JP6622168B2 - Image composition apparatus, image composition method, and program - Google Patents

Description

  The present invention relates to an image synthesizing apparatus, an image synthesizing method, and a program capable of presenting a template suitable for the user's preference to the user.

  Conventionally, digital contents (hereinafter referred to as “image collections”) composed of a plurality of pages have been created and enjoyed by collecting a plurality of images obtained by photographing with a digital camera, a smartphone or the like. The created image collection can be browsed by being displayed on a display device in addition to printing and browsing. The image collection is called “album”, “book”, “collection”, and the like. Depending on the application and browsing mode, it may be called “calendar”, “slide show”, or the like.

  In order to create an image collection, for example, a plurality of templates are displayed and the user selects a favorite template, and a plurality of images are displayed and the user selects a favorite image. Here, the template generally includes information indicating the arrangement position of the image. When the user selects a favorite template and a favorite image, the user's favorite image is automatically selected with respect to the user's favorite template. Can be arranged.

  Various techniques for automatically selecting a template from a plurality of templates have been proposed.

  Patent Document 1 describes that a template selection history is stored for each user, and a plurality of templates are displayed side by side in descending order of the number of past selections for each user. Further, Patent Document 1 also describes that a plurality of templates are displayed side by side in descending order of the number of past selections for each season.

  Patent Document 2 describes that the degree of matching of an image with a template is determined by comparing the attribute information previously given to the template by the template creator or the like with the attribute information of the image placed on the template. Yes.

  Patent Document 3 describes that an event theme is determined based on a feature amount extracted from an image, and a design indicating a ground pattern and a color of a template is determined based on the event theme. For example, when the event theme is a ski trip, a ground pattern showing a snow crystal is determined.

  Patent Document 4 describes that an atmosphere and an impression of an image group are analyzed and a template is selected based on the analysis result. For example, the feature quantity of the “dynamic-static” axis is obtained from the ratio of images mainly composed of non-human subjects, and the characteristic of the “emotional-reasonable” axis is calculated from the ratio of images showing a smiling person. A quantity is obtained, and a template with a name corresponding to the feature quantity is selected.

  Patent Document 5 describes that an image is arranged on a template based on an event name (for example, “travel”, “growth record”) input by a user. For example, in the case of “Travel”, the background of the person is also important, so the face area of the person is not made as large as the “growth record” and the shooting dates and times are adjacent so that multiple images with similar colors do not approach each other Are arranged apart from each other on the template.

Japanese Patent Laid-Open No. 10-232917 JP 2016-34098 A Japanese Patent No. 5214825 JP 2011-170690 A JP 2014-016825 A

  However, there are cases where a template that matches the actual user's preference cannot be presented.

  Since the technique described in Patent Document 1 merely displays a plurality of templates in order from the largest number of past selections for each user, there is a possibility that a template contrary to the user's preference may be preferentially displayed. It was. For example, when a user requests an image book on the theme of marriage, even if the user preferentially displays a template selected when creating an image book of another theme (for example, ski trip), the displayed template is not displayed. There is a possibility that the user does not want to use it for an image collection whose theme is marriage. Similarly, even if a plurality of templates are arranged and displayed in order of increasing past selection frequency for each season, there is a possibility that a template contrary to the user's preference is displayed with priority.

  Since the technique described in Patent Document 2 simply compares attribute information previously given to a template with attribute information of a selection target image, even if a template that matches the intention of the template creator can be determined, A template that matches the preferences of the user who is the orderer of the collection is not always determined.

  The technique described in Patent Document 3 merely determines the event theme based on the feature amount extracted from the image and determines the design indicating the background pattern and color of the template. The technique described in Patent Document 4 The technique described in Patent Document 5 merely arranges an image on a template based on an event name input by a user, and only selects a template by analyzing the atmosphere and impression of the image group. In the technology, a template that matches the user's preference is not always displayed to the user.

  Based on the correspondence between predetermined themes and templates, there is known a technique for presenting to the user which template is suitable for such a theme, but a template that matches the actual user's preference is known. It is not always possible to present it.

  An object of the present invention is to provide an image composition device, an image composition method, and a program capable of presenting a template suitable for the user's preference to the user.

  In order to achieve the above-described object, an image composition device according to the first aspect of the present invention includes an image acquisition unit that acquires an image, an attribute information acquisition unit that acquires attribute information about the acquired image, and a plurality of templates. A storage unit that stores information, a display unit, a template determination unit that determines a template to be displayed to the user among a plurality of stored templates, a display control unit that displays the determined template on the display unit, and a display An instruction input unit that receives an instruction indicating whether or not to use the template that has been adopted from the user, an image synthesis unit that synthesizes the template designated by the user and the obtained image, and the acquired attribute information to the user A storage control unit that stores in the storage unit in association with the instructed template, and the template determination unit includes the unsynthesized image and the unsynthesized image. If the attribute information about is acquired, based on the attribute information stored in the storage unit in association with the attribute information and the template for the image of non-composed and determines the template to be displayed to the user.

  According to this aspect, the attribute information related to the synthesized image is stored in the storage unit in association with the template instructed to be adopted by the user, and the unsynthesized image and the attribute information related to the unsynthesized image are acquired. In this case, the template to be displayed to the user is determined based on the attribute information regarding the unsynthesized image and the attribute information of the synthesized image stored in the storage unit in association with the template. Template can be presented to the user. That is, by accumulating the association between the template adopted by the user and the attribute information related to the combined image, it is possible to present the template that matches the actual user's preference to the user.

  In the image composition device according to the second aspect of the present invention, the attribute information acquisition unit acquires attribute information of a plurality of items related to the acquired image, and the template determination unit includes attribute information about the unsynthesized image in the plurality of items. And the attribute information stored in the storage unit in association with the template to determine a template to be displayed to the user.

  The image composition device according to the third aspect of the present invention includes an evaluation value calculation unit that calculates an evaluation value for each combination of each of the attribute information of a plurality of items and a template, and the template determination unit includes the calculated evaluation value The template to be displayed to the user is determined based on the above. According to this aspect, the evaluation value is calculated so that the attribute information is highly relevant to the template (that is, the possibility that the template is likely to be adopted by the user). It becomes possible to recommend to.

