JP2020140556A - Image processing device, control method, and program - Google Patents

Abstract

To allow for appropriately generating multiple sets of album data comprising common pages that are common to all of the sets of album data and individual pages that are not common to all of the sets of album data.SOLUTION: The above problem is solved by providing a program configured to make a computer perform a second selection step for selecting at least one of multiple sets of image data as individual image data corresponding to images to be placed on individual pages that are not common to all of multiple albums, and to provide control such that cover page image data corresponding to images to be placed on cover pages of the albums is selected as the individual image data.SELECTED DRAWING: Figure 1

Description

The present invention relates to image processing devices, control methods, and programs.

In recent years, a method of generating album data for outputting an album in which images are arranged has been known. Patent Document 1 proposes a method in which a plurality of users jointly edit album data.

JP 2016-66328

However, Patent Document 1 describes a process for generating a plurality of album data including a common page which is a page common to all the plurality of album data and an individual page which is a page not common to all the plurality of album data. Is not considered.

Therefore, an object of the present invention is to appropriately generate a plurality of album data including a common page which is a page common to all the plurality of album data and an individual page which is a page not common to all the plurality of album data. To do.

The program of the present invention applies to a computer of an image processing device that generates a plurality of album data corresponding to a plurality of albums.
The acquisition step to acquire multiple image data and
A first selection step of selecting at least one image data out of the plurality of image data as common image data corresponding to an image arranged on a common page which is a page common to all the plurality of albums.
A first generation step of generating common page data corresponding to the common page based on the at least one image data selected as the common image data, and
A second selection step of selecting at least one image data out of the plurality of image data as individual image data corresponding to an image arranged on an individual page which is a page not common to all the plurality of albums.
A second generation step of generating a plurality of individual page data corresponding to the individual page based on the at least one image data selected as the individual image data.
A third generation step of generating the plurality of album data based on the common page data and the plurality of individual page data is executed.
The individual page data corresponding to the first album data among the plurality of album data and the individual page data corresponding to the second album data among the plurality of album data are different.
The common page data corresponding to the first album data among the plurality of album data and the common page data corresponding to the second album data among the plurality of album data are the same.
The cover image data corresponding to the image arranged on the cover of the album is controlled so as to be selected as the individual image data.

According to the present invention, it is possible to appropriately generate a plurality of album data including a common page which is a page common to a plurality of album data and an individual page which is a page not common to the plurality of album data.

It is a block diagram which shows the hardware structure of an image processing apparatus. It is a figure which shows the example of the spread included in the album created by the album creation application. It is a figure of the setting screen displayed by an album creation application. It is a flowchart which shows the automatic layout processing executed by an album creation application. It is a figure for demonstrating division of an image data group. It is a figure for demonstrating the classification of a scene. It is a figure for demonstrating selection of image data. It is a flowchart which shows the process of determining the template used for creating a layout image. It is a figure for demonstrating the layout of image data. It is a flowchart which shows the spread joining process executed by an album creation application. It is a flowchart which shows the automatic layout processing executed by an album creation application. It is a flowchart which shows the automatic layout processing executed by an album creation application. It is a flowchart which shows the automatic layout processing executed by an album creation application. It is a figure for demonstrating the cover mode setting area. It is a figure which shows an example of the cover template.

(First Embodiment)
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

In the following embodiment, a procedure for operating an application program for creating an album (hereinafter, also referred to as an “album creation application”) on an image processing device and generating an automatic layout will be described. Unless otherwise specified, the images described below include still images, videos, frame images in videos, and still images, videos, and frame images in videos on SNS (Social Networking Service) servers. ..

FIG. 1 is a block diagram illustrating a hardware configuration of an image processing device according to the present invention. Examples of the image processing device include a PC (personal computer), a smartphone, a tablet terminal, a camera, a printer, and the like, and in the present embodiment, the image processing device is a PC.

In FIG. 1, the image processing device 100 includes a CPU 101, a ROM 102, a RAM 103, an HDD 104, a display 105, a keyboard 106, a mouse 107, a data communication unit 108, and the like. These are connected to each other by the data bus 109. The computer of the image processing apparatus 100 is formed by the CPU 101, the ROM 102, the RAM 103, and the like.

The CPU (Central Processing Unit / Processor) 101 is a system control unit and controls the entire image processing unit 100. Further, the CPU 101 executes the image processing method described in the present embodiment according to a program. Although the number of CPUs in the figure is one, the number of CPUs is not limited to one, and a plurality of CPUs may be provided.

The ROM 102 stores a program and an OS (operating system) executed by the CPU 101. The RAM 103 provides a memory for temporarily storing various information when the program is executed by the CPU 101. The HDD (hard disk) 104 is a storage medium for storing an image file, a database that holds processing results such as image analysis, and the like. In this embodiment, the RAM 103 stores an album creation application described later.

The display 105 (display unit) is a device that presents the UI (user interface) of the present embodiment and the layout result of the image to the user. The display 105 may have a touch sensor function. The keyboard 106 is one of the input devices, and is used, for example, to input predetermined information on the UI displayed on the display 105. The predetermined information is, for example, information such as the number of spreads and the number of pages of the album to be created. The mouse 107 is one of the input devices and is used, for example, to click a button on the UI displayed on the display 105. For example, the user double-clicks the icon corresponding to the album creation application displayed on the display 105 by operating the mouse 107 to start the album creation application.

The data communication unit 108 (communication unit) is a device for communicating with an external device such as a printer or a server. For example, the data created by the album creation application is transmitted to a printer or server (not shown) connected to the image processing device 100 via the data communication unit 108. In addition, the data communication unit 108 receives still image data on a server (not shown) or an SNS (social networking service) server. In the present embodiment, the data communication unit 108 receives the still image data from the SNS server, but may also receive the moving image data.

The data bus 109 connects each unit (102 to 108) described above to the CPU 101.

In the present embodiment, the album creation application has a function of generating a plurality of album data including a common page and an individual page at one time. The common page is a page that is commonly included in all the album data generated by the album creation application at one time. The individual page is a page included in any of the album data generated by the album creation application at one time, and is not included in all the album data generated by the album creation application at once. .. Since the individual pages have contents corresponding to each album data, the contents of the individual pages are different for each album data. In the present embodiment, the element (reference) for selecting the image data included in the common page and the element for selecting the image data included in the individual page are different from each other. Then, the elements for selecting the image data included in the individual pages are different for each album data.

For example, suppose there is a use case where a plurality of users bring their own image data and generate album data. In this case, the plurality of album data output to each of the plurality of users includes a common page that is common to the plurality of album data and a page that is not common to the plurality of album data and is different for each album. It is requested that individual pages are included. As a method of generating album data including both common pages and individual pages, for example, there is a method of manually editing the album data after generating album data composed of only common pages. However, this method has low usability because it takes time and effort for the user. As in the present embodiment, the image data included in the common page and the image data included in the individual pages are selected according to different criteria, and a plurality of album data are generated to generate album data having appropriate contents. It can be easily generated.

When the album creation application according to the present embodiment is installed in the image processing device 100, a start icon is generated on the top screen (desktop) displayed on the display 105 by the OS running on the image processing device 100. Then, when the user double-clicks the start icon by operating the mouse 107, the program of the album creation application stored in the HDD 104 is loaded into the RAM 103. Then, the program loaded in the RAM 103 is executed by the CPU 101, and the album creation application is started.

FIG. 3 is a diagram showing an example of the setting screen 301 provided by the started album creation application. The setting screen 301 is displayed on the display 105. When the user sets the album creation conditions via the setting screen 301, the album creation application acquires the setting contents specified by the user.

In the present embodiment, the image data group used for the album, the total number of spread data, the products used for creating the album, the number of album data to be created at one time, and the main subject for each album are set as the album creation conditions. It is possible. In the present embodiment, the page includes a spread page (hereinafter referred to as a spread) and an individual page. Then, in the present embodiment, the spread corresponds to a pair of individual pages printed on different sheets and adjacent to each other, and the spread data is for determining the layout of the spread and printing the spread according to the determined layout. It is the data of. In this embodiment, processing is performed for each spread data, but processing may be performed for each page data corresponding to one page (one individual page). The main subject is a subject that is preferentially laid out in the album. As the main subject, for example, a specific individual, a category of an object such as a dog, a cat, a flower, or a dish, an object, or the like can be set.

The pass box 302 on the setting screen 301 indicates a storage location (path) in the HDD 104 of the image data group to be created as an album. The folder selection button 303 is clicked by the operation of the mouse 107 by the user to display a folder containing an image data group to be created as an album so that the user can select it in a tree structure. Then, the folder path including the image data group selected by the user is displayed in the pass box 302. The image data group specified here is acquired and album data is generated. The image data group may be acquired from a storage area such as a server on the network or an SNS server via the data communication unit 108. The image data group referred to here refers to image data candidates used for creating an album. Further, when designating the image data group to be created as an album, information other than the storage location of the image data group to be created as an album may be input. For example, the date and time (hereinafter referred to as the shooting date and time) when the image data group to be created for the album is generated (the photo corresponding to the image data was taken) may be specified.

The image data to be created as an album is, for example, still image data or cut-out image data obtained by cutting out a frame from moving image data. The still image data and the cut-out image data are acquired from the imaging device. The image processing device may be provided by the image processing device 100, or may be provided by an external device (PC, smartphone, digital camera, tablet terminal, etc.) which is an external device of the image processing device 100. When the image processing device 100 acquires the image data from the external device, the image processing device 100 acquires the image data via the data communication unit 108. Further, the image processing device 100 may acquire still image data and cut-out image data from a network or a server via a data communication unit 108. The CPU 101 analyzes the data accompanying the image data to determine where each image data was acquired. When the CPU 101 acquires the image data from the SNS server via the album creation application, the album creation application may manage where the image data is acquired. The image data used by the album creation application is not limited to the above-mentioned types of image data, and may be other types of image data.

The spread number box 304 is a box for accepting from the user the designation of the total spread number in one album. The user can specify the total number of spreads by directly inputting a number into the spread number box 304 using the keyboard 106 or by inputting a number into the spread number box 304 from the list using the mouse 107. The number of spreads specified here is applied to all albums corresponding to the number specified in the album number box 310, but for example, the total number of spreads may be specified for each album.

The album number box 310 is a box for accepting from the user the number of albums to be created at one time by the album creation application. The number of albums created by the album creation app by the user by entering a number directly into the album number box 310 using the keyboard 106 or by entering a number from the list into the album number box 310 using the mouse 107. Can be specified.

An example of the spread included in the album created by the album creation application will be described with reference to FIG. As described above, in the present embodiment, since each album of the number specified by the album number box 310 includes a common page and an individual page, each album has at least a part of content different from each other.

