示符合综合标准。
同理,在第三种实现方式中得到的待推荐图片存在与第二种实现方式类似的问题,即符合综合标准的待选图片数目与预定图片数目的大小关系问题,可参考第二种实现方式的解决方案执行。
第四种实现方式,如图7所示。
S701,当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。
也就是说,在将目标信息与数据库中的图片对应的标签进行匹配后,选择匹配度达到预定匹配度的图片为待选图片。
S702,将该待选图片显示在显示区域。
将该待选图片显示在显示区域,以便于用户可以选择图片。
S703,接收用户输入的选择标志。
S704,将具有选择标志的图片作为待推荐图片。
在第四种实现方式中,待推荐图片的数目存在两种方式,第一种方式,设定一个预定图片数目来约束用户选择的图片数目;第二种方式,由用户自行决定选择的图片数目。需要强调的是,这里的用户指具有图片筛选权利的人,也就是,在用户A希望分享一组同主题图片时,该用户A可以自行决定选择的图片数目,而在某一平台希望分享一组同主题图片时,平台的管理人员可以自行决定选择的图片数目,这都是合理的。
通过上述描述可以看出,本申请通过将数据库中图片对应的标签与目标信息进行匹配,可以智能的选择待推荐图片,而免去人工手动主观的去筛选图片。
进一步举例来说,当目标信息包括图片类型-母亲、图片时间-2016/5/8,通过目标信息得到的待推荐图片可以显示如下:
图片一:img01,标签#母亲/mum/mother#,2016/5/8
图片二:img02,标签#母亲/mum/mother#,2016/5/8
图片三:img03,标签#母亲/mum/mother#,2016/5/8。
然后根据上述信息去数据库中获取img01、img02、img03。
可选的,在本申请一些可能的实施方式中,在将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集之前,图片处理方法还包括:确定目标图片填充模板:
第一种方式,根据预定图片数目确定目标图片填充模板。
第二种方式,根据目标信息和预定图片数目确定目标图片填充模板。
第三种方式,根据目标信息和实际图片数目确定目标图片填充模板。
可以理解的是,当预定图片数目作为选择目标图片填充模板的依据时,该预定图片数目可以为随机设定的值或经验值等等。并且,该实际图片数目为所确定出的待推荐图片的数目。
其中,目标信息中包括的信息,如图片类型、图片颜色基调、图片关注度。根据图片类型来选择适合摆放图片的模板。
在本申请中,列举几种图片填充模板。如图8(a)所示,图片填充模板 是中规中矩的方块。如图8(b)所示,图片填充模板为圆形模块。如图8(c)所示,图片填充模板为有横向图片和纵向图片之分的模板。
已上述示出的三种图片模板来说,当目标信息中包括的图片类型为人物,则优先适用图8(a)和图8(b)示出的模板,当待推荐图片中包括横向图片和纵向图片时,则优先适用图8(c)示出的模板。
可选的,在本申请一些可能的实施方式中,将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集,包括:
按照目标图片填充模板中包括的每个框架信息,将待推荐图片对应的放入框架中。
可以理解的是,目标图片填充模板包括至少一个框架信息。框架信息可以是时间顺序、可以是图片大小、可以是图片关注度顺序、可以是图片光线强弱、可以人物所在图片中的比例大小、还可以是图片色彩渐变程度等。
以图8(a)来说,在确定了4张待推荐图片之后,可以按照图片的获取时间(拍摄时间、下载时间等)前后来确定图片所在位置。
以图8(b)来说,在确定了5张待推荐图片之后,可以按照图片关注度的高低来确定图片所在位置,将图片关注度高的图片放在显眼的位置,如C区域,图片关注度由高到低的位置可以是:C>A>B>D>E。
以图8(c)来说,在确定了4张待推荐图片之后,当出现横向图片两张、竖向图片两张时,可以按照图片的尺寸放入图片,当然图片关注度A>D;B>C,两张同尺寸的图片可以按照关注度来确定所在位置。
当根据图片光线强弱来确定图片所在目标图片填充模板中的位置时,可以参考位置顺序,如“一”字、“Z”字、“N”字等,将光线由弱到强依次排布。以图8(a)来说,当是4张待推荐图片时,光线由弱到强依次为A区域、B区域、D区域、C区域,即“Z”字型。
当根据人物所在图片中的比例大小或者图片色彩渐变程度来确定图片所在目标图片填充模板中的位置时,可以参考图片光线强弱来确定图片位置,在此不一一赘述。
上述只是类举一些常见的目标信息,当出现其他信息时,可以参考上述的方式来确定图片所在图片填充模板的位置。
本申请可以有效的解决软件运营人员在云服务器数据库产生的人力。通过自动化的算法识别图片特征,将特定图片进行归类整理。便于图片精准展示,滤掉不需要的图片。同时该发明将杂乱无章的图片,通过统一定义的多种维度筛选,解决人力主观筛选的误差性。在筛选图片得到待推荐图片之后,又可以智能的按照图片类型、图片关注度等信息来确定图片模板来组合这些待推荐图片成一组同主题图片集,提高生成同主题图片集的效率以及图片质量