  In the image composition device according to the fourth aspect of the present invention, an evaluation value calculation unit for calculating an evaluation value for each combination of attribute information of a plurality of items and a template, an evaluation value, and weight information for each of the plurality of items And a comprehensive evaluation value calculation unit that calculates a comprehensive evaluation value for each template with respect to the attribute information of a plurality of items, and the template determination unit displays to the user based on the calculated comprehensive evaluation value Determine the template. According to this aspect, the comprehensive evaluation value is weighted to determine which item is important for each template by calculating the comprehensive evaluation value, so that a more appropriate template can be recommended to the user.

  In the image composition device according to the fifth aspect of the present invention, the storage control unit deletes, from the storage unit, a template whose comprehensive evaluation value is continuously equal to or less than the threshold value for a certain period from the stored templates. According to this aspect, it is possible to organize templates that are not often used, and to improve visibility.

  In the image composition device according to the sixth aspect of the present invention, the display control unit displays a plurality of templates in descending order of the comprehensive evaluation value. According to this aspect, it is possible to recommend a plurality of templates to the user while making it easy to see the optimum template.

  In the image composition device according to the seventh aspect of the present invention, the storage control unit receives a template change instruction indicating that the template determined by the template determination unit is not adopted and a template different from the determined template is adopted. If accepted, the template instructed to be adopted is more strongly associated with the attribute information than when the determined template is associated with the attribute information. According to this aspect, since the template selected by the user spontaneously upon feedback of the user instruction is regarded as important, it is possible to recommend a more appropriate template to the user.

  In the image composition device according to the eighth aspect of the present invention, the storage control unit receives a template change instruction indicating that the template determined by the template determination unit is not adopted and a template different from the determined template is adopted. If accepted, the weight information is changed. According to this aspect, since the user's preference tendency is learned more appropriately, it is possible to recommend a more appropriate template to the user.

  In the image composition device according to the ninth aspect of the present invention, the storage control unit includes the theme information of the composite image of the acquired image and the template, the text information for the composite image, the object information in the acquired image, the user's At least one item of attribute information among age information, user gender information, user family information, and user residence information is stored in the storage unit in association with the template.

  The image composition device according to the tenth aspect of the present invention includes an image analysis unit that recognizes the content of the acquired image by image analysis, and the storage control unit receives attribute information indicating the content of the recognized image as a template. And stored in the storage unit. According to this aspect, since the user's preference tendency is learned more appropriately according to the content of the image, it is possible to recommend a more appropriate template to the user.

  In the image synthesizing device according to the eleventh aspect of the present invention, the image synthesizing unit synthesizes the template and the image for a plurality of pages, and the template determining unit performs the processing for at least one page among the plurality of pages. Determine the template. According to this aspect, it is possible to recommend an appropriate template to the user when creating an image collection consisting of a plurality of pages.

  In the image composition device according to the twelfth aspect of the present invention, the template determination unit determines a plurality of templates to be displayed to the user, and the display control unit displays the plurality of templates determined for the user, and inputs an instruction. The unit receives an instruction from the user indicating one template to be adopted from among the plurality of displayed templates.

  In the image composition device according to the thirteenth aspect of the present invention, the storage control unit stores the decoration added to the template in accordance with the user's instruction in association with the template, and the display control unit is associated with the determined template. Display the decoration to the user.

  In the image composition device according to the fourteenth aspect of the present invention, the display control unit displays two or more templates including the determined template among the plurality of templates stored in the display unit, and displays the determined template. Display at the top.

  In the image composition device according to the fifteenth aspect of the present invention, the storage control unit associates the attribute information with the template when the user satisfies a predetermined condition. According to this aspect, a user who does not want to learn can be excluded from the learning target.

  In the image composition device according to the sixteenth aspect of the present invention, the storage control unit associates the attribute information with the template at regular intervals. According to this aspect, it is possible to prevent the template determination result from changing during the user's work, so that an effect that does not give the user a sense of incongruity can be expected.

  In the image synthesizing method according to the seventeenth aspect of the present invention, the step of acquiring an image, the step of acquiring attribute information relating to the acquired image, and displaying to the user among a plurality of templates stored in the storage unit A step of determining a template to be performed, a step of displaying the determined template on the display unit, a step of accepting an instruction indicating whether or not to employ the displayed template, and a template instructed by the user are acquired. And a step of storing the acquired attribute information in a storage unit in association with a template instructed by the user, and the step of determining the template includes the step of determining the template If attribute information related to the image is acquired, attribute information related to the unsynthesized image and the template Association with on the basis of the attribute information stored in the storage unit, determines the template to be displayed to the user.

  In the program according to the eighteenth aspect of the present invention, a step of acquiring an image, a step of acquiring attribute information relating to the acquired image, and a template to be displayed to the user among a plurality of templates stored in the storage unit A step of displaying the determined template on the display unit, a step of accepting an instruction indicating whether or not to use the displayed template, a template instructed by the user, and an acquired image And a step of causing the computer to execute a step of associating the acquired attribute information with a template instructed by the user and storing the attribute information in a storage unit, and determining a template. Attribute information about the unsynthesized image Based on the attribute information stored in the storage unit in association with the template and determines the template to be displayed to the user.

  ADVANTAGE OF THE INVENTION According to this invention, the template suitable for a user's liking can be shown with respect to a user.