Here, it is assumed that three albums (albums 1 to 3) are created at a time by designating the album number box 310. Image 301 is an example of an image arranged in a spread of album 1, and the characters in image 301 represent the main subject shown in the image. The spread 302 is a spread composed of common pages and is included in all of albums 1 to 3. Since the common page is included in all the albums in this way, the layout is centered on the image in which each main subject specified in each album is shown. On the other hand, the spreads 303, 304, and 305 are spreads composed of individual pages. Therefore, each spread is included in only one album. Then, for example, the spread 303 included in the album 1 is laid out centering on an image in which the main subject A, which is the main subject designated in the album 1, is captured. Further, the spread 304 included in the album 2 is laid out centering on an image in which the main subject B, which is the main subject designated in the album 2, is shown. As described above, in the present embodiment, a plurality of albums composed of two types of spreads, which are created according to different criteria, are created.

The main subject designation unit 305 is an area for receiving the designation of the main subject for each album corresponding to the number input in the album number box 310 from the user. For example, the user can specify the main subject for each album by dragging and dropping the image data in which the main subject is captured to the area corresponding to each album in the main subject designation unit 305 with the mouse 107.

The spread photo number 306 is an area for accepting from the user the designation of the number of image data arranged in each spread of the album to be created. The user can increase the number of image data arranged in each spread by setting the slider bar to the "many" side. By increasing the number of image data arranged in each spread, as a result, the number of image data arranged in each album is increased. In addition, the user can reduce the number of image data arranged in each spread by setting the slider bar to the "small" side. The number of image data arranged in each spread is reduced, and as a result, the number of image data arranged in each album is reduced. The number of image data specified here is applied to all albums corresponding to the number specified in the album number box 310. For example, the number of image data is specified for each album. It may be configured to be done.

The product designation unit 307 is an area for receiving the designation of the product used for the album to be created from the user. The user can set the size of the album, the type of paper of the album, the type of the cover of the album, the type of the binding part of the album, and the like by inputting to the product designation unit 307.

The OK button 308 is a button for receiving an input from the user that the setting related to the album to be created is completed. When the OK button 308 is clicked by the user with the mouse 107, the album creation application acquires the contents set on the setting screen 301, and uses the acquired contents for the album data creation process described below.

The reset button 309 is a button for resetting each setting information on the setting screen 301.

It should be noted that settings other than the above-mentioned settings may be executed on the setting screen 301. For example, it may be possible to execute settings related to moving images, settings of acquisition destinations of image / moving image data, and the like, and it may be possible to specify the mode of the album to be created. The album mode is a mode for preferentially laying out an image including a predetermined object in a template, and is, for example, three modes of "person", "animal", and "cooking". The album mode can be rephrased as the theme of the album, for example. For example, when "person" is selected, the image including the person is preferentially laid out in the template. Further, for example, when "animal" is selected, the image including the animal is preferentially laid out in the template. Further, for example, when "cooking" is selected, the image including the cooking is preferentially laid out in the template. In addition, there may be a mode for laying out the image data representing the image in which objects other than the above three objects are reflected in the template with priority. Moreover, a plurality of modes may be selected at the same time. In that case, the image containing at least one of the plurality of objects corresponding to the plurality of selected modes is preferentially laid out in the template. When the user clicks with the mouse 107, the user can select one of the plurality of icons corresponding to each mode. Then, the mode corresponding to the selected icon is set as the mode of the album to be created. The mode of the album is not limited to the above three modes, and there may be other modes such as "building", "vehicle", and "flower".

FIG. 5 is a flowchart showing an automatic layout process executed by the album creation application according to the present embodiment. The flowchart shown in FIG. 5 is realized, for example, by the CPU 101 reading a program corresponding to the album creation application stored in the HDD 104 into the ROM 102 or the RAM 103 and executing the program. In the present embodiment, the album creation application saved in the HDD 104 is activated by the user operating the icon corresponding to the album creation application displayed on the display 105 by using the mouse 107, and the following processing is performed. To execute.

In S401, the CPU 101 sets the album creation conditions. Specifically, for example, the user accepts the setting of the album creation condition via the screen shown in FIG. The details of setting the album creation conditions are as described above in the description using FIG.

In S402, the CPU 101 acquires the image data included in the image data group specified in the pass box 302. Specifically, the CPU 101 reads the image data group specified in the pass box 302 from the HDD 104 and expands it into the RAM 103.

In S403, the CPU 101 executes an image analysis process for analyzing the image data expanded in the RAM 103 in S402. FIG. 5B is a flowchart showing an image analysis process executed by the album creation application according to the present embodiment.

In S40301, the CPU 101 acquires information regarding the shooting date and time from information (Exif information and the like) associated with the image data acquired in S402.

In S40302, the CPU 101 acquires information regarding the feature amount of the image data from the image data acquired in S402. Examples of the feature amount include focus. As an edge detection method for acquiring the feature amount of focus, for example, a general Sobel filter is used. The edge inclination, that is, the brightness gradient can be calculated by detecting the edge with the Sobel filter and dividing the brightness difference between the start point and the end point of the edge by the distance between the start point and the end point. From the result of calculating the average inclination of the edges in the image, it can be considered that the image having a large average inclination is in focus more than the image having a small average inclination. Then, if a plurality of threshold values having different values are set for the slope, it is possible to output an evaluation value of the focus amount by determining which threshold value or more. In the present embodiment, two different threshold values are set in advance, and the focus amount is determined in three steps of ○ △ ×. The threshold value is set in advance by an experiment or the like so that the inclination of the focus to be adopted for the album is "○", the allowable inclination of the focus is "Δ", and the unacceptable inclination is "x". The threshold value may be provided by, for example, the creator of the album creation application, or may be set on the user interface.

In S40303, the CPU 101 executes an object detection process for each image data acquired in S402. First, the CPU 101 detects a person's face from the image represented by each image data acquired in S402. A known method can be used for the face detection process. For example, AdaBoost, which creates a strong classifier from a plurality of weak classifiers prepared, is used. In the present embodiment, a face image of a person (object) is detected by a strong classifier created by AdaBoost. Further, the CPU 101 extracts the face image and acquires the upper left coordinate value and the lower right coordinate value of the position of the detected face image. By having these two types of coordinates, the CPU 101 can acquire the position of the face image and the size of the face image. Further, in S40303, the CPU 101 may create a strong classifier by AdaBoost not only for the face but also for objects such as animals such as dogs and cats, flowers, dishes, buildings, figurines, and vehicles. As a result, the CPU 101 can detect objects other than the face. Further, the object may be searched by a deep neutral network or the like instead of AdaBoost.

In S40304, the CPU 101 executes the personal recognition process. Specifically, the CPU 101 performs personal recognition by comparing the similarity between the face image extracted in S40303 and the representative face image stored in the face dictionary database for each personal ID. The CPU 101 determines the similarity between the face image extracted in S40303 and each representative face image, and determines the ID of the representative face image whose similarity is equal to or higher than the threshold value and has the highest similarity, and the ID of the face image extracted in S40304. And. That is, the person corresponding to the representative face image having the similarity equal to or higher than the threshold value and having the highest similarity is specified as the person corresponding to the face image extracted in S40304. If the similarity between the face image extracted in S40304 and all the representative face images stored in the face dictionary database is less than the threshold value, the CPU 101 assigns a new personal ID to the extracted face image. Register as a new person in the face dictionary database. The face dictionary database is stored in the HDD 104, for example.

In S404, the CPU 101 determines whether or not the image analysis process has been completed for all the image data included in the image data group specified in the pass box 302. If it is not finished (No in S404), the process returns to S402, and image data that has not yet been processed is acquired. If it is finished (Yes in S404), the process proceeds to S405.

In S405, the CPU 101 divides the scene. The scene division refers to dividing all the image data obtained in S401 to S404 for each scene and managing them as a plurality of image groups. Specifically, the CPU 101 divides all the image data into a plurality of image groups based on the time difference between the shooting dates and times of each image data calculated from the shooting date and time information acquired in S403. In the following description, each image group obtained by dividing all the image data (main image group) is referred to as a sub image group. In the present embodiment, for example, the scene is divided by the method shown below. First, if the difference between the imaging date and time of the Nth captured image data and the imaging date and time of the (N + 1) th captured image data in the order of oldest imaging date and time is one day or less, it is as follows. If the difference between the imaging date and time of the Nth captured image data and the imaging date and time of the (N + 1) th captured image data is 16 hours or more in the order of the oldest imaging date and time, the Nth captured image data and the (N + 1) th captured image data Set the boundary of the group with the captured image data. Further, it is assumed that the difference in imaging date and time between adjacent captured image data in the order of oldest imaging date and time is less than 16 hours regardless of which captured image data. In this case, if the difference between the imaging date and time of the first captured image data and the imaging date and time of the last captured image data in the captured image data group captured in one day is less than 4 hours, the imaging of the day Let the image data group be one sub-image group (group). On the other hand, it is assumed that the difference between the imaging date and time of the first captured image data and the imaging date and time of the last captured image data in the captured image data group captured in the one day is 4 hours or more. In this case, if the number of captured image data captured in one day is less than 50 (the number of captured images captured in one day is less than 50), the captured image data group of the day is divided into one sub-image group. (Group). An example of such grouping of captured image data is shown in FIG. 5 (A). In FIGS. 5A to 5C, the horizontal axis represents the imaging date and time (older toward the left side and newer toward the right side), and the vertical axis represents the number of captured image data. In FIG. 5A, the captured image data group is divided into eight sub-image groups (groups) of groups 601-608. In FIG. 5A, the arrows indicate the boundaries of the groups. The threshold value for the difference in the imaging date and time and the threshold value for the number of captured image data used in the above description of the scene division method are examples, and are not limited to these values. The divided image group is called a divided image group, and one divided image group is set for each scene.

Further, in the present embodiment, the shooting date / time information is used for scene division, but the present invention is not limited to this. For example, using the shooting position information, image data whose shooting positions are close to each other may be set as one divided image group. Further, for example, the personal recognition result may be used. For example, the image data of students belonging to a certain group (class, club activities, etc.) is registered in advance in the album creation application. Then, by using the individual recognition result recognized by the image data, the image data showing the students belonging to the group may be set as one divided image group. Further, for example, the name of the folder in which the image is stored or the tag information attached by the social networking service or the like may be used. Specifically, for example, image data having tag information including a search word such as "athletic meet" or "school trip" may be set as one divided image group. The search word is input by the user via, for example, the setting screen 301.

In S406, the CPU 101 classifies the scenes. Specifically, the CPU 101 scores the sub-image group obtained by dividing the scene in S407 for each scene type, and classifies the sub-image group into the type of the scene having the highest score. In the following description, scoring in S406 is referred to as scene classification scoring. In the present embodiment, it is assumed that there are "travel", "daily life", and "ceremony" as the types of scenes, and an example of classifying the sub-image group into any of these scenes will be described. A scene classification table in which information on features corresponding to each type of scene is stored is used for scene classification scoring.