为了达到上述目的,本申请还提供一种图片处理装置90,如图9所示,该装置90包括获取单元901,确定单元902,生成单元903,存储单元904。
其中,获取单元901,用于获取目标信息,并将目标信息提供给确定单元902,目标信息为表示待推荐图片的主题的信息。
确定单元902,用于根据目标信息筛选存储单元904中存储的图片,确定待推荐图片,并将待推荐图片提供给生成单元903。
生成单元903,用于将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
存储单元904,用于存储图片,以便于确定单元902从中挑选待推荐图片。
可以看出,采用本申请实施例提供的技术方案,在获取到表示待推荐图片的主题的目标信息,以及根据目标信息确定获取到待推荐图片之后,将待推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集,可以解决避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
可选的,在本申请的一种具体实现方式中,在确定单元902根据目标信息筛选数据库中的图片确定待推荐图片之前,获取单元901,还用于获取用户上传的图片,将用户上传的图片提供给存储单元904;获取用户上传的图片中携带的图片信息,图片信息为表示图片属性的信息。
生成单元903,还用于根据图片信息,生成图片信息对应图片的标签,并将生成的图片的标签提供给存储单元904。
存储单元904,用于将该用户上传的图片以及与用户上传的图片对应的标 签进行映射存储。
可选的,在本申请的一种具体实现方式中,在生成单元903将待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集之前,确定单元902,还用于根据预定图片数目确定目标图片填充模板;或者,根据目标信息和预定图片数目确定目标图片填充模板;或者,根据目标信息和实际图片数目确定目标图片填充模板。
可选的,在本申请的一种具体实现方式中,生成单元903,具有用于按照目标图片填充模板中包括的每个框架信息,将待推荐图片对应的放入框架中,得到一组待推荐的同主题图片集。其中,目标图片填充模板包括至少一个框架信息。
进一步的,本申请还提供一种图片处理装置100,如图10所示,该装置100还包括匹配单元905。
匹配单元905,用于将目标信息与数据库中的图片对应的标签进行匹配;然后,确定单元902,用于将匹配成功的图片确定为待推荐图片。也就是说,所述确定单元902,用于根据匹配结果,确定待推荐图片。
进一步的,本申请还提供了一种图片处理装置110,如图11所示,该装置110中的确定单元902包括第一选择模块9021和第一确定模块9022。
第一选择模块9021,用于当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。也就是说,所述第一选择模块9021,用于选择匹配度达到预定匹配度的图片为待选图片。
第一确定模块9022,用于当待选图片的数目未超过预定图片数目时,将待选图片确定为待推荐图片;当待选图片的数目超过预定图片数目时,根据匹配度由高到低的顺序选择预定图片数目的待选图片确定为待推荐图片。
进一步的,本申请还提供了一种图片处理装置120,如图12所示,该装置120中的确定单元902包括第二选择模块9023、第二确定模块9024和第一获取模块9025。
第二选择模块9023,用于当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片。也就是说,所述第二选择模块9023,用于选择匹配度达到预定匹配度的图片为待选图片。
第一获取模块9025,用于获取待选图片对应的图像质量度。
第二确定模块9024,用于当待选图片的数目未超过预定图片数目时,将待选图片确定为待推荐图片;当待选图片的数目超过预定图片数目时,选择图像质量度达到预设图像质量度的待选图片确定为待推荐图片。也就是说,所述第二确定模块9024,用于用于当待选图片的数目未超过预定图片数目时,将待选图片确定为待推荐图片;当待选图片的数目超过预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取待推荐图片。
进一步的,本申请还提供了一种图片处理装置130,如图13所示,该装置130中的确定单元902包括第三选择模块9026,第三确定模块9027,第二获取模块9028。
第三选择模块9026,用于当匹配度达到预定匹配度时,选择达到预定匹配度的图片为待选图片;也就是说,所述第三选择模块9026,用于选择匹配度达到预定匹配度的图片为待选图片;