FIG. 1 is a block diagram illustrating a configuration example of an image composition apparatus according to the first embodiment. FIG. 2 is a flowchart illustrating an exemplary flow of image composition processing according to the first embodiment. FIG. 3 is a diagram illustrating an example of a theme selection screen. FIG. 4 is a diagram showing a first editing screen. FIG. 5 is a diagram showing a first template list screen. FIG. 6 is a diagram showing a second template list screen. FIG. 7 is a diagram showing a background color selection screen. FIG. 8 is a diagram showing a second editing screen. FIG. 9 shows a stamp list screen. FIG. 10 is a diagram showing a font instruction screen. FIG. 11 is a diagram illustrating an example of a log according to the first embodiment. FIG. 12 is a block diagram illustrating a configuration example of the image composition apparatus according to the second embodiment. FIG. 13 is a flowchart illustrating a flow of an example of an image composition process according to the second embodiment. FIG. 14 is a diagram illustrating an example of a log according to the second embodiment. FIG. 15 is a block diagram illustrating a configuration example of the image composition apparatus according to the third embodiment. FIG. 16 is an explanatory diagram illustrating an example of a template evaluation value table according to the third embodiment. FIG. 17 is a flowchart illustrating an exemplary flow of an image composition process according to the third embodiment. FIG. 18 is a block diagram illustrating a configuration example of an image composition device according to the fourth embodiment. FIG. 19 is an explanatory diagram illustrating an example of a template evaluation value table according to the fourth embodiment. FIG. 20 is an explanatory diagram illustrating an example of a template comprehensive evaluation value table according to the fourth embodiment. FIG. 21 is a flowchart illustrating an example of an image composition process according to the fourth embodiment. FIG. 22 is an explanatory diagram used for explaining a case where a plurality of items are grouped and weight information is changed.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, embodiments for carrying out an image synthesis apparatus, an image synthesis method, and a program according to the present invention will be described with reference to the accompanying drawings.

<First Embodiment>
FIG. 1 is a block diagram showing a configuration example of an image composition apparatus according to the first embodiment of the present invention.

  The image composition device 10 of this example is configured by a computer device. Examples of computer devices include personal computers, tablet terminals, and smartphones. You may use computer apparatuses other than these.

  The image composition device 10 of this example includes an image acquisition unit 12 that acquires an image, a display unit 14 that can display an image, an instruction input unit 16 that receives an instruction from a user, a program, and information necessary for executing the program. A storage unit 20 that stores data and a CPU (central processing unit) 30 that executes programs are configured.

  The image acquisition unit 12 can be configured by a device that inputs a digital signal. As such a device, for example, a communication device that performs wireless communication or wired communication can be used. You may use the device which can acquire an image from storage media, such as a memory card.

  The display unit 14 is configured by a display device such as a liquid crystal display device.

  The instruction input unit 16 can be configured by a touch panel, for example. A keyboard and mouse may be used, or other user interfaces may be used. A voice input device may be used.

  The storage unit 20 includes a temporary storage device such as a RAM (random access memory) and a non-temporary storage device such as a ROM (read only memory) or an EEPROM (electrically erasable programmable read only memory). The program is stored in a non-transitory storage device. You may memorize | store a program in non-temporary storage devices other than these.

  The storage unit 20 of this example stores a plurality of templates. The template includes image arrangement information indicating image arrangement, background design (color, pattern, etc.) or background design information indicating a back image, and decoration design information indicating decoration (frame, stamp, text, etc.). In the present invention, the template may include any one of image arrangement information, background design information, and decoration design information, or the template may include information other than these. That is, the template may be a composition target to be synthesized with the acquired image.

  The CPU 30 stores the image analysis unit 32 that performs image analysis on the image acquired by the image acquisition unit 12, the attribute information acquisition unit 34 that acquires attribute information related to the image acquired by the image acquisition unit 12, and the storage unit 20. The template determination unit 36 that determines a template to be displayed to the user (hereinafter referred to as “recommended template”), a display control unit 38 that controls the display unit 14, and the instruction input unit 16. Instruct the user about the attribute information acquired by the image composition unit 40 and the attribute information acquisition unit 34 that synthesizes a template (hereinafter referred to as “adopted template”) instructed by the user and the image acquired by the image acquisition unit 12. And a storage control unit 42 that is stored in the storage unit 20 in association with the adopted template.

  The image analysis unit 32 of this example evaluates the image acquired by the image acquisition unit 12 by image analysis. For example, the image quality of the image is evaluated.

  The attribute information acquisition unit 34 of this example can acquire various attribute information. The “attribute information” is not limited to the attribute information added to the acquired image. For example, information instructed by the user (hereinafter referred to as “user instruction information”) can be acquired as attribute information about the image. Specifically, for example, theme information selected by the user and text information (title, comment, keyword, etc.) input by the user are examples of the user instruction information. Also, information indicating the image analysis result (hereinafter referred to as “image analysis information”) can be acquired as attribute information about the image. Note that a case where information (object information) indicating an object (subject image) in an image is acquired as attribute information will be described in a second embodiment described later. You may acquire the attribute information (henceforth "user information") of the user who is the orderer of an image collection as attribute information regarding an image. For example, user age information, user gender information, user family information, and user residence information are examples of user information. In this specification, “attribute information related to an image” will be described as an example including at least one of the above-mentioned “user instruction information”, “image analysis information”, and “user information”. The “attribute information” is not limited to such a case. Information that is related to the acquired image and that is estimated to be related to the adoption of the template may be used as “attribute information related to the image”. Further, the information related to each acquired image is not limited, and information related to the entire image collection or information related to a part of the composite image in the image collection may be used as “attribute information related to the image”.

  The template determination unit 36 of this example recommends a template to be displayed to the user based on attribute information related to an image that has not been combined by the image combining unit 40 and attribute information stored in the storage unit 20 in association with the template. To decide.

  The attribute information is not limited to one item. The attribute information acquisition unit 34 acquires attribute information of a plurality of items related to the unsynthesized image, and the template determination unit 36 stores the attribute information of the plurality of items related to the unsynthesized image and the template in association with the template. The template to be displayed to the user may be determined by comparing the attribute information of the plurality of items.

  The display control unit 38 of this example causes the display unit 14 to display the recommended template determined by the template determination unit 36. The instruction input unit 16 in this example receives an instruction from the user indicating whether or not to adopt the recommended template while the recommended template is displayed.

  A specific example of image composition by the image composition unit 40 will be described in detail later.

  When the storage control unit 42 of this example receives a template change instruction indicating that the recommended template determined by the template determining unit 36 is not adopted and a non-recommended template different from the recommended template is adopted, Rather than associating the recommended template with the attribute information, the non-recommended template instructed to be adopted is more strongly associated with the attribute information.

  FIG. 2 is a flowchart showing a flow of an example of the image composition processing of the first embodiment to which the image composition method of the present invention is applied. This process is executed by the CPU 30 according to the program stored in the storage unit 20.