Here, a method of creating a scene classification table stored in advance in the program will be described. First, a plurality of image data groups determined in advance to be classified into "travel", "daily life", and "ceremony" scenes are collected by the program designer, and the feature amount is acquired for the collected image data groups. Will be done. Examples of the feature amount acquired here are, for example, the shooting period, the number of shots, and the number of shots. The shooting period is the shooting time difference between the first generated image data and the last generated image data in each image data group. The number of shots is the number of each image data group. The number of photographers is the average number of faces included in each image represented by each image data group. As a result, for example, the shooting period, the number of shots, and the feature amount of the number of shots are acquired for one image data group composed of a plurality of image data determined in advance as a travel scene. The feature amount is not limited to the shooting period, the number of shots, and the number of photographers, and other feature amounts may be used, or only one of them may be used.

Then, the acquisition of the shooting period, the number of shots, and the feature amount of the number of shots as described above is also performed for other image data groups collected in advance. Next, based on the feature quantities acquired from a plurality of image data groups collected for each scene, the average value and standard deviation of the shooting period, the average value and standard deviation of the number of shots, and the average number of shots per image. The value and standard deviation are calculated. By associating the values obtained in this way with each type of scene, a scene classification table showing each average value and standard deviation for each type of scene is created.

In the present embodiment, the table 600 shown in FIG. 6 is used as the scene classification table. In the table 600, the average values and standard deviations of the shooting period 602, the number of shots 603, and the number of shots 604 are registered in association with the scene ID 601. The CPU 101 stores the table 600 in a storage area such as the ROM 102 or the HDD 104 in advance before the scene classification process. The table 600 may be incorporated in the program of the album creation application in advance, or may be incorporated in a program other than the album creation application.

Here, scene classification scoring will be described. After the album creation application is started, the CPU 101 performs the shooting period, the number of shots, and the shooting for each sub-image group obtained by dividing the image data group specified by the user in the pass box 302 into scenes in S405. Calculate the score for each feature of the number of people. The CPU 101 calculates the shooting period for each division, the number of shots, the score of the number of shots, and the average score thereof from the equations (1) and (2) using the average value and standard deviation for each scene shown in FIG. To do. In the following formula, the average value of the predetermined feature amount corresponding to the predetermined type of scene and the standard deviation of the predetermined feature amount corresponding to the predetermined type of scene are registered in the table 600. In addition, the feature amount is acquired for three feature items of the shooting period, the number of shots, and the number of shots. Therefore, the number of feature items is 3 in this example.

First, the CPU 101 acquires a score for each type of scene and each feature amount of the sub-image group by the equation (1).

Score of a predetermined feature amount corresponding to a predetermined type of scene in the sub-image group = 50- | 10 × (average value of a predetermined feature amount corresponding to a predetermined type of scene-a predetermined feature amount of the sub-image group ) / Standard deviation of a predetermined feature amount corresponding to a predetermined type of scene | ... Equation (1)
As a result, for example, in the sub-image group, the scores of the shooting period, the number of shots, and the number of shots corresponding to the "travel" scene are acquired. The CPU 101 acquires points not only for the "travel" scene but also for each of the other types of scenes.

Next, the CPU 101 averages each score obtained by the equation (1) by the equation (2), and acquires the score for each type of scene of the sub-image group.

Score of a predetermined type of scene in the sub image group = (Score of the shooting period corresponding to the scene of the predetermined type of the sub image group + score of the number of shots + score of the number of shots) / Number of feature items ... (2)
As a result, for example, in the sub-image group, scores for each type of scene of "travel", "daily life", and "ceremony" are acquired. The CPU 101 performs scene classification scoring for each sub-image group.

Based on the above, the scores for each "travel", "daily life", and "ceremony" are calculated for each sub-image group. Then, the CPU 101 classifies the scene having the highest score as the scene of the sub-image group. For example, it is assumed that the sub-image group 5 corresponding to the scene 5 after the scene division in FIG. 5A has a shooting period of 36 hours, the number of shots is 300, and the number of shots is 1.7. Then, in the sub image group 5, the score for "travel" is 45.32, the score for "daily life" is 18.38, the score for "ceremony" is -29.92, and the sub image group 5 is the scene with the highest score. It is classified as a certain "travel". It should be noted that which sub-image group is classified into which scene is managed by the scene ID so that it can be identified. If there is a tie score among the scores for each scene, the CPU 101 classifies the sub-image group into one of the tie scenes according to a predetermined priority. Specifically, the CPU 101 classifies the sub-image group into scenes having a high priority among the scenes having the same score. For example, in the present embodiment, the order of priority is daily> ceremony> travel. The order of priority magnitude is not limited to this, and for example, the user may be able to set the order of priority.

It should be noted that the feature quantities used for scoring the scene classification are three, the shooting period, the number of shots, and the number of shots, but the present invention is not limited to this form. For example, a flag such as whether or not a predetermined object corresponding to each scene is included in the image data may be used as a feature amount. For example, when the predetermined object corresponding to "travel" is "sky", the score related to "travel" is set to be high in the sub-image group having a lot of image data including "sky". In addition, personal identification information may be used as a feature quantity. For example, suppose there are scenes such as "wedding" and "reception" in which "ceremonies" are further classified. Then, the CPU 101 identifies the two people included in the image data most in the main image group as the bride and groom. Then, the feature amount is a flag such as whether only the bride and groom are included or a person other than the bride and groom is included. In this case, for example, a sub-image group containing many image data containing only the bride and groom is set so that the score related to "wedding" is high, and many sub-image data including people other than the bride and groom are included. The score for the "wedding reception" of the image group is set to be high. Note that the scene classification may be performed by, for example, output by machine learning using Convolution Neural Network (CNN) or the like.

In S407, the CPU 101 sets the main subject for each album corresponding to the number input in the album number box 310 according to the user's input to the main subject designation unit 305. Here, for the sake of explanation, it is assumed that the main subject 1 is set in the album 1 and the main subject 2 is set in the album 2.

In S408, the CPU 101 executes image scoring. The image scoring in S418 is to give a score evaluated from the viewpoint described later for each image data (scoring), and is referred to when selecting the image data to be arranged in the template, which will be described later. In the present embodiment, the image scoring is performed from a plurality of viewpoints based on the feature amount of each image data acquired in S40302. That is, in the present embodiment, a plurality of points are given to each image data by image scoring. Specifically, in the present embodiment, a score based on the image quality, a score based on the main subject 1, and a score based on the main subject 2 are given to each image data.

First, image scoring based on image quality will be described. In this embodiment, for example, in image scoring based on image quality, feature quantities such as focus and the number of pixels are used. Specifically, for example, the score added to the image data whose focus feature amount is "○" acquired in S40302 is for the image data whose focus feature amount is "Δ" or "×". The score based on the image quality is added so as to be higher than the score added. Further, for example, the score based on the image quality is the image data so that the score added to the image data representing the image having a high number of pixels is higher than the score added to the image data representing the image having a low number of pixels. Is added to. The feature amount used for image scoring based on image quality may be shooting information such as lens information used at the time of shooting, or may be a compression format of an image input to an application.

Next, image scoring based on the main subject 1 and image scoring based on the main subject 2 will be described. These image scoring is performed based on the information regarding whether or not the main subject is included, which is identified using the face size and personal recognition analyzed in S40303 and S40304. For example, a score based on the main subject 1 so that the score added to the image data including the main subject 1 is higher than the score added to the image data not including the main subject 1. Is added to the image data. Further, for example, the score added to the image data in which the area (size) occupied by the main subject 1 is large is higher than the score added to the image data in which the area occupied by the main subject 1 is small. A score based on 1 is added to the image data. Further, for example, it is based on the main subject 1 so that the score added to the image data including the smiling main subject 1 is higher than the score added to the image data including the non-smiling main subject 1. Scores are added to the image data. The main subject 2 is also scored from the same viewpoint.

In S409, the CPU 101 determines whether or not the image scoring has been completed for all the image data groups specified in the pass box 302. If it is not completed (No in S409), the process returns to S408, and image scoring is executed for the image data that has not yet been processed. If it is finished (Yes in S409), the process proceeds to S410.

In S410, the CPU 101 specifies the score for the common page and the score for the individual page with respect to all the image data acquired in S402 based on the result of the image scoring executed in S409. The common page is a page commonly included in all the albums instructed to be created by the setting screen 301. On the other hand, the individual page is a page included in only one album among the albums instructed to be created by the setting screen 301. The score for the individual page is specified for each album instructed to be created by the setting screen 301.

The score ^I score _s for the common page of the image data I is expressed by the following equation (3).
^I score _s = Σ _i w _i · ^I score _i formula (3)
Here, ^I score _i represents the i-th score of each score given to the image data I (score based on quality, score based on the main subject 1, the score based on the main subject 2), w _i is the Represents the weight for the score. In the present embodiment, by setting _wi = 1/3, the score based on the image quality, the score based on the main subject 1, and the score based on the main subject 2 are equally evaluated. As a result, the score for the common page is specified so that the image quality is good and the score of the image in which each main subject is large (or large) is high. That is, the score for the common page is specified by considering each main subject corresponding to each of all the album data instructed to be created.

The score ^I score _IO of the image data I for the individual page corresponding to the album data O is represented by the following equation (4). Note that O is an album number assigned to each of the plurality of album data instructed to be created by the user. That is, in the present embodiment, points for individual pages are added to the image data I by the number of album data.

Here, ^I score _q represents a score based on the image quality given to the image data I, ^I score _o represents a score given to the image I based on the main subject s O corresponding to the album data O, and w _q is It represents the weight for the score based on the image quality, w _o represents the weight for the score based on the main subject sO. In the present embodiment, by setting w _q = w _o = 1, the score for the individual page is high so that the image quality is good and the score of the image in which the main subject so is large (or large) is high. Is identified. In other words, the score for each page is specified without considering the main subject other than the main subject sO (the main subject that does not correspond to the album data O). The identification of the score for each page is performed for each album data. That is, as a result, in S410, the score of the individual page is specified by the number of album data instructed to be created by the setting screen 301, and one score of the common page is specified. In the present embodiment, when ^I score _o is 0 points, ^I score ^I _O is 0 points regardless of the score of ^I score _q .

As described above, in the present embodiment, the evaluation for the common page and the evaluation for the individual page are performed based on different elements. Specifically, the evaluation for the common page is performed based on the elements related to the plurality of main subjects corresponding to each of the plurality of album data. On the other hand, the evaluation for the individual page corresponding to the album O is performed based on the element related to the main subject corresponding to the album O, and not based on the element related to the main subject corresponding to another album. As a result, the evaluation for the common page and the evaluation for the individual page can be appropriately performed.

It should be noted that the identification of the score for the common page and the identification of the score for the individual page were performed based on the image quality and the main subject, but the present invention is not limited to this form. For example, the score of the image data that does not include the main subject (for example, the image data classified into a “landscape”) may be specified from other image information associated with the image data. Further, for example, the image data having a small difference in shooting time from the image data having a high score may be controlled so that the score is high. Thereby, for example, it is possible to give a high score to the image data that is likely to be related to the image data including the main subject.