第二获取模块9028,用于获取待选图片对应的图像质量度;
第三确定模块9027,用于当待选图片的数目未超过预定图片数目时,将待选图片确定为待推荐图片;当待选图片的数目超过预定图片数目时,根据匹配度和图像质量度的综合标准选择符合综合标准的待选图片确定为待推荐图片。也就是说,该第三确定模块9027,用于当待选图片的数目未超过预定图片数目时,将待选图片确定为待推荐图片;当待选图片的数目超过预定图片数目时,从符合综合标准的待选图片中,选取待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
需要说明的是,上述图11至图13中示出的是确定单元902包括的各个模块以及各个模块对应的实现功能,本申请还可以包括一种图片处理装置,该图片处理装置中的确定单元902可以包括第一选择模块9021、第二选择模块9023、第三选择模块9026、第一确定模块9022、第二确定模块9024、第三确定模块9027、第一获取模块9025、第二获取模块9028。
上述描述的装置中其功能实现的详细说明可参照图2至图8示出的方法侧对应的描述,在此不再一一赘述。
进一步的,相应于上述提供的图片处理方法,本申请还提供一种图片处理设备140,如图14所示,图片处理设备140可以包括:处理器1401、存储器1402、通信接口1403和总线1404;
处理器1401、存储器1402和通信接口1403通过总线1404连接并完成相互间的通信;
存储器1402存储可执行程序代码;
处理器1401通过读取存储器1402中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行一种图片处理方法;其中,图片处理方法包括:
获取目标信息,该目标信息为表示待推荐图片的主题的信息;
根据该目标信息筛选数据库中的图片,得到待推荐图片;
将该待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
可以看出,采用本申请实施例提供的技术方案,在获取到表示待推荐图片的主题的目标信息,以及根据目标信息获取到待推荐图片之后,将待推荐图片放入目标图片填充模板中,生成一组待推荐的同主题图片集,可以解决避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
值得说明的是,本申请中图片处理设备可以是云服务器,当然并不局限于此,例如可以为各类终端设备。
相应于上述的图片处理方法,本申请实施例还提供了一种存储介质,其中,该存储介质用于存储可执行程序代码,所述可执行程序代码被运行以执行本申请实施例所述的一种图片处理方法;其中,所述图片处理方法包括:
获取目标信息,所述目标信息为表示待推荐图片的主题的信息;
根据所述目标信息筛选数据库中的图片,得到所述待推荐图片;
将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
本实施例中,存储介质存储有在运行时执行本申请实施例所提供的图片 处理方法的可执行程序代码,能够实现:避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
相应于上述的图片处理方法,本申请实施例还提供了一种应用程序,其中,该应用程序用于在运行时执行本申请实施例所述的一种图片处理方法;其中,所述图片处理方法包括:
获取目标信息,所述目标信息为表示待推荐图片的主题的信息;
根据所述目标信息筛选数据库中的图片,得到所述待推荐图片;
将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
本实施例中,应用程序在运行时执行本申请实施例所提供的图片处理方法,能够实现:能够实现:避免人工筛选图片的步骤,以及避免人工生成待推荐的同主题图片集,提高图片筛选效率的同时,还能减少一定的人工资源。
需要强调的是,对于图片处理设备、应用程序以及存储介质实施例而言,由于其所涉及的方法内容基本相似于前述的方法实施例,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,因为依据本申请,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的装置,可通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方 式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本申请技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,其中,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申请各实施例技术方案的范围。