  First, a plurality of images are acquired by the image acquisition unit 12 (step S2).

  Next, the acquired image is analyzed by the image analysis unit 32 (step S4). In this example, the image quality of the image is evaluated.

  Next, attribute information about each acquired image is acquired by the attribute information acquisition unit 34 (step S6). In this example, the theme selection screen STM shown in FIG. 3 is displayed on the display unit 14, and the instruction input unit 16 accepts selection of the image collection theme from the user who is the orderer of the image collection. Get one theme information. In FIG. 3, two themes “marriage” and “travel” are illustrated as examples of major themes, but other themes may be used, and the number of themes is not limited. FIG. 3 shows four examples of “simple”, “art”, “cool”, and “chic” as subcategory examples in “marriage”, and “city”, “ Three are shown: “Beach” and “Forest”. Input of text information indicating the title of the image collection may be accepted as attribute information related to the image. Moreover, the attribute information acquisition part 34 of this example acquires age information, sex information, family structure information, and residence information as user information. Such user information may be stored in the storage unit 20 in advance or may be acquired in this step. Moreover, you may acquire the attribute information added to the image.

  Next, the template determination unit 36 determines a template (recommended template) to be displayed to the user from among a plurality of templates stored in the storage unit 20 (step S8). The template determining unit 36 of this example compares the attribute information of a plurality of items related to an unsynthesized image with the attribute information of the plurality of items stored in the storage unit 20 in association with the template, and determines a recommended template. If there is no template corresponding to the attribute information acquired in step S6, a default template is determined as a recommended template.

  Next, the recommended template is displayed on the display unit 14 by the display control unit 38 (step S10). In this example, the first editing screen SE1 shown in FIG. The first editing screen SE1 is provided with a template display area A11 in which recommended templates are displayed.

  Next, the instruction input unit 16 receives an instruction indicating whether or not to adopt the recommended template from the user (step S12).

  It is determined whether or not the recommended template (the template displayed on the display unit 14) is an adoption instruction (OK instruction) or a non-recruitment instruction (NG instruction) (step S14). (NO in step S14), the display control unit 38 displays a plurality of templates stored in the storage unit 20 different from the recommended template on the display unit 14 (step S16), and an instruction input unit. 16, an instruction to select an adopted template from a plurality of newly displayed templates is received (step S <b> 18). In this example, when the OK button B11 is operated on the first editing screen SE1 of FIG. 4, it is determined that the instruction is an adoption instruction (OK instruction), and is not adopted when the layout change button B12 is operated. It is determined that it is an instruction (NG instruction). When the layout change button B12 is operated, the first template list screen ST1 shown in FIG. In this example, four templates T1, T2, T3, and T4 are displayed on the first template list screen ST1. The check mark MC indicates that the recommended template is determined in step S8 and displayed in the template display area A11 of the first editing screen SE1 in FIG. When the next screen button B21 of the first template list screen ST1 is operated, the second template list screen ST2 shown in FIG. 6 is displayed. In this example, four templates T5, T6, T7, and T8 are displayed on the second template list screen ST2. In this example, only eight templates T1 to T8 are shown, but the number of selectable templates is not limited. When the previous screen button B22 of the second template list screen ST2 is operated, the first template list screen ST1 of FIG. 5 is displayed.

  Further, in this example, when the background color change button B13 is operated on the first editing screen SE1 of FIG. 4, the background color selection screen SB shown in FIG. The check mark MC indicates that the background color is currently selected.

  If it is an adoption instruction (OK instruction) with respect to the recommended template, that is, if YES in step S14, the adoption template (for example, the template of the code T3) and the image acquired in step S2 are synthesized by the image synthesis unit 40. (Step S20), the composite image is displayed on the display unit 14 (Step S22).

  In this example, when the OK button B11 is operated on the first editing screen SE1 shown in FIG. 4, that is, when an adoption instruction is input for the recommended template, the second editing screen SE2 shown in FIG. Is displayed on the display unit 14. The second editing screen SE2 is provided with a composite image display area A21 where the composite image 60 is displayed.

  Next, an instruction regarding decoration of the composite image 60 is received by the instruction input unit 16 (step S24).

  In this example, when the stamp addition button B14 is operated on the second editing screen SE2 of FIG. 8, the stamp list screen SS shown in FIG. The user can add a favorite stamp as a decoration to the composite image 60 in FIG. 8 by designating a favorite stamp from a plurality of stamps in the stamp list screen SS. In this example, when the font instruction button B15 is operated on the second editing screen SE2 in FIG. 8, the font instruction screen SF shown in FIG. In the font instruction screen SF, the user can instruct the font type by operating the font selection scroll bar BF, and can instruct the font color by operating the color selection scroll bar BC. In addition, it is possible to instruct in the font instruction screen SF whether to make it bold or italic, font size, display style, and the like.

  Next, the attribute information acquired in step S2 is stored by the storage control unit 42 in association with a template (adopted template, for example, a template with the code T3) designated by the user (step S26).

  FIG. 11 is a diagram showing an example of a log (history information) created by the storage control unit 42 of this example. It can be said that the log is information stored by associating attribute information related to the combined image and the adopted template. The log 70 of this example includes an order log 72 and an operation log 74. The order log 72 of this example includes, as user information, age information indicating the user's age or age, gender information indicating the user's gender, family structure information indicating the user's family structure, and residence indicating the user's residence. Including location information. The operation log 74 of this example is extracted from the theme information indicating the theme of the image book and the text information input by the user (the title of the image book, the comment for each image, the title and the comment) as user instruction information for the image. Keyword), template information indicating the adopted template specified by the user, font information indicating the font specified by the user, and stamp information indicating the stamp specified by the user.

  Next, it is determined whether or not to continue the present process (step S28). If it is determined to continue the present process (in the case of YES), the process returns to step S2.

  In step S2, a new unsynthesized image is acquired. In step S6, attribute information related to the unsynthesized image is acquired. In step S8, attribute information related to the new unsynthesized image and a template are associated with the template. Based on the attribute information stored in the template 20, a template (recommended template) to be displayed to the user is determined. That is, in step S10, it is possible to display to the user a template that matches the user's preference and that is suitable for a new unsynthesized image among the plurality of templates stored in the storage unit 20.