In S411, the CPU 101 uses the score specified in S410 to create spread data representing the spread included in the album. FIG. 5C is a flowchart showing a spread data generation process executed by the album creation application according to the present embodiment.

In S41101, the CPU 101 reads one of the scores specified in S410 with respect to all the image data acquired in S402. In this embodiment, it is assumed that the number of albums specified to be created by the user is two. Then, the CPU 101 reads the score of each image data in the order of the score for the individual page related to the album 1, the score for the individual page related to the album 2, and the score for the common page. However, the present invention is not limited to this, and the CPU 101 may read any score first. When the score for the individual page is read in S41011, the spread data for the individual page is created in the following processing, and when the score for the common page is read in S41101, the common page is read in the following processing. Spread data for will be created.

In S41102, the CPU 101 acquires candidate image data as a candidate for the image data arranged in the spread from all the image data acquired in S402 based on the score read in S41101. When the score read in S41011 is the score for the individual page, the candidate image data that is a candidate for the image data arranged in the template for the individual page is acquired here. Further, when the score read in S41011 is the score for the common page, the candidate image data that is a candidate for the image data arranged in the template for the common page is acquired here. In the present embodiment, the CPU 101 acquires image data having a score equal to or higher than the threshold value as the score read in S41101 as candidate image data. If there is no image data having a score equal to or higher than the threshold value, the image data having the highest score is used as a candidate image. Here, candidate images were acquired from all the image groups, but the present invention is not limited to this. Images already selected in the image selection process described later may be excluded from the acquisition target.

In S41103, the CPU 101 sets the number of spreads based on the result of the scene division performed in S405 and the candidate image data acquired in S41102. First, the CPU 101 specifies which number of candidate image data belongs to each scene. In this embodiment, spread data is created for each scene. Therefore, the CPU 101 specifies the number of spread data corresponding to each scene by the equation (5). The maximum number of image data per spread is determined according to the input for the number of spread photographs 306.

In the following, first, a case where the score read in S41011 is a score for an individual page will be described. Since the spread data corresponding to the individual pages is generated by the set of the spread data corresponding to each scene, the CPU 101 specifies the number of spread data corresponding to the individual pages by the equation (6). S is a scene number assigned to each scene.

Number of spread data of scene S = ceil (number of candidate image data belonging to scene S)
÷ Maximum number of image data per spread) Equation (5)
Number of spread data corresponding to individual pages = Number of spread data of Σ _S scene S Equation (6)
If the number of spread data corresponding to the individual page specified by the formula (6) is equal to or greater than the number (total number of spread data) specified by the user in the spread number box 304, the individual page is described by the following formula. Respecify the number of spread data corresponding to.
Number of spread data corresponding to individual pages = Total number of spread data-1 Equation (7)

As described above, in the present embodiment, the common page and the individual page are mixed in the album. At least one is specified as described above in order to include a spread composed of common pages in the album. An upper limit value and a lower limit value may be set for the number of spread data corresponding to individual pages. When the score read in S41011 is the score for the individual page related to the album 1, the number of spread data corresponding to the individual page included in the album 1 is specified by this process. Then, when the score read in S41011 is the score for the individual page related to the album 2, the number of spread data corresponding to the individual page included in the album 2 is specified by this process.

Next, a case where the score read in S41011 is a score for a common page will be described. Of the spreads that make up the album, the spreads other than the spreads that correspond to the individual pages are the spreads that correspond to the common pages. Therefore, the CPU 101 specifies the number of spread data corresponding to the common page by the equation (8).

Number of spread data corresponding to common page = Total number of spread data-MIN
(Number of spread data corresponding to individual pages) Equation (8)
That is, in the present embodiment, the value obtained by subtracting the number of spread data corresponding to individual pages from the total number of spread data is the number of spread data corresponding to the common page.

In the present embodiment, the number of spread data corresponding to the individual page and the spread data corresponding to the common page are set according to the number of candidate images included in each scene, but the present invention is not limited to this. For example, the number of spread data may be a number preset in the album creation application, or may be a number specified by the user.

In S41104, the CPU 101 allocates the candidate image data acquired in S41102 to each spread data. Here, first, the CPU 101 divides the candidate image data acquired in S41102 into an image data group corresponding to the number of spread data specified in S41103. If the candidate image data acquired in S41102 is candidate image data for individual pages, they are divided into image data groups corresponding to the number of spreads corresponding to the individual pages. If the candidate image data acquired in S41102 is candidate image data for a common page, they are divided into image data groups corresponding to the number of spreads corresponding to the common page. Specifically, the CPU 101 arranges the candidate image data acquired in S41102 in order of shooting time based on the information acquired in S4301. Then, when the difference in shooting time between the adjacent image data is larger than the threshold value, the CPU 101 divides the candidate image data between the adjacent image data. The division by this method is repeated until the image data group for the number of spreads specified in S41103 is formed. After that, each image data group formed by the division is assigned to the beginning of the spread of the album in order from the image data group having the first shooting date and time. That is, the image data group is assigned to each spread of the album in the order of shooting date and time. This makes it possible to create an album in which image data are arranged in order of shooting date and time. The images do not have to be arranged at the shooting date and time in one spread page.

In S41105, the CPU 101 executes an image selection process for selecting image data arranged in a spread. Here, an example of selecting four image data from the divided image data group assigned to a certain spread will be described with reference to FIG. 7. The spread is an area for two pages, but the first spread (front cover) and the last spread (back cover) are areas for one page. Further, in which spread data, which number of image data is selected is determined according to, for example, a user input for the spread photo number 306. For example, when the number of spread photos 306 based on user input is 4, the number of images selected in S41105 is determined so that the average of the image data included in each spread data in the album is 4. .. Therefore, the number of image data included in each spread data in the album may be different. If the image data is selected from the divided image data group for the individual pages, this process is executed based on the score for the individual pages. The image data selected from the divided image data group for the individual page based on the score for the individual page is the individual image data. Further, if the image data is selected from the divided image data group for the common page, this process is executed based on the score for the common page. The image data selected from the divided image data group for the common page based on the score for the common page is the common image data.

FIG. 7A shows the time difference between the shooting date and time (divided shooting period) between the image data with the earliest shooting date and time and the image data with the latest shooting date and time among the divided image data groups assigned to the spread, in other words, the divided image data It shows the shooting period of the group. Here, the image data is selected in the order of the main slot and the sub slot. Here, it is assumed that the template corresponding to the spread includes one main slot. Therefore, the image data selected for the first image is the image data for the main slot. As the image data for the main slot, the CPU 101 selects the image data (1) having the highest score specified in S410 from the image data corresponding to the divided shooting period shown in FIG. 7 (B).

The image data selected for the second and subsequent images is the image data for the subslot. The selection of the second and subsequent image data is performed by the method described below so as not to concentrate on a part of the divided shooting period. First, the CPU 101 divides the divided shooting period into two, as shown in FIG. 7 (C). Next, as shown in FIG. 7D, the CPU 101 is the second image from the image data generated during the divided shooting period (the period shown by the solid line in the figure) in which the first image data is not selected. Select the image data of. As the second image data, the image data (2) having the highest score specified in S410 is selected from the image data generated during the divided shooting period in which the first image data is not selected. To do. Next, as shown in FIG. 7 (E), the CPU 101 divides each divided imaging period shown in FIG. 7 (D) into two. Then, as shown in FIG. 7 (F), the CPU 101 generates the first image data and the second image data in the divided shooting period (the period shown by the solid line in the figure) in which neither of them is selected. The third image data is selected from the obtained image data. As the third image data, the score specified in S410 is the highest among the image data generated during the divided shooting period in which neither the first image data nor the second image data is selected. Select the point image data (3). Then, as the fourth image data, the score specified in S410 among the image data generated in the divided shooting period in which none of the first, second, and third image data is selected is obtained. Select the highest point image data.

Next, there is no image generated in the divided shooting period in which none of the first, second, and third image data is selected, and four images are generated from the image data generated in the divided shooting period. An example in which the image data of the eyes cannot be selected will be described. Here, as shown in FIG. 9 (G), it is assumed that there is no image data generated during the divided shooting period (the period indicated by the diagonal line in the figure) in which the image data has not been selected yet. In that case, the CPU 101 further divides each divided shooting period into two as shown in FIG. 9 (H). Next, as shown in FIG. 9 (I), the CPU 101 has a divided shooting period other than the divided shooting period in which it is recognized that there is no image data generated within the period, and the image data has not yet been selected (in the figure). , The fourth image data is selected from the images generated in the period indicated by the solid line). The CPU 101 selects the highest point image data (4) for the subslot among the image data generated during the divided shooting period as the fourth image data.

In S41106, the CPU 101 acquires a plurality of templates according to the input to the setting screen 301. Specifically, the CPU 101 acquires a plurality of templates of the design corresponding to the product designation unit 307. Note that the setting screen 301 may accept, for example, input of the size of the margin generated in each spread, and the template acquired here may be determined according to the input margin or the like. As described above, in the present embodiment, the image data arranged in the template is automatically selected without the image processing device 100 accepting the image data selection operation by the user.

In S41107, the CPU 101 determines the image layout of the spread to be processed and generates the spread data. Specifically, first, the CPU 101 determines a template suitable for laying out the image data selected in S41105 from the plurality of templates acquired in S41106. FIG. 8 is a flowchart showing a process of determining a template used for creating a layout image in the present embodiment.

In S801, the CPU 101 acquires the number of image data selected in S41105 and information about the image data. The information regarding the image data is, for example, the width and height of the image represented by the image data, the shooting date / time information of the image data, and the score of the image data. Here, it is assumed that the number of image data selected in S424 is 3.

In S802, the CPU 101 selects a template in which the number of image data selected in S41105 and the number of slots match. Here, since the number of image data selected in S41105 is assumed to be 3, a template having 3 slots is selected. Here, it is assumed that (1-1) to (4-4) of FIG. 9 are selected as the template having 3 slots.

In S803, the CPU 101 sorts the image data selected in S41105 in order of shooting date and time. Here, it is assumed that the shooting dates and times of the respective images represented by the three image data are in the order shown in FIG. 9A. Further, here, the image 905 is an image for the main slot (main image), and the images 906 and 907 are images for the sub slot (sub image).

In S804, the CPU 101 selects a template suitable for the main image from the templates selected in S802. In the present embodiment, the image data with the older shooting date and time is laid out in the upper left slot of the template, and the image data with the newer shooting date and time is laid out in the lower right slot. Therefore, first, the CPU 101 selects a template in which the position of the main slot corresponds to the order of the shooting date and time of the image data representing the main image among the templates selected in S802. That is, for example, when the image data representing the main image is the oldest in the order of shooting date and time, the template in which the main slot is the first slot from the left among all the slots is selected. Since the image data is sorted in the order of the shooting date and time, the CPU 101 can grasp the order of the shooting date and time of the image data representing the main image. Further, the CPU 101 finally selects a template in which the aspect ratio of the slot in which the main image is arranged matches (or is close to) the aspect ratio of the main image among the templates selected in this way. Here, since the image 905, which is the main image, has the latest shooting date and time and is a vertically long image, the templates of FIGS. 9 (3-1) to (3-4) are selected here.