Claims (19)

  1. 一种图片处理方法,其特征在于,包括:
    获取目标信息,所述目标信息为表示待推荐图片的主题的信息;
    根据所述目标信息筛选数据库中的图片,得到所述待推荐图片;
    将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
  2. 根据权利要求1所述的方法,其特征在于,在所述根据所述目标信息筛选数据库中的图片,得到所述待推荐图片之前,所述方法还包括:
    获取用户上传的图片;
    获取所述用户上传的图片中携带的图片信息,所述图片信息为表示图片属性的信息;
    根据所述图片信息,生成所述图片信息对应图片的标签;
    将所述用户上传的图片以及与所述用户上传的图片对应的标签提供给所述数据库。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述目标信息筛选数据库中的图片,得到所述待推荐图片的步骤,包括:
    将所述目标信息与所述数据库中的图片对应的标签进行匹配;
    根据匹配结果,确定所述待推荐图片。
  4. 根据权利要求3所述的方法,其特征在于,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
    选择匹配度达到预定匹配度的图片为待选图片;
    当所述待选图片的数目未超过预定图片数目时,将所述待选图片作为所述待推荐图片;
    当所述待选图片的数目超过所述预定图片数目时,根据匹配度由高到低的顺序选择所述预定图片数目的待选图片作为所述待推荐图片。
  5. 根据权利要求3所述的方法,其特征在于,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
    选择匹配度达到预定匹配度的图片为待选图片;
    获取所述待选图片对应的图像质量度;
    当所述待选图片的数目未超过预定图片数目时,将所述待选图片作为所述待推荐图片;
    当所述待选图片的数目超过所述预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取所述待推荐图片。
  6. 根据权利要求3所述的方法,其特征在于,所述根据匹配结果,确定所述待推荐图片的步骤,包括:
    选择匹配度达到所述预定匹配度的图片为待选图片;
    获取所述待选图片对应的图像质量度;
    当所述待选图片的数目未超过所述预定图片数目时,将所述待选图片作为所述待推荐图片;
    当所述待选图片的数目超过所述预定图片数目时,从符合综合标准的待选图片中,选取所述待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
  7. 根据权利要求4至6中任一项所述的方法,其特征在于,在所述将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集之前,所述方法还包括:
    根据所述预定图片数目确定所述目标图片填充模板;或者,
    根据所述目标信息和所述预定图片数目确定所述目标图片填充模板;或者,
    根据所述目标信息和实际图片数目确定所述目标图片填充模板。
  8. 根据权利要求1所述的方法,其特征在于,所述目标图片填充模板包括至少一个框架信息;
    所述将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集的步骤,包括:
    按照所述目标图片填充模板中包括的每个框架信息,将所述待推荐图片对应的放入框架中,得到一组待推荐的同主题图片集。
  9. 一种图片处理装置,其特征在于,包括:
    获取单元,用于获取目标信息,并将所述目标信息提供给确定单元,所述目标信息为表示待推荐图片的主题的信息;
    所述确定单元,用于根据所述目标信息筛选存储单元中存储的图片,确定所述待推荐图片,并将所述待推荐图片提供给生成单元;
    所述生成单元,用于将所述待推荐图片放入目标图片填充模板,生成一组待推荐的同主题图片集。
  10. 根据权利要求9所述的装置,其特征在于,