  If it is determined in step S28 that the process is not continued (NO), the process is terminated.

  According to the present embodiment, it is possible to present to the user a template that suits the user's preference by learning to associate the template adopted by the user with the attribute information related to the combined image. That is, compared with the case where the template and the attribute information are associated unconditionally in advance, the present embodiment accumulates the association between the adopted template and the attribute information related to the combined image, thereby It is possible to present a template suitable for the user to the user.

  In the above-described image composition processing example, the strength of association between the adopted template and the attribute information may be set. Specifically, when a template change instruction indicating that the recommended template determined by the template determining unit 36 is not adopted and a non-recommended template different from the recommended template is accepted is received, the recommended template is received. Compared to the attribute information, the non-recommended template instructed to be adopted is more strongly associated with the attribute information. In other words, the template selected spontaneously by the user is regarded as important. The association strength may be set to “1” when the recommended template is changed, and the association strength may be set to “0” (zero) when the recommended template is adopted. As a result, the user's instruction feedback is applied and the template spontaneously selected by the user is regarded as important, so that a more appropriate template can be recommended to the user.

  Further, in the above-described image composition processing example, image composition is not limited to the case where a template and an image are composed for one page.

  The image composition unit 40 may compose the template and the image for a plurality of pages. The template determination unit 36 determines a template for at least one of the plurality of pages.

  In the above-described image composition processing example, the case where one template is determined by the template determination unit 36 has been described as an example, but the present invention is not limited to such a case.

  The template determination unit 36 determines a plurality of templates to be displayed to the user, the display control unit 38 displays the plurality of templates determined for the user, and the instruction input unit 16 displays the plurality of templates displayed. It is good also as a structure which receives the instruction | indication which shows one template employ | adopted from from a user.

  Further, the decoration added to the adopted template in accordance with the user instruction is stored by the storage control unit 42 in association with the adopted template, and the decoration associated with the adopted template is displayed to the user by the display control unit 38. It is good as composition. For example, the stamp and font described above are associated with the adopted template and stored in the storage unit 20 and displayed to the user as a recommended stamp and a recommended font when editing an unsynthesized image.

<Second Embodiment>
FIG. 12 is a block diagram illustrating a configuration example of an image composition device according to the second embodiment of the present invention. The same components as those in the image synthesizing apparatus according to the first embodiment shown in FIG. 1 are denoted by the same reference numerals, and the description thereof will be omitted below.

  The image analysis unit 32 of the present embodiment includes an object recognition unit 33, and recognizes the content of the image acquired by the image acquisition unit 12 by image analysis.

  The object recognition unit 33 recognizes an object in the image. Here, the object is a subject image in the image. The object recognition unit 33 of this example recognizes what type of subject image the subject image in the image is. For example, it recognizes the type of person, food, drink, flower, etc. In the case of a person, who the person is may be specified.

  There are various modes of object recognition by the object recognition unit 33. The present invention is not limited to recognizing the presence or absence of a single object, and a combination of a plurality of types of objects may be recognized. For example, when creating an image collection on the theme of marriage, a combination of a woman wearing a wedding dress, a man wearing a suit next to the woman, and a cake may be recognized. Moreover, you may recognize the combination of an object and its movement. For example, when creating an image collection based on the theme of athletic meet, a child may be recognized and the child may be running.

  The storage control unit 42 of the present embodiment causes the storage unit 20 to store attribute information indicating the content of the image recognized by the image analysis unit 32 in association with the adopted template. In this example, attribute information (object information) indicating an object recognized by the object recognition unit 33 (an object in the acquired image) is stored in the storage unit 20 in association with the adopted template.

  FIG. 13 is a flowchart showing a flow of an example of the image composition processing of the second embodiment to which the image composition method of the present invention is applied. This process is executed by the CPU 30 according to the program stored in the storage unit 20. The same steps as those in the image synthesizing process example of the first embodiment shown in FIG. 2 are denoted by the same reference numerals, and the description thereof will be omitted below.

  Step S2 is the same as in the first embodiment.

  In step S204, the object recognition unit 33 recognizes the object in the image acquired in step S2.

  The subsequent step S6 is the same as in the first embodiment.

  In this embodiment, in step S208, the template determination unit 36 uses the attribute information related to the unsynthesized image and includes the object recognition result in step S204, and the object stored in the storage unit 20 in association with the template. Based on the attribute information including the recognition result, a template to be displayed to the user is determined.

  Subsequent steps S10 to S24 are the same as those in the first embodiment.

  In the present embodiment, in step S226, the storage control unit 42 stores attribute information indicating the object in the image recognized in step S204 in the storage unit 20 in association with the adopted template.

  The subsequent step S28 is the same as in the first embodiment.

  FIG. 14 is a diagram illustrating an example of the log 700 according to the second embodiment. The same reference numerals are given to the same information as the log 70 in the first embodiment shown in FIG.

  The log 700 of this example includes an image analysis log 76 (image analysis information) indicating the image analysis result of the image analysis unit 32. The image analysis log 76 of this example includes object information indicating an object in the image recognized in step S204. Such image analysis information is included in “attribute information related to an image”.

  According to the present embodiment, the object in the acquired image is recognized, the relationship between the object, each template, and whether or not the template is adopted by the user is learned, and the recommended template is determined based on the learning result. As a result, it is possible to present to the user a template that is sufficiently adapted to both the image content and the user's preferences.

<Third Embodiment>
FIG. 15 is a block diagram illustrating a configuration example of an image composition device according to the third embodiment of the present invention. The same components as those in the image synthesizing apparatus according to the second embodiment shown in FIG. 12 are denoted by the same reference numerals, and the description thereof will be omitted below.

  The evaluation value calculation unit 52 calculates an evaluation value (hereinafter referred to as “template evaluation value”) for each combination of attribute information of a plurality of items and a template. For example, when the number of items is “N”, a value indicating the relevance (relation strength in this example) between the attribute information of each item from item 1 to item N and each template is calculated as the template evaluation value. . The template evaluation value is, for example, the number of times each past template has been adopted.