In S805, the CPU 101 selects a template suitable for the sub-image from the templates selected in S802. Specifically, first, the CPU 101 selects a template in which the positions of the sub slots correspond to the order of the shooting date and time of the image data representing the sub image. Further, the CPU 101 finally selects a template in which the aspect ratio of the subslot matches (or is close to) the aspect ratio of the sub image among the templates selected in this way. Here, the image 906, which is a sub image, is an image having the oldest shooting date and time and being vertically long. Further, the image 907, which is a sub image, is a horizontally long image having the second newest shooting date and time. Therefore, the template shown in FIG. 9 (3-2) is selected. At this time, it is also specified which sub-image is arranged in which sub-slot.

In this way, the CPU 101 generates spread data by deciding which template to lay out in which slot of the template and the template used for creating the layout image corresponding to the spread. Specifically, the CPU 101 manages the information of each slot included in the selected template in association with the image data corresponding to the image laid out in each slot. That is, the spread data includes a template used for the spread and each image data arranged in the template. As described above, in the present embodiment, the template used for each page is automatically selected without the image processing device 100 accepting the image data selection operation by the user. Further, in the present embodiment, the image data is automatically arranged in the template without the image processing device 100 accepting the image data arrangement operation by the user. By this process, spread data (individual page data) corresponding to individual pages and spread data (common page data) corresponding to common pages are generated. In the above, the data is generated in the spread unit, but the data may be generated in the page unit.

In S41108, the CPU 101 determines whether or not the processing of S41105 to S41107 has been completed for all the spread data. When the score for the individual page is read in S41101, all the spread data in S41108 are all the spread data corresponding to the individual page. Further, when the score for the common page is read in S41101, all the spread data in S41108 are all the spread data corresponding to the common page. If the CPU 101 has not finished, it returns to S41105 and performs the processing of S41105 to S41107 on the spread that has not yet been processed. On the other hand, when the CPU 101 is finished, the CPU 101 shifts to S41109.

In S41109, whether or not the CPU 101 has read all the scores specified in S410 (here, the score for the individual page regarding the album 1, the score for the individual page regarding the album 2, and the score for the common page) in S41101. To judge. In other words, it is determined whether or not the template has been specified for each individual page constituting the plurality of albums instructed to be created by the user and the common page. If the CPU 101 has not finished, it returns to S41101, reads a score that has not been acquired yet, and performs processing from S41102 to S41108. On the other hand, when the CPU 101 is finished, the CPU 101 shifts to S412.

In S412, the CPU 101 combines the generated spread data to execute a spread join process for generating album data. Here, the CPU 101 creates the layout of the entire album by adding the page number information corresponding to the page numbers in the album to each spread data. At this time, the CPU 101 arranges the spread data so that the page number of the page on which the image data having a fast shooting time is arranged becomes smaller based on the shooting time of the image data arranged in the template in the spread data. After that, each spread data is combined. FIG. 10 is a flowchart showing a spread joining process executed by the album creation application according to the present embodiment.

In S1001, the CPU 101 acquires the spread data related to one album among the spread data generated in S411. In the present embodiment, for example, the spread data for the album 1 is "spread data for a common page + spread data for individual pages related to the album 1".

In S1002, the CPU 101 specifies a sort reference value (sort reference value) for each spread data acquired in S1001. In the present embodiment, the sort reference value is the average shooting time of the image data arranged in the spread data. The sort reference value is not limited to the average shooting time. For example, the sort reference value may be the average shooting position (latitude / longitude) of the image data arranged in the spread data, or may be the number of image data arranged in the spread data. Further, for example, the image analysis information (color histogram or the like) of the image data arranged in the spread data may be used.

In S1003, the CPU 101 sorts the spread data acquired in S1001 based on the sort reference value specified in S1002. As described above, since the sort reference value is the average shooting time in the present embodiment, the CPU 101 arranges the spread data so that the page number of the spread data having an early average shooting time becomes smaller.

In S1004, the CPU 101 determines whether or not the number of spread data of the album acquired in S1001 is the same as the total number of spread data. When the number of spread data of the album acquired in S1001 is not the same as the total number of spread data (No in S1004), the process proceeds to S1005. Then, when the number of spread data of the album acquired in S1001 is the same as the total number of spread data (Yes in S1004), the process proceeds to S1006.

In S1005, the CPU 101 deletes unnecessary spread data from the spread data acquired in S1001 and adjusts the number of spread data of the album to be processed to be the total number of spread data. In the present embodiment, the CPU 101 adjusts the number of spread data by selecting the spread data to be deleted from the spread data for the common page. Specifically, among the spread data for the common page, the spread data whose average shooting time is closest to the average shooting time of the spread data for any of the individual pages is deleted. The CPU 101 adjusts the number of spread data by repeating this deletion process. The average shooting time is the average of the shooting times of a plurality of image data included in the spread data. After that, the CPU 101 shifts to S1004. In the present embodiment, the spread data to be deleted is selected from the spread data for the common page, and the spread data to be deleted is not selected from the spread data for the individual pages, but the present invention is not limited to this. For example, it is not necessary to select the spread data to be deleted from the spread data for individual pages and to select the spread data to be deleted from the spread data for the common page. Further, for example, the spread data to be deleted may be selected from both the spread data for individual pages and the spread data for common pages. When the number of spread data is determined in this way, the CPU 101 creates album data by combining the spread data that remains without being deleted in the order sorted by S1003.

In S1006, the CPU 101 determines whether or not the processes S1001 to S1005 have been performed on the spread data related to all the albums instructed to be created by the setting screen 301. In other words, the CPU 101 determines whether or not the album data for all the albums instructed to be created by the setting screen 301 has been created. When the spread data of all the albums is not processed from S1001 to S1005, the CPU 101 shifts to S1001, acquires the spread data of the album that has not been acquired yet, and processes the spread data. .. When the processes of S1001 to S1005 are performed for the spread data related to all the albums, the CPU 101 ends the automatic layout process and proceeds to S413.

In S413, the CPU 101 outputs the created album data. As the output of the album data, the CPU 101 can execute, for example, display the album data on the display 105, transmit the album data, print the album based on the album data, and the like. For example, the CPU 101 can make the printer print an album based on the created album data by transmitting the created album data to the printer.

In the present embodiment, it is assumed that the user can arbitrarily edit the completed spread data. For example, if there is image data to be changed among the image data arranged in each slot, the user clicks the image data to be changed with the mouse 107. After that, the user can select the image data to be arranged in place of the image data to be changed, so that the image data arbitrarily selected by the user can be newly arranged in place of the clicked image data. When the user clicks the image data to be changed, the CPU 101 may display the image data candidates after the change. Further, for example, when the image data that the user wants to change is the image data in the individual page, the CPU 101 may display the image data having a high score for the individual page as a candidate for the changed image data. Similarly, when the image data that the user wants to change is the image data in the common page, the CPU 101 may display the image data having a high score for the common page as a candidate for the changed image data.

As described above, in the present embodiment, the album creation application can generate album data for creating an album including a common page and an individual page. Further, the selection criteria of the image data arranged on the common page and the selection criteria of the image data arranged on the individual pages are controlled to be different. By such control, the image data suitable for the common page can be selected as the image data arranged on the common page, and the image data suitable for the individual page can be selected as the image data arranged on the individual page. .. In addition, it is possible to prevent the image data arranged on the common page from becoming the same as the image data arranged on the individual pages.

(Second Embodiment)
In the above-described embodiment, the image data belonging to the same scene is used for both the spread data for the common page and the spread data for the individual pages. In the present embodiment, the image data belonging to the same scene is used only for either the spread data for the common page or the spread data for the individual pages. As a result, it is possible to prevent the image data belonging to the same scene from being included in both the spread data for the common page and the spread data for the individual pages.

Unless otherwise specified, the configuration of the present embodiment shall be the same as the configuration of the first embodiment.

FIG. 11 is a flowchart showing an automatic layout process executed by the album creation application according to the present embodiment. The flowchart shown in FIG. 11 is realized, for example, by the CPU 101 reading a program corresponding to the album creation application stored in the HDD 104 into the ROM 102 or the RAM 103 and executing the program.

The processes from S401 to S410 are the same as the processes described in the first embodiment.

In S1101, the CPU 101 specifies whether it is suitable for a common page or an individual page for each scene. In other words, the CPU 101 specifies whether to apply the score for the common page or the score for the individual page for each scene. The image data group included in the scene suitable for the common page is the common image data group, and the image data group included in the scene suitable for the individual page is the individual image data group. In the present embodiment, it is specified by the following formula whether the score for the common page or the score for the individual page is applied to each scene.

_{^{S Q P = Σ I∈S I T}} P (9)

^I score _P represents the value of the score P added to the image data I, S represents the scene number assigned to the scene to be determined, and THR represents the threshold value. ^S Q _P is an indication of whether the page corresponding to the score P is suitable much to the determination target scene. The score P is either a score Pd for individual pages or a score Pc for common pages.

CPU101, if the score P is a score for individual pages, the value ^I T _Pd indicating whether the image data I are suitable for individual pages calculated by the equation (10). Then CPU101, if the score P is a score for the common page, the value ^I T _Pc that indicates whether the image data I are suitable for common page is calculated by equation (10). As a result, for the image data in which the score for the individual page is higher than the threshold value, a value indicating that the image data is suitable for the individual page is calculated by the equation (10). Then, for the image data in which the score for the common page is higher than the threshold value, a value indicating that the image data is suitable for the common page is calculated by the equation (10).

After that, when the score P is a score for an individual page, the CPU 101 uses the equation (9) to set a value ^S Q _Pd indicating how much image data suitable for the individual page is included in the scene to be determined. calculate. Further, when the score P is a score for a common page, the CPU 101 calculates a value ^S Q _Pc indicating how much image data suitable for the common page is included in the scene to be determined by the equation (9). To do.

Then, specified by equations (9) and (10), the score Pd relates index ^S Q _Pd for index ^S Q _Pc and the individual pages for scoring Pc for common page, the determination target scene is a common page Identify which of the individual pages is suitable. Specifically, by using a score corresponding to the larger value out of the index ^S Q _Pd about score Pd for individual and index ^S Q _Pc about the score Pc for common page, the image data belonging to the determination target scene Identifies to create spread data in which is placed. By repeating this process for all the scenes, the CPU 101 can specify which scene is suitable for the individual page or the common page. As a result, the image data belonging to the scene is used only for the page suitable for the scene among the common page and the individual page. By this processing, for example, the score for the common page can be applied to the scenes (1) to (6) in FIG. 5 (B), and the score for the individual page can be applied to the scenes (7) to (10). Be identified.