    所述获取单元,还用于获取用户上传的图片,将所述用户上传的图片提供给所述存储单元;获取所述用户上传的图片中携带的图片信息,所述图片信息为表示图片属性的信息;
    所述生成单元,还用于根据所述图片信息,生成所述图片信息对应图片的标签,并将生成的图片的标签提供给所述存储单元;
    所述存储单元,用于将所述用户上传的图片以及与所述用户上传的图片对应的标签进行映射存储。
  11. 根据权利要求10所述的装置,其特征在于,所述装置还包括:匹配单元;
    所述匹配单元,用于将所述目标信息与所述数据库中的图片对应的标签进行匹配;
    所述确定单元,还用于根据匹配结果,确定所述待推荐图片。
  12. 根据权利要求11所述的装置,其特征在于,所述确定单元包括:第一选择模块和第一确定模块;
    所述第一选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
    所述第一确定模块,用于当所述待选图片的数目未超过预定图片数目时,将所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,根据匹配度由高到低的顺序选择所述预定图片数目的待选图片确定为所述待推荐图片。
  13. 根据权利要求11所述的装置,其特征在于,所述确定单元包括:第二选择模块,第二确定模块和第一获取模块;
    所述第二选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
    所述第一获取模块,用于获取所述待选图片对应的图像质量度;
    第二确定模块,用于当所述待选图片的数目未超过预定图片数目时,将 所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,从所对应图像质量度达到预设图像质量度的待选图片中,选取所述待推荐图片。
  14. 根据权利要求11所述的装置,其特征在于,所述确定单元包括:第三选择模块,第三确定模块和第二获取模块;
    所述第三选择模块,用于选择匹配度达到预定匹配度的图片为待选图片;
    所述第二获取模块,用于获取所述待选图片对应的图像质量度;
    所述第三确定模块,用于当所述待选图片的数目未超过所述预定图片数目时,将所述待选图片确定为所述待推荐图片;当所述待选图片的数目超过所述预定图片数目时,从符合综合标准的待选图片中,选取所述待推荐图片,其中,所述综合标准为与匹配度和图像质量度两者相关的标准。
  15. 根据权利要求12-14任一项所述的装置,其特征在于,
    所述确定单元,还用于根据所述预定图片数目确定所述目标图片填充模板;或者,根据所述目标信息和所述预定图片数目确定所述目标图片填充模板;或者,根据所述目标信息和实际图片数目确定所述目标图片填充模板。
  16. 根据权利要求9所述的装置,其特征在于,所述目标图片填充模板包括至少一个框架信息;
    所述生成单元,具有用于按照所述目标图片填充模板中包括的每个框架信息,将所述待推荐图片对应的放入框架中,得到一组待推荐的同主题图片集。
  17. 一种图片处理设备,其特征在于,包括:处理器、存储器、通信接口和总线;
    所述处理器、所述存储器和所述通信接口通过所述总线连接并完成相互间的通信;
    所述存储器存储可执行程序代码;
    所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程序,以用于执行权利要求1至8中任一项所述的一种图片处理方法。
  18. 一种存储介质,用于存储可执行程序代码,所述可执行程序代码被 运行以执行权利要求1至8中任一项所述的一种图片处理方法。
  19. 一种应用程序,其特征在于,所述应用程序用于在运行时执行权利要求1至8中任一项所述的一种图片处理方法。
PCT/CN2017/075748 2016-05-18 2017-03-06 一种图片处理方法、装置及设备 WO2017197959A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610331774.1A CN105975612A (zh) 2016-05-18 2016-05-18 一种图片处理方法、装置及设备
CN201610331774.1 2016-05-18