  The storage control unit 42 causes the storage unit 20 to store the template evaluation value calculated by the evaluation value calculation unit 52 in association with the adopted template instructed by the user. That is, the storage control unit 42 of this example associates the template evaluation value with the adoption template, and associates the attribute information of the synthesized image with the adoption template and stores them in the storage unit 20.

  The template determination unit 36 determines a recommended template to be displayed to the user based on the template evaluation value. Specifically, the template determination unit 36 of this example is based on attribute information of a plurality of items related to an unsynthesized image and a template evaluation value table stored in the storage unit 20 in association with each of the plurality of templates. Determine a recommended template.

  FIG. 16 shows an example of a template evaluation value table in the present embodiment. The template evaluation value table 80 shown in FIG. 16 is table information in which template identification information is associated with template evaluation values TV of a plurality of items (item 1 to item N).

  For example, for a template whose template identification information is “1”, an evaluation value TV11 when the user is in their 10s, an evaluation value TV12 when the user is in their 20s, and an evaluation when the user is in their 30s The value TV13, the evaluation value TV14 when the user is in their 40s, the evaluation value TV15 when the user is in their 50s, and the evaluation value TV16 when the user is over 60s are calculated and registered. ing. Further, for a template whose template identification information is “1”, an evaluation value TV21 when the user is a female and an evaluation value TV22 when the user is a male are calculated and registered. In this way, the user information can be attribute information about the image, and the relevance with the template can be represented by the template evaluation value and stored in the storage unit 20.

  Also, for example, for a template whose template identification information is “1”, the evaluation value TV31 when the user instructs the theme “marriage” and “simple”, and the user instructs the theme “marriage” and “art” Evaluation value TV32, evaluation value TV33 when the user instructs with the theme of "marriage" and "cool", evaluation value TV34 when the user instructs with the theme of "marriage" and "chic", "travel" and Evaluation value TV35 when the user has instructed with the theme of “city”, evaluation value TV36 when the user has instructed with the theme of “travel” and “beach”, instructed by the user with the theme of “travel” and “forest” The evaluation value TV37 for each case is calculated and registered. As described above, the user instruction information can be used as attribute information about the image, and the relevance with the template can be represented by the template evaluation value and stored in the storage unit 20.

  For example, for a template whose template identification information is “1”, an evaluation value TV41 when a person object is recognized, an evaluation value TV42 when at least one of a food object and a drink object is recognized, and a flower object are Evaluation values when recognized are calculated and registered. TV44, TV45, TV46, and TV47 are evaluation values when other objects are recognized. As described above, the image analysis information can be used as attribute information about the image, and the relevance with the template can be expressed by the template evaluation value and stored in the storage unit 20.

  FIG. 17 is a flowchart showing a flow of an example of the image composition process of the third embodiment to which the image composition method of the present invention is applied. This process is executed by the CPU 30 according to the program stored in the storage unit 20. The same steps as those in the image synthesis processing example of the second embodiment shown in FIG. 13 are denoted by the same reference numerals, and the description thereof will be omitted below.

  Steps S2, S204, and S6 are the same as those in the second embodiment.

  In the present embodiment, in step S308, the template determination unit 36 determines a template (recommended template) to be displayed to the user based on the template evaluation value stored in the storage unit 20.

  Steps S10 to S24 are the same as those in the second embodiment.

  In this embodiment, in step S325, the evaluation value calculation unit 52 calculates a template evaluation value (which is an evaluation value of a combination of each attribute information and the template).

  In the present embodiment, in step S326, the template evaluation value TV is stored in the storage unit 20 in association with the adopted template.

  The subsequent step S28 is the same as in the second embodiment.

<Fourth Embodiment>
FIG. 18 is a block diagram illustrating a configuration example of an image composition device according to the fourth embodiment of the present invention. The same components as those in the image synthesizing apparatus according to the third embodiment shown in FIG. 15 are denoted by the same reference numerals, and the description thereof will be omitted below.

  The comprehensive evaluation value calculation unit 54 includes a template evaluation value (which is an evaluation value calculated by the evaluation value calculation unit 52) and weight information Ki for each item (i is an integer from 1 to N, where N is Is a comprehensive evaluation value for each template for a combination of attribute information of a plurality of items (hereinafter referred to as “template comprehensive evaluation value”).

  FIG. 19 shows an example of a template evaluation value table in the present embodiment. Hereinafter, differences from the template evaluation value table 80 in the third embodiment illustrated in FIG. 16 will be described. In the template evaluation value table 82 of this example, weight information Ki (i is an integer from 1 to N and N is the number of items) is assigned to each item of attribute information. The comprehensive evaluation value calculation unit 54 is a combination of a plurality of items (for example, the user's age is in his 30s, the user's gender is female, and the theme instructed by the user is “travel” and “city”, Further, for example, a weighted average of the template evaluation value TV is calculated using the weight information Ki for a combination of cases where a person object is recognized by image analysis), and the calculation result is set as a template total evaluation value TTV.

  The storage control unit 42 associates the template evaluation value calculated by the evaluation value calculation unit 52 and the template total evaluation value TTV calculated by the total evaluation value calculation unit 54 with the adopted template instructed by the user. 20 is stored. In other words, the storage control unit 42 of this example associates the template evaluation value and the template comprehensive evaluation value with the adopted template, and associates the attribute information of the synthesized image with the adopted template and stores them in the storage unit 20.

  FIG. 20 shows an example of the template comprehensive evaluation value table. The template comprehensive evaluation value table 84 shown in FIG. 20 is table information in which template identification information, combination identification information for identifying a combination of a plurality of items, and a template comprehensive evaluation value TTV are associated with each other. For example, for a template whose template identification information is “1”, a combination of a plurality of items (for example, the user's age is in his 30s, the user's gender is female, and the theme instructed by the user is “travel” and A combination of “city” and a person object recognized by image analysis) and a template comprehensive evaluation value TTV for the combination are associated with each other and stored in the storage unit 20. Similarly, the combination identification information and the template comprehensive evaluation value TTV are associated with each other and stored in the storage unit 20 for templates other than the template identification information “1”.