In this embodiment, the score for the individual page and the score for the common page of the image data included in each scene are used as an index for specifying which of the common page and the individual page is suitable for each scene. Was used, but it is not limited to this. For example, an index such as the amount of image data in which the main subject is shown, the amount of image data in which the number of faces in the picture is large, or the number of image data in the scene may be used. Further, it may be determined whether each scene is suitable for a common page or an individual page based on the type of scene determined by the scene classification result in S406. For example, a scene classified as "wedding" was identified as suitable for a common page with the bride and groom as the main subject, and a scene classified as "wedding reception" was identified with relatives or friends as the main subjects, respectively. Individual pages are identified as suitable. In this way, information on which type of scene is identified as suitable for which page may be incorporated in the album creation application in advance.

In the above description, as a method for specifying which scene is suitable for the individual page or the common page, the method using the formula (9) or the formula (10) has been described, but the method is limited to this form. Not done. For example, it is possible to specify which scene is suitable for an individual page or a common page by the method shown below.

For example, the CPU 101 calculates the average value of the scores for the common page and the average value of the scores for the individual pages of each image data included (included) in the scene to be determined. Then, when the average value of the scores for the common page is larger than the average value of the scores for the individual pages, the CPU 101 determines that the scene to be determined is suitable for the scores for the common page. Further, when the average value of the scores for the individual pages is larger than the average value of the scores for the common pages, the CPU 101 determines that the scene to be determined is suitable for the scores for the individual pages.

Further, for example, the CPU 101 sets the maximum value among the scores for the common page of each image data included in the determination target scene and the maximum value among the scores for the individual pages of each image data included in the determination target scene. calculate. Then, when the maximum value of the score for the common page is larger than the maximum value of the score for the individual page, the CPU 101 determines that the scene to be determined is suitable for the score for the common page. Further, when the maximum value of the score for the individual page is larger than the maximum value of the score for the common page, the CPU 101 determines that the scene to be determined is suitable for the score for the individual page.

In S1102, the CPU 101 uses the score specified in S410 to create spread data representing the spread included in the album. FIG. 11C is a flowchart showing a spread data generation process executed by the album creation application according to the present embodiment.

The process of S41101 is the same as the process described in the first embodiment.

In S110201, the CPU 101 acquires candidate image data as a candidate for the image data arranged in the template from the image data belonging to the scene corresponding to the score read in S41101 based on the score read in S41101. When the score read in S41101 is a score for an individual page, the scene corresponding to the score read in S41101 is a scene specified in S1101 as being suitable for an individual page. Further, when the score read in S41101 is a score for a common page, the scene corresponding to the score read in S41101 is a scene specified in S1101 as being suitable for the common page. When the score read in S41011 is the score for the individual page, the candidate image data that is a candidate for the image data arranged in the template for the individual page is acquired here. Further, when the score read in S41011 is the score for the common page, the candidate image data that is a candidate for the image data arranged in the template for the common page is acquired here. In the present embodiment, the CPU 101 acquires image data having a score equal to or higher than the threshold value as the score read in S41101 as candidate image data. If there is no image data having a score equal to or higher than the threshold value, the image data having the highest score is used as a candidate image. The image already selected in the image selection process described later may be excluded from the acquisition target.

In S110202, the CPU 101 sets the number of spreads based on the result of the scene division performed in S405 and the candidate image data acquired in S110201. The details of this process are the same as those described in S41103 of the first embodiment, but the differences from the first embodiment will be described below. In the first embodiment, regardless of whether the score read in S41101 is a score for an individual page or a score for a common page, the equation (5) is applied to all the scenes to apply the spread data. Identified the number. However, in the present embodiment, when the score read in S41101 is the score for the individual page, the number of spread data is specified only for the scene specified in S1101 as being suitable for the individual page. Further, when the score read in S41101 is the score for the common page, the number of spread data is specified only for the scene specified in S1101 as being suitable for the common page.

In S110203, the CPU 101 divides the candidate image data acquired in S110201 into image data groups for the number of spreads specified in S110202. The details of this process are the same as those described in S41104 of the first embodiment. After that, the CPU 101 shifts to S41105.

Subsequent processing is the same as the processing described in the first embodiment.

By executing such control, in the present embodiment, the image data belonging to the same scene is controlled to be used only for either the spread data for the common page or the spread data for the individual page. As a result, it is possible to prevent the image data belonging to the same scene from being included in both the spread data for the common page and the spread data for the individual pages.

(Third Embodiment)
As described above, each scene contains one or more image data. One image data group included in one scene is referred to as a scene image data group. In the first embodiment, both the image data used for the spread data for the common page and the image data used for the spread data for the individual pages are acquired from all the scene image data groups. In the present embodiment, the image data used for the spread data for the common page is acquired from all the scene image data groups. Then, the image data used for the spread data for the individual page is not acquired from all the scene image data groups, but is acquired only from some scene image data groups.

Unless otherwise specified, the configuration of the present embodiment shall be the same as the configuration of the first embodiment.

FIG. 12 is a flowchart showing an automatic layout process executed by the album creation application according to the present embodiment. The flowchart shown in FIG. 12 is realized, for example, by the CPU 101 reading a program corresponding to the album creation application stored in the HDD 104 into the ROM 102 or the RAM 103 and executing the program.

The processes from S401 to S410 are the same as the processes described in the first embodiment.

In S1201, the CPU 101 specifies whether or not it is suitable for individual pages for each scene. In other words, the CPU 101 specifies whether to apply the score for the common page or the score for the individual page for each scene. For example, it is specified that the scores for the common page are applied to the scenes (1) to (8) in FIG. 5 (A), and the scores for the individual pages are applied to the scenes (2) and (5). In the present embodiment, it is specified that the score for the common page is applied to all the scenes. Then, to which scene the score for the individual page is applied is specified by the same equations (11) and (12) as the equations (9) and (10) described in the second embodiment.

_{^{S Q P = Σ I∈S I T}} P formula (11)

CPU101 is as described above in the description of formula (9) and (10), calculates an index ^S Q _Pd about score Pd for individual pages. Then, CPU 101 determines that if the index ^S Q _Pd about score Pd for individual pages is the threshold value THR2 above, the determination target scene is suitable for individual pages. The CPU101 determines that the index ^S Q _Pd relates score _{P d} for the individual pages is less than the threshold value THR2, the scene determination target is not suitable for individual pages. By repeating this process for all the scenes, the CPU 101 can specify which scene is suitable for the individual page.

In the present embodiment, the score for the individual page of the image data included in each scene is used as an index for specifying whether the image is suitable for the individual page for each scene, but the present invention is not limited to this. For example, an index such as the amount of image data in which the main subject is shown, the amount of image data in which the number of faces in the picture is large, or the number of image data in the scene may be used. Further, it may be determined whether each scene is suitable for an individual page based on the type of scene determined by the scene classification result in S406. For example, a scene classified as a "wedding reception" is identified as suitable for individual pages with relatives or friends as the main subjects. In this way, information on which type of scene is identified as suitable for the individual page may be incorporated in the album creation application in advance.

In S1202, the CPU 101 uses the score specified in S410 to create spread data representing the spread included in the album. FIG. 11C is a flowchart showing a spread data generation process executed by the album creation application according to the present embodiment.

The process of S41101 is the same as the process described in the first embodiment.

In S120201, the CPU 101 acquires candidate image data that is a candidate for the image data arranged in the template from the image data belonging to the scene corresponding to the score read in S41011, based on the score read in S41101. When the score read in S41101 is a score for an individual page, the scene corresponding to the score read in S41101 is a scene specified in S1101 as being suitable for an individual page. Further, when the score read in S41011 is a score for a common page, the scenes corresponding to the score read in S41101 are all scenes. When the score read in S41011 is the score for the individual page, the candidate image data that is a candidate for the image data arranged in the template for the individual page is acquired here. Further, when the score read in S41011 is the score for the common page, the candidate image data that is a candidate for the image data arranged in the template for the common page is acquired here. In the present embodiment, the CPU 101 acquires image data having a score equal to or higher than the threshold value as the score read in S41101 as candidate image data. If there is no image data having a score equal to or higher than the threshold value, the image data having the highest score is used as a candidate image. The image already selected in the image selection process described later may be excluded from the acquisition target.

Further, in the present embodiment, candidate image data is selected according to the following formula.

Or ^I C _P is scored read in S41101 is, if it is one of the score P of the scores for the common page with scores P1 for individual pages P2, the image data I is selected as the candidate image data It is a value indicating whether or not. SI is a set of image data belonging to the scene S corresponding to the score P. ^I score _{p = P1} and ^I score _{p ≠ P1} represent the score P1 for the individual page of the image data I and the score P1 for the individual page of the image data I (that is, the score P2 for the common page). THR represents a threshold. ^{When I} C _P is 1, ^I C _P means that the image data I is selected as the candidate image data, and when ^I C _P is 0, ^I C _P means that the image data I is the candidate image. Indicates that the data is not selected.

As a result, as the candidate image data that is a candidate for the image data to be arranged in the template for the individual page, the image data whose score for the individual page is higher than the score for the common page is selected. Further, as the candidate image data that is a candidate for the image data arranged in the template for the common page, the image data whose score for the common page is higher than the score for the individual page is selected. By adopting such a form, it is possible to prevent the same image data from being used on the individual page and the common page. The method of selecting image data according to the above formula may be applied, for example, in the first embodiment or the second embodiment.

In S120202, the CPU 101 sets the number of spreads based on the result of the scene division performed in S405 and the candidate image data acquired in S110201. The details of this process are the same as those described in S41103 of the first embodiment, but the differences from the first embodiment will be described below. In the first embodiment, regardless of whether the score read in S41101 is a score for an individual page or a score for a common page, the equation (5) is applied to all the scenes to apply the spread data. Identified the number. However, in the present embodiment, when the score read in S41101 is the score for the individual page, the number of spread data is specified only for the scene specified in S1101 as being suitable for the individual page. On the other hand, when the score read in S41011 is the score for the common page, the number of spread data is specified for all the scenes.

In S120203, the CPU 101 divides the candidate image data acquired in S120201 into image data groups for the number of spreads specified in S120202. The details of this process are the same as those described in S41104 of the first embodiment. After that, the CPU 101 shifts to S41105.

Subsequent processing is the same as the processing described in the first embodiment.

As described above, in the present embodiment, all the scenes are candidates for selecting the image for the common page, so that only some scenes are candidates for selecting the image for the common page. Compared with, the possibility that a better image is selected as the image for the common page is improved. In addition, since only some scenes are candidates for selecting an image for an individual page, the image selected as the image for the common page and the image selected as the image for the individual page become the same. It can be suppressed from being stored.

In the present embodiment, the image data used for the spread data for the common page is acquired from all the scene image data groups, and the image data used for the spread data for the individual pages is all the scene image data groups. It was not acquired from, but was acquired only from some scene image data groups. However, it is not limited to this form. For example, there are cases where the number of image data suitable for spread data for individual pages is small. In such a case, for example, the image data used for the spread data for individual pages may be acquired from all the scene image data groups. Further, the image data used for the spread data for the common page may not be acquired from all the scene image data groups, but may be acquired only from some scene image data groups. As a result, the image selected as the image for the common page and the image selected as the image for the individual page become the same while securing a sufficient number of image data to be used for the spread data for the individual page. Can be suppressed.