Publications (1)

Publication Number Publication Date
WO2017197959A1 true WO2017197959A1 (zh) 2017-11-23

Family

ID=56957054

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/075748 WO2017197959A1 (zh) 2016-05-18 2017-03-06 一种图片处理方法、装置及设备

Country Status (2)

Country Link
CN (1) CN105975612A (zh)
WO (1) WO2017197959A1 (zh)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975612A (zh) * 2016-05-18 2016-09-28 北京金山安全软件有限公司 一种图片处理方法、装置及设备
CN106791912B (zh) * 2016-12-28 2020-07-03 Tcl科技集团股份有限公司 一种海报图片匹配方法及系统
CN109582401B (zh) * 2017-09-27 2021-08-24 腾讯科技(深圳)有限公司 推广图片生成方法、装置、存储介质和计算机设备
CN109064526A (zh) * 2018-06-07 2018-12-21 珠海格力电器股份有限公司 一种生成拼图的方法及装置
CN108804667B (zh) * 2018-06-08 2021-11-02 百度在线网络技术(北京)有限公司 用于呈现信息的方法和装置
CN108986026A (zh) * 2018-06-25 2018-12-11 努比亚技术有限公司 一种图片拼接方法、终端及计算机可读存储介质
CN108965745B (zh) * 2018-06-27 2021-01-12 Oppo广东移动通信有限公司 回忆视频创建方法及相关装置
CN108920591A (zh) * 2018-06-27 2018-11-30 Oppo广东移动通信有限公司 回忆视频创建方法及相关装置
CN108989703B (zh) * 2018-06-28 2021-04-06 Oppo广东移动通信有限公司 回忆视频创建方法及相关装置
CN109241303B (zh) * 2018-06-29 2022-10-21 Oppo广东移动通信有限公司 视频创建方法及相关产品
CN108924439B (zh) * 2018-07-10 2021-07-09 Oppo广东移动通信有限公司 图像处理方法及相关产品
CN109068070A (zh) * 2018-07-10 2018-12-21 Oppo广东移动通信有限公司 视频生成方法及相关装置
CN112312189B (zh) * 2019-08-02 2023-07-14 百度在线网络技术(北京)有限公司 一种视频生成方法及视频生成系统
CN111209424B (zh) * 2020-01-10 2023-05-12 北京字节跳动网络技术有限公司 一种图片展示方法及装置
CN111552826B (zh) * 2020-05-06 2023-09-29 深圳市卡牛科技有限公司 示例图片的生成方法、装置、计算机设备及存储介质
CN111669620A (zh) * 2020-06-05 2020-09-15 北京字跳网络技术有限公司 主题视频生成方法、装置、电子设备及可读存储介质
CN115205416B (zh) * 2022-08-12 2023-06-09 广州鼎甲计算机科技有限公司 图像生成方法、装置、计算机设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102024050A (zh) * 2010-12-16 2011-04-20 浙江大学 一种网页浏览方法
CN103685498A (zh) * 2013-12-06 2014-03-26 北京奇虎科技有限公司 一种壁纸的加载方法和浏览器装置
KR20150015062A (ko) * 2013-07-30 2015-02-10 주식회사 케이티 이미지를 추천하는 장치 및 방법
CN104469141A (zh) * 2013-09-24 2015-03-25 富士胶片株式会社 图像处理装置以及图像处理方法
CN105975612A (zh) * 2016-05-18 2016-09-28 北京金山安全软件有限公司 一种图片处理方法、装置及设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102930522B (zh) * 2012-11-12 2015-11-25 北京奇虎科技有限公司 一种实现图片拼接的装置和方法
CN104881844B (zh) * 2015-06-29 2017-12-29 北京金山安全软件有限公司 一种图片组合的方法、装置以及终端设备
CN105512255A (zh) * 2015-12-01 2016-04-20 上海斐讯数据通信技术有限公司 图片筛选方法及装置、移动终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102024050A (zh) * 2010-12-16 2011-04-20 浙江大学 一种网页浏览方法
KR20150015062A (ko) * 2013-07-30 2015-02-10 주식회사 케이티 이미지를 추천하는 장치 및 방법
CN104469141A (zh) * 2013-09-24 2015-03-25 富士胶片株式会社 图像处理装置以及图像处理方法
CN103685498A (zh) * 2013-12-06 2014-03-26 北京奇虎科技有限公司 一种壁纸的加载方法和浏览器装置
CN105975612A (zh) * 2016-05-18 2016-09-28 北京金山安全软件有限公司 一种图片处理方法、装置及设备

Also Published As

Publication number Publication date
CN105975612A (zh) 2016-09-28

Similar Documents

Publication Publication Date Title
WO2017197959A1 (zh) 一种图片处理方法、装置及设备
EP3907657A1 (en) A digital media frame and method for configuring a field of view of a digital media frame
US10979624B2 (en) Methods and devices for establishing photographing template database and providing photographing recommendation information
JP6850291B2 (ja) 顔認識アプリケーションにおけるフォールスポジティブの最小化のための方法および装置
CN106776662B (zh) 一种照片的分类整理方法和装置
US11538096B2 (en) Method, medium, and system for live preview via machine learning models
CN110276366A (zh) 使用弱监督模型来检测对象
US20120321131A1 (en) Image-related handling support system, information processing apparatus, and image-related handling support method
CN108961157B (zh) 图片处理方法、图片处理装置及终端设备
US20160104054A1 (en) Saliency Map Computation
WO2019233256A1 (zh) 人脸贴图生成方法、装置、可读存储介质及移动终端
CN106021405A (zh) 生成相册封面的方法及装置
CN113870133B (zh) 多媒体显示及匹配方法、装置、设备及介质
WO2017143852A1 (zh) 一种图片处理方法、装置及电子设备
US20170352175A1 (en) Picture processing method and apparatus
CN111182196A (zh) 拍照预览方法、智能终端及具有存储功能的装置
CN109753873A (zh) 图像处理方法及相关装置
WO2016082470A1 (zh) 一种图片处理方法、装置及计算机存储介质
US11442980B2 (en) System and method for photo scene searching
WO2015196681A1 (zh) 一种图片处理方法及电子设备
CN107169093B (zh) 一种目标图像的获取方法及装置
WO2017143846A1 (zh) 一种图片备份方法、装置及电子设备
CN109636711B (zh) 漫画册生成方法、装置及计算机可读存储介质
CN113793252B (zh) 图像处理方法、装置、芯片及其模组设备
CN111738087B (zh) 一种游戏角色面部模型的生成方法和装置

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 17798525

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25.02.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17798525

Country of ref document: EP

Kind code of ref document: A1