  The template determination unit 36 determines a recommended template using the template comprehensive evaluation value TTV stored in the storage unit 20 with respect to the attribute information of a plurality of items related to the unsynthesized image. That is, the template determination unit 36 determines a template to be displayed to the user based on the template comprehensive evaluation value calculated by the comprehensive evaluation value calculation unit 54.

  FIG. 21 is a flowchart showing a flow of an example of the image composition process of the fourth embodiment to which the image composition method of the present invention is applied. This process is executed by the CPU 30 according to the program stored in the storage unit 20. The same steps as those in the image synthesis processing example of the third embodiment shown in FIG. 17 are denoted by the same reference numerals, and the description thereof will be omitted below.

  Steps S2, S204, and S6 are the same as those in the third embodiment.

  In this embodiment, in step S408, the template determination unit 36 determines a template (recommended template) to be displayed to the user based on the attribute information of a plurality of items related to the unsynthesized image and the template comprehensive evaluation value TTV. Is done. In this example, a template having the highest template total evaluation value TTV is determined as a recommended template for a combination of attribute information of a plurality of items related to an unsynthesized image.

  Steps S10 to S24 and step S325 are the same as those in the third embodiment.

  In this embodiment, in step S425, the comprehensive evaluation value calculation unit 54 calculates the template comprehensive evaluation value TTV based on the template evaluation value TV and the weight information Ki of each of the plurality of items.

  In the present embodiment, in step S426, the template evaluation value TV and the template comprehensive evaluation value TTV are stored in the storage unit 20 in association with the adopted template. For example, the template evaluation value is registered in the template evaluation value table 82 in FIG. 19, and the template total evaluation value TTV is registered in the template total evaluation value table 84 in FIG.

  The subsequent step S28 is the same as in the third embodiment.

  Although the case where the template is not deleted has been described as an example, a configuration may be adopted in which a template with a low adoption frequency is deleted. For example, the storage control unit 42 deletes, from the storage unit 20, a template whose template comprehensive evaluation value TTV is continuously equal to or less than the threshold value for a certain period among a plurality of templates stored in the storage unit 20.

  Moreover, although the case where the template with the highest template total evaluation value TTV is determined as the recommended template with respect to the attribute information of a plurality of items has been described as an example, a plurality of templates may be determined as the recommended template. For example, the display control unit 38 displays a plurality of templates in descending order of the template comprehensive evaluation value TTV.

  Moreover, although the case where the weight information Ki is fixed has been described as an example, the weight information Ki may be variable. For example, the storage control unit 42 receives an instruction (template change instruction) indicating that the recommended template determined by the template determining unit 36 is not adopted and a template different from the determined recommended template is adopted. If it is, the weight information Ki is changed. In other words, depending on whether the user has adopted a recommended template, the weight information is controlled by determining which item has a higher relevance weight and which item has a lower relevance weight. This increases the probability that a user's favorite template can be presented.

  There are various ways of changing the weight information Ki. First, there is an aspect in which the weight information Ki is changed for each item of attribute information, and second, there is an aspect in which a plurality of items are grouped and the weight information Ki is changed for each group. In the former mode, the weight information can be finely controlled for each item, and in the latter mode, the weight information can be easily controlled for each group.

  For example, as shown in FIG. 22, the user information (age information, gender information, family composition information, residence information, etc.) is the first group G1, and the user instruction information (theme information, text information, etc.) is the second. Group G2 and image analysis information (object information, etc.) as third group G3, and for each template, which group weight information is increased and which group weight information is decreased is controlled. FIG. 22 shows the concept of changing the ratio of the weight information of the groups G1, G2, and G3. That is, depending on the image layout, background design, and decoration design of the template, which attribute information of the user information, the user instruction information, and the image analysis information is different for each template, the template total evaluation value TTV Can be calculated and associated with the employment template to learn the user's recruitment tendency and present a recommended template that is more favored by the user.

<Variation>
Various variations of the present invention will be described.

≪Template display≫
In the above-described embodiment, an example is shown in which only the recommended template determined by the template determination unit 36 is displayed, and when the user instructs display of another template different from the recommended template, display of another template is performed. However, the present invention is not limited to such a case.

  The display control unit 38 causes the display unit 14 to display two or more templates including the determined template (recommended template) among the plurality of templates stored in the storage unit 20, and scrolls by the instruction input unit 16. When an instruction is received, the determined template (recommended template) may be displayed at the top. In other words, the recommended template and other templates than the recommended template are displayed to the user at the same time, and if there is no scrolling instruction, the display order is not changed, but if there is a scrolling instruction, the recommended template is moved to the top. Let According to this aspect, since the template display order does not change frequently, an effect that does not confuse the user can be expected.

<< Association conditions >>
In the above-described embodiment, an example has been described in which any user is associated with attribute information and a template, but the present invention is not limited to such a case.

  The storage control unit 42 may associate the attribute information with the template when the user satisfies a predetermined condition. For example, a display for selecting whether to perform learning for the user is displayed, and a selection instruction for determining whether to perform learning is received from the user. According to this aspect, a user who does not want to learn can be excluded from the learning target.

≪Association timing≫
In the above-described embodiment, an example has been described in which attribute information and a template are immediately associated with each time image synthesis is performed. However, the present invention is not limited to such a case.

  The storage control unit 42 may associate the attribute information with the template at regular intervals. For example, the association is performed every month and the learning data (for example, the template evaluation value table of the third embodiment and the fourth embodiment, the template comprehensive evaluation value table of the fourth embodiment, etc.) is updated. It is good. According to this aspect, it is possible to prevent the template determination result from changing during the user's work, so that an effect that does not give the user a sense of incongruity can be expected.

  As mentioned above, although the form for implementing this invention has been demonstrated, this invention is not limited to embodiment and the modification which were mentioned above, A various deformation | transformation is possible in the range which does not deviate from the main point of this invention.