(Fourth Embodiment)
In the above-described embodiment, the album data is generated without distinguishing between the page corresponding to the cover page and the other pages. In the present embodiment, the album data is generated by distinguishing the page corresponding to the cover page from the other pages. Further, in the present embodiment, a mode in which the page corresponding to the cover page is controlled to be a common page and a mode in which the page corresponding to the cover page is controlled to be an individual page will be described.

Unless otherwise specified, the configuration of the present embodiment shall be the same as the configuration of the first embodiment.

In the present embodiment, the album creation application further displays the cover mode setting area 1400 for accepting the cover mode setting as shown in FIG. 14A on the setting screen 301. The area 1401 is an area for selecting an individual mode as the cover mode, and the area 1402 is an area for selecting a common mode as the cover mode. The individual mode is a mode for controlling the page corresponding to the cover page to be an individual page, and the common mode is a mode for controlling the page corresponding to the cover page to be a common page. The cover mode selected here is applied to all the albums instructed to be created by the setting screen 301, but the form is not limited to this, and the cover mode may be selected for each album.

FIG. 13 is a flowchart showing an automatic layout process executed by the album creation application according to the present embodiment. The flowchart shown in FIG. 13 is realized, for example, by the CPU 101 reading a program corresponding to the album creation application stored in the HDD 104 into the ROM 102 or the RAM 103 and executing the program.

The processes from S401 to S411 are the same as the processes described in the first embodiment.

In S1301, the CPU 101 determines a cover layout, and executes a cover data generation process for generating cover data for printing the cover according to the determined layout. In the present embodiment, the front cover data is data for printing pages corresponding to each of the front cover and the back cover. However, the present invention is not limited to this form, and for example, the cover data may be data for printing a page corresponding only to the front cover. FIG. 13D is a flowchart showing a cover data generation process executed by the album creation application according to the present embodiment.

In S130101, the CPU 101 specifies which of the plurality of albums instructed to be created by the setting screen 301 to generate the cover data of the album.

In S130102, the CPU 101 specifies the cover mode of the album specified in S13101 based on the user input to the cover mode setting area 1400.

In S130103, the CPU 101 acquires cover candidate image data that is a candidate for image data arranged on the cover of the album specified in S130101. Specifically, when the mode of the cover page of the album specified in S130101 is the individual mode, the CPU 101 selects the image data included in the spread data corresponding to the individual page among the spread data generated in S411 as the cover candidate. Acquire as image data. Then, when the mode of the cover of the album specified in S130101 is the common mode, the CPU 101 acquires the image data included in the spread data corresponding to the common page among the spread data generated in S411 as the cover candidate image data. To do.

In S130104, the CPU 101 selects the image data to be arranged on the cover from the cover candidate image data. In the present embodiment, since there is only one image data arranged on the cover, the CPU 101 selects only one image data. Specifically, when the cover mode of the album specified in S130101 is the individual mode, the CPU 101 selects image data having a high score for individual pages from the cover candidate image data. The score for the individual page referred to at this time is the score for the individual page evaluated based on the main subject set in the album specified in S130101. Further, when the mode of the cover of the album specified in S130101 is the common mode, the CPU 101 selects the image data having a high score for the common page from the cover candidate image data. If there are a plurality of image data arranged on the cover, a plurality of image data may be selected at this time.

In the above description, the image data to be arranged on the cover is selected from the image data included in the spread data generated in S411, but the present invention is not limited to this form. As long as the image data corresponds to the cover mode (that is, the score corresponding to the cover mode is high), the image data not included in the spread data generated in S411 may be selected.

In addition, image data may be selected based on factors other than the score corresponding to the cover mode. For example, the image data in which only the main subject is shown may be preferentially selected over the image data in which a person other than the main subject is shown. Further, the image data corresponding to the slot design and aspect ratio arranged in the cover template may be selected with priority over the image data not corresponding to them. Further, the image data whose resolution of the image data when arranged in the slot is equal to or higher than a predetermined value may be preferentially selected.

In S130105, the CPU 101 acquires a template for the cover page. In this embodiment, it is assumed that only one template for the cover page is prepared. An example of the cover template acquired at this time is shown in FIG. 15 (A). In each cover template shown in FIG. 15, the area on the right side with respect to the center line is the area corresponding to the front cover, and the area on the left side with respect to the center line is the area corresponding to the back cover. For example, the slot 1502 is arranged in the area corresponding to the front cover of the front cover template 1501, and none of the slots is arranged in the area corresponding to the back cover of the front cover template 1501. In S130105, templates for a plurality of different types of covers may be acquired. In addition, slots may be arranged in the area corresponding to the back cover. It should be noted that the cover template as shown in FIG. 15 and the template for pages other than the cover as shown in FIG. 9 have different layouts such as the size and number of slots. In addition, the cover template may be provided with an area for arranging text such as an album name.

In S130106, the CPU 101 generates cover data. Specifically, the CPU 101 generates cover data by arranging the image data selected in S130104 in the slot of the template acquired in S130105. When a plurality of cover page templates have been acquired in S130105, the CPU 101 determines which of the plurality of cover page templates should be used and which image data should be placed in which slot. It may be determined in the same manner as the process shown in FIG. If the slot is also arranged in the area corresponding to the back cover, the image data selected in S130104 is also arranged in the slot arranged in the area corresponding to the back cover. For example, even when the front cover mode is the common mode, image data for individual pages (image data with a high score for individual pages) is placed in the slots arranged in the area corresponding to the back cover. You may.

In S130107, it is determined whether or not the generation of the cover data of all the albums instructed to be created by the setting screen 301 is completed. If it is not finished, the process returns to S130101 and specifies that the cover data of the album for which the cover data has not been generated is generated. On the other hand, if it is finished, the process proceeds to S1302.

In S1302, the CPU 101 executes a spread combination process for generating album data by combining the generated cover data and each spread data. This process is the same as S412 described in the first embodiment, but the cover data and the page number corresponding to the back cover are the smallest and the page number of the page corresponding to the back cover is the largest. After arranging each spread data, combine them. At this time, the spread data other than the cover data is arranged based on the sort reference value, but the cover data is arranged regardless of the sort reference value. In addition, when adjusting the number of spread data, the cover data is controlled so as not to be deleted. After that, the CPU 101 shifts to S413.

Subsequent processing is the same as the processing described in the first embodiment.

With such a form, the album data can be generated by distinguishing the page corresponding to the cover page from the other pages. Further, as an image included in the cover, an image suitable for the cover can be arranged in the cover template.

In the above description, the mode in which the user can select the individual mode and the common mode has been described, but the mode is not limited to this mode. For example, the cover data may be created only in one of the individual mode and the common mode, which is predetermined. In that case, it is not necessary to display the cover mode setting area and accept the user to select the cover mode.

(Fifth Embodiment)
In this embodiment, a mode for accepting the cover mode setting in more detail will be described.

Unless otherwise specified, the configuration of the present embodiment shall be the same as the configuration of the first embodiment.

In the present embodiment, the album creation application further displays the cover mode setting area 1410 for accepting the cover mode setting as shown in FIG. 14B on the setting screen 301. In the present embodiment, it is assumed that the area for selecting the individual mode as the cover mode includes three areas (areas 141 to 1413). Region 1411 is similar to region 1402. The area 1412 is an area for selecting an individual mode for arranging an image including a main subject set in another album on the back cover. The area 1413 is an area for selecting an individual mode for arranging an image including a main subject set in another album on the front cover. Region 1413 is similar to region 1403. The cover mode selected here is applied to all the albums instructed to be created by the setting screen 301, but the form is not limited to this, and the cover mode may be selected for each album.

The album data generation process when the area 1411 is selected is the same as the album data generation process when the area 1402 is selected. Further, the album data generation process when the area 1413 is selected is the same as the album data generation process when the area 1403 is selected.

The processing when the area 1412 is selected will be described. In S130104, the CPU 101 selects high image data for individual pages evaluated based on the main subject set in the album specified in S130101, as in the third embodiment. Further, the CPU 101 selects high image data for individual pages evaluated based on the main subject set in the album other than the album specified in S130101.

In S130105, the CPU 101 acquires the cover template 1503 (FIG. 15B) corresponding to the area 1412.

In S130106, the CPU 101 arranges image data having a high score for individual pages evaluated based on the main subject set in the album specified in S130101 in slot 1504 in the cover page. Then, the CPU 101 arranges the image data having a high score for the individual page evaluated based on the main subject set in the album other than the album specified in S130101 in the slots 1505 and 1506 in the back cover. As a result, it is possible to increase the variation of the layout of the back cover of the album while making the main subject set in the album specified in S130101 stand out.

Subsequent processing is the same as the processing described in the third embodiment.

The processing when the area 1413 is selected will be described. In S130104, the CPU 101 selects high image data for individual pages evaluated based on the main subject set in the album specified in S130101, as in the third embodiment. Further, the CPU 101 selects high image data for individual pages evaluated based on the main subject set in the album other than the album specified in S130101.

In S130105, the CPU 101 acquires the cover template 1507 (FIG. 15C) corresponding to the area 1413.

In S130106, the CPU 101 arranges high-scoring image data for individual pages evaluated based on the main subject set in the album specified in S130101 in slot 1508 in the cover page. Then, the CPU 101 arranges image data having a high score for individual pages evaluated based on the main subject set in an album other than the album specified in S130101 in slots 1509 and 1510 in the back cover. Slot 1508 is larger than slot 1509 and slot 1510. As a result, it is possible to increase the variation of the layout of the front cover of the album while making the main subject set in the album specified in S130101 stand out.

Subsequent processing is the same as the processing described in the first embodiment.

(Sixth Embodiment)
In this embodiment, a mode different from the processing in the above-described embodiment will be described as a processing when the common mode is selected as the cover mode.

In the above-described embodiment, when the cover mode is the common mode, the CPU 101 selects image data having a high score for the common page from the cover candidate image data. However, in the present embodiment, when the cover mode is the common mode, a plurality of image data having a high score for individual pages are selected from the cover candidate image data. Specifically, for example, it is assumed that three albums, an album in which the main subject A is set, an album in which the main subject B is set, and an album in which the main subject C is set are instructed to be created. In that case, in S130104, the CPU 101 has image data having a high score for the individual page based on the main subject A, image data having a high score for the individual page based on the main subject B, and image data for the individual page based on the main subject C. Select each image data with a high score. The number of image data selected is not limited to three. At least, a number of image data equal to or larger than the number of albums instructed to be created may be selected.

In S130105, the CPU 101 acquires the cover template 1511 (FIG. 15D) for the common mode.