DESCRIPTION OF SYMBOLS 10 Image composition apparatus 12 Image acquisition part 14 Display part 16 Instruction input part 20 Storage part 30 CPU
32 Image analysis unit 33 Object recognition unit 34 Attribute information acquisition unit 36 Template determination unit 38 Display control unit 40 Image synthesis unit 42 Storage control unit 52 Evaluation value calculation unit 54 Overall evaluation value calculation unit 60 Composite image 70 Log 72 Order log 74 Operation Log 76 Image analysis log 80 Template evaluation value table 82 Template evaluation value table 84 Template comprehensive evaluation value table 700 Log A11 Template display area A21 Composite image display area B11 OK button B12 Layout change button B13 Background color change button B14 Stamp addition button B15 Font Instruction button B21 Next screen button B22 Previous screen button BC Color selection scroll bar BF Font selection scroll bar G1 First group G2 Second group G3 Third group Ki Weight information MC Check Mark SB Background color selection screen SE1 First editing screen SE2 Second editing screen SF Font instruction screen SS Stamp list screen ST1 First template list screen ST2 Second template list screen STM Theme selection screen T1 to T8 Template TTV Template Overall evaluation value TV, TV11 to TV16, TV21 to TV22, TV31 to TV37, TV41 to TV47 Template evaluation value

Claims (18)

An image acquisition unit for acquiring images;
An attribute information acquisition unit for acquiring attribute information about the acquired image;
A storage unit for storing a plurality of templates;
A display unit;
A template determination unit for determining a template to be displayed to the user among the plurality of stored templates;
A display control unit for displaying the determined template on the display unit;
An instruction input unit that receives an instruction indicating whether or not to adopt the displayed template from the user;
An image synthesis unit that synthesizes the template instructed by the user and the acquired image;
A storage control unit for storing the acquired attribute information in the storage unit in association with a template instructed by the user;
With
The template determination unit, when the unsynthesized image and the attribute information related to the unsynthesized image are acquired, the attribute information related to the unsynthesized image and the attribute information stored in the storage unit in association with the template, To determine a template to be displayed to the user,
Image composition device. The attribute information acquisition unit acquires attribute information of a plurality of items related to the acquired image,
The template determination unit determines a template to be displayed to the user by comparing attribute information regarding the unsynthesized image with attribute information stored in the storage unit in association with the template in the plurality of items. To
The image composition device according to claim 1. An evaluation value calculating unit that calculates an evaluation value for each combination of the attribute information of the plurality of items and the template;
The template determination unit determines a template to be displayed to the user based on the calculated evaluation value.
The image composition device according to claim 2. An evaluation value calculating unit that calculates an evaluation value for each combination of the attribute information of the plurality of items and the template;
A comprehensive evaluation value calculating unit that calculates a comprehensive evaluation value for each of the templates for the attribute information of the plurality of items based on the evaluation value and weight information of each of the plurality of items;
The template determination unit determines a template to be displayed to the user based on the calculated comprehensive evaluation value;
The image composition device according to claim 2. The storage control unit deletes, from the storage unit, a template in which the comprehensive evaluation value is continuously equal to or less than a threshold value for a certain period among the plurality of stored templates.
The image composition device according to claim 4. The display control unit displays the plurality of templates in descending order of the comprehensive evaluation value.
The image composition device according to claim 4 or 5. The storage control unit, when a template change instruction indicating that the template determined by the template determination unit is not adopted and a template different from the determined template is accepted is received, Rather than associating the attribute information with the attribute information, the template instructed to be adopted is more strongly associated with the attribute information.
The image composition device according to any one of claims 1 to 6. The storage control unit changes the weight information when a template change instruction indicating that the template determined by the template determination unit is not adopted and a template different from the determined template is accepted is received. ,
The image composition device according to any one of claims 4 to 6. The storage control unit includes the theme information of a composite image of the acquired image and the template, text information on the composite image, object information in the acquired image, age information of the user, gender information of the user , At least one item of attribute information among the user's family structure information and the user's residence information is stored in the storage unit in association with the template.
The image composition device according to any one of claims 1 to 8. An image analysis unit for recognizing the content of the acquired image by image analysis;
The storage control unit stores attribute information indicating the content of the recognized image in the storage unit in association with the template;
The image composition device according to any one of claims 1 to 8. The image combining unit combines the template and the image for a plurality of pages.
The template determination unit determines the template for at least one of the plurality of pages;
The image composition device according to any one of claims 1 to 10. The template determination unit determines a plurality of templates to be displayed to the user,
The display control unit causes the user to display the determined plurality of templates,
The instruction input unit receives an instruction from the user indicating a template to be adopted from the displayed templates.
The image composition device according to any one of claims 1 to 11. The storage control unit stores the decoration added to the template according to the user's instruction in association with the template,
The display control unit displays the decoration associated with the determined template to the user;
The image composition device according to any one of claims 1 to 12. The display control unit displays two or more templates including the determined template among the plurality of stored templates on the display unit, and displays the determined template at the top.
The image composition device according to any one of claims 1 to 13. The storage control unit associates the attribute information with the template when the user satisfies a predetermined condition.
The image composition device according to any one of claims 1 to 14. The storage control unit associates the attribute information with the template at regular intervals.
The image composition device according to any one of claims 1 to 15. Acquiring an image;
Obtaining attribute information relating to the obtained image;
Determining a template to be displayed to the user among a plurality of templates stored in the storage unit;
Displaying the determined template on a display unit;
Receiving an instruction from the user indicating whether or not to adopt the displayed template;
Synthesizing the template instructed by the user and the acquired image;
Storing the acquired attribute information in the storage unit in association with a template instructed by the user;
With
In the step of determining the template, when the unsynthesized image and the attribute information related to the unsynthesized image are acquired, the attribute information related to the unsynthesized image and the attribute stored in the storage unit in association with the template An image composition method for determining a template to be displayed to the user based on information. Acquiring an image;
Obtaining attribute information relating to the obtained image;
Determining a template to be displayed to the user among a plurality of templates stored in the storage unit;
Displaying the determined template on a display unit;
Receiving an instruction from the user indicating whether or not to adopt the displayed template;
Synthesizing the template instructed by the user and the acquired image;
Storing the acquired attribute information in the storage unit in association with a template instructed by the user;
To the computer,
In the step of determining the template, when the unsynthesized image and the attribute information related to the unsynthesized image are acquired, the attribute information related to the unsynthesized image and the attribute stored in the storage unit in association with the template A program for determining a template to be displayed to the user based on information.

Images