In S130106, the CPU 101 arranges each image data selected in S130104 in slots 1512 to 1514, respectively. It is assumed that the sizes of slots 1512 to 1514 are the same. Further, which image data is arranged in which slot is not particularly limited. For example, high-scoring image data for individual pages evaluated based on the main subject of the album identified in S130101 may be placed in slot 1513 located in the center of the cover area.

As described above, in the present embodiment, the cover of the common mode is configured by arranging a plurality of image data corresponding to each main subject on the cover. When the individual mode is selected as the cover mode, at least one image data corresponding to one main subject is arranged on the cover as described in the fourth embodiment and the fifth embodiment. ..

(Other embodiments)
In the above-described embodiment, the form in which the number of spread data corresponding to individual pages differs depending on the album has been described. However, the present invention is not limited to this form, and the number of spread data corresponding to individual pages may be controlled to be the same in all of the plurality of albums instructed to be created by the user.

In the above-described embodiment, the form in which the number of spread data corresponding to the common page differs depending on the album has been described. However, the present invention is not limited to this form, and the number of spread data corresponding to the common page may be controlled to be the same in all of the plurality of albums instructed to be created by the user.

In the above-described embodiment, the set of the spread data for the common page and the spread data for the individual pages is sorted by the sort reference value to generate the album data. That is, the position (page number) of the spread data for the common page and the spread data for the individual pages in the album data was different for each album data. However, the present invention is not limited to this form, and for example, the position of the spread data for the common page and the position of the spread data for the common page may be fixed in each album data. For example, each spread data may be arranged so that the spread data for individual pages is located after the spread data for the common page. More specifically, for example, even if each spread data is arranged so that the spread data for the common page sorted by the sort reference value is followed by the spread data for the individual pages sorted by the sort reference value. good. Of course, each spread data may be arranged so that the spread data for the common page is located after the spread data for the individual pages.

Each of the above-described embodiments is also realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiment is supplied to the system or device via a network or various storage media, and the computer (CPU, MPU, etc.) of the system or device reads and executes the program. It is a process to do. Further, the program may be executed on one computer or may be executed in conjunction with a plurality of computers. Further, it is not necessary to realize all of the above-mentioned processes by software, and a part or all of the processes may be realized by hardware such as ASIC. Further, the CPU is not limited to one that performs all processing by one CPU, and a plurality of CPUs may perform processing while appropriately coordinating with each other.

Claims (23)

On the computer of the image processing device that generates multiple album data corresponding to multiple albums,
The acquisition step to acquire multiple image data and
A first selection step of selecting at least one image data out of the plurality of image data as common image data corresponding to an image arranged on a common page which is a page common to all the plurality of albums.
A first generation step of generating common page data corresponding to the common page based on the at least one image data selected as the common image data, and
A second selection step of selecting at least one image data out of the plurality of image data as individual image data corresponding to an image arranged on an individual page which is a page not common to all the plurality of albums.
A second generation step of generating a plurality of individual page data corresponding to the individual page based on the at least one image data selected as the individual image data.
A third generation step of generating the plurality of album data based on the common page data and the plurality of individual page data is executed.
The individual page data corresponding to the first album data among the plurality of album data and the individual page data corresponding to the second album data among the plurality of album data are different.
The common page data corresponding to the first album data among the plurality of album data and the common page data corresponding to the second album data among the plurality of album data are the same.
A program characterized in that cover image data corresponding to an image arranged on the cover of an album is controlled to be selected as the individual image data. The first aspect of claim 1 is that the cover image data is selected as the individual image data from the image data corresponding to the images already selected as the individual image data and arranged on a page other than the cover. Described program. Further execute the acceptance step of accepting the user's input regarding the cover data corresponding to the cover.
The program according to claim 1 or 2, wherein the cover image data is controlled so as to be selected as image data based on the input among the common image data and the individual image data. As the image data corresponding to the image already selected as the individual image data corresponding to the first album data and arranged on the page other than the cover page, and the individual image data corresponding to the second album data. The program according to claim 2, wherein the cover image data is selected as the individual image data from the image data corresponding to the images already selected and arranged on the page other than the cover. Further execute the acceptance step of accepting the user's input regarding the cover data corresponding to the cover.
When the input is the first input, the image data corresponding to the image already selected as the individual image data corresponding to the first album data and arranged on the page other than the cover page, and the second image data. The cover image data is selected as the individual image data from the image data already selected as the individual image data corresponding to the album data of the above and corresponding to the images arranged on the pages other than the cover.
When the input is the second input, the image data corresponding to the image already selected as the individual image data corresponding to the first album data and arranged on the page other than the cover page, and the second image data. The cover image data is selected as the individual image data from any of the image data already selected as the individual image data corresponding to the album data of the above and corresponding to the image arranged on the page other than the cover. The program according to claim 4, wherein the program is characterized by the above. The program according to any one of claims 1 to 5, wherein the cover image data corresponding to the image arranged on the back cover of the album is controlled to be selected as the individual image data. A first evaluation step of evaluating each of the plurality of image data based on the first element, and
A second evaluation step of evaluating each of the plurality of image data based on a second element different from the first element is further executed.
Of the at least one image data group specified as the common image data group, at least one image data is selected as the common image data based on the evaluation based on the first element.
Of the at least one image data group specified as the individual image data group, at least one image data is selected as the individual image data based on an evaluation based on the second element. The program according to any one of claims 1 to 6. Each of the plurality of image data is evaluated by the second element relating to the first album data and the second element relating to the second album data.
At least one image data out of the plurality of image data is automatically used as the individual image data corresponding to the first album data based on the evaluation based on the second element regarding the first album data. Selected,
At least one of the plurality of image data is automatically used as the individual image data corresponding to the second album data based on the evaluation based on the second element regarding the second album data. Selected,
The individual page data corresponding to the first album data is generated based on at least one image data selected as the individual image data corresponding to the first album data.
The individual page data corresponding to the second album data is generated based on the at least one image data selected as the individual image data corresponding to the second album data.
The album data corresponding to the first album data is generated based on the common page data and the individual page data corresponding to the first album data.
The program according to claim 7, wherein the album data corresponding to the second album data is generated based on the common page data and the individual page data corresponding to the second album data. .. Further executing the main subject identification step of identifying at least one main subject corresponding to each of the plurality of album data is performed.
The first element includes an element relating to the at least one main subject corresponding to the first album data and an element relating to the at least one main subject corresponding to the second album data.
The second element relating to the first album data includes an element relating to the at least one main subject corresponding to the first album data, and the element relating to the at least one main subject corresponding to the second album data. Does not contain elements
The second element relating to the second album data includes an element relating to the at least one main subject corresponding to the second album data, and the element relating to the at least one main subject corresponding to the first album data. The program according to claim 8, wherein the program does not include an element. The program according to claim 8 or 9, wherein the first element and the second element include an element related to image quality. By the evaluation based on the first element, the first evaluation value is added to the plurality of image data.
By the evaluation based on the second element, the second evaluation value is added to the plurality of image data.
At least one image data out of the plurality of image data is automatically selected as the common image data based on the first evaluation value.
One of claims 8 to 10, wherein at least one image data out of the plurality of image data is automatically selected as the individual image data based on the second evaluation value. The program described in. Of the plurality of image data, at least one image data to which the first evaluation value having a larger value than the other image data is added is automatically selected as the common image data.
A claim characterized in that at least one image data to which the second evaluation value having a larger value than the other image data is added is automatically selected as the individual image data among the plurality of image data. Item 2. The program according to item 11. Of the plurality of image data, at least one to which the first evaluation value having a larger value than the other image data is added and the first evaluation value having a value larger than the second evaluation value is added. One image data is automatically selected as the common image data,
Of the plurality of image data, at least one to which the second evaluation value having a larger value than the other image data is added and the second evaluation value having a value larger than the first evaluation value is added. The program according to claim 12, wherein one image data is automatically selected as the individual image data. A division step of dividing the plurality of image data into a plurality of image data groups according to a predetermined standard, and
A first specific step of specifying at least one image data group among the plurality of image data groups as a common image data group for selecting the common image data, and
A second specific step of identifying at least one image data group among the plurality of image data groups as an individual image data group for selecting the individual image data is further executed.
Of the at least one image data group specified as the common image data group, at least one image data is selected as the common image data.
The invention according to any one of claims 1 to 13, wherein at least one image data out of the at least one image data group specified as the individual image data group is selected as the individual image data. Described program. The 14th aspect of claim 14, wherein at least one image data group out of at least one image data group specified as the common image data group is controlled so as not to be specified as the individual image data group. program. The program according to claim 15, wherein all the image data groups of the at least one image data group specified as the common image data group are controlled so as not to be specified as the individual image data group. .. All the image data groups among the plurality of image data groups are specified as the common image data group, and the image data group is specified.
The program according to claim 15, wherein at least one image data group among the plurality of image data groups is not specified as the individual image data group. The common page data is generated by automatically arranging the at least one image data selected as the common image data in the first template without accepting the arrangement operation by the user.
The second template is characterized in that the individual page data is generated by automatically arranging the at least one image data selected as the individual image data without accepting the arrangement operation by the user. The program according to any one of claims 1 to 17. The program according to claim 18, wherein the template in which the cover image data is arranged and the template in which the image data other than the cover image data is arranged are different from each other. The cover image data already selected as the individual image data corresponding to the first album data and selected from the image data corresponding to the image arranged on the page other than the cover is the center of the cover. The program according to claim 18 or 19, wherein the common page data corresponding to the first album data is generated by being arranged in the first template as described above. The output step of outputting the plurality of album data and the output of the plurality of album data to be further executed include displaying the plurality of album data, transmitting the plurality of album data, and the plurality of album data based on the plurality of album data. The program according to any one of claims 1 to 20, wherein the printing of the album is at least one. An image processing device that generates multiple album data corresponding to multiple albums.
An acquisition method for acquiring multiple image data,
A first selection means for selecting at least one image data out of the plurality of image data as common image data corresponding to an image arranged on a common page which is a page common to all the plurality of albums.
A first generation means for generating common page data corresponding to the common page based on at least one image data selected as the common image data.
A second selection means for selecting at least one image data out of the plurality of image data as individual image data corresponding to an image arranged on an individual page which is a page not common to all the plurality of albums.
A second generation step of generating a plurality of individual page data corresponding to the individual page based on the at least one image data selected as the individual image data.
A third generation means for generating the plurality of album data based on the common page data and the plurality of individual page data is executed.
The individual page data corresponding to the first album data among the plurality of album data and the individual page data corresponding to the second album data among the plurality of album data are different.
The common page data corresponding to the first album data among the plurality of album data and the common page data corresponding to the second album data among the plurality of album data are the same.
An image processing apparatus characterized in that cover image data corresponding to an image arranged on the cover of an album is controlled so as to be selected as the individual image data. It is a control method of an image processing device that generates multiple album data corresponding to a plurality of albums.
The acquisition step to acquire multiple image data and
A first selection step of selecting at least one image data out of the plurality of image data as common image data corresponding to an image arranged on a common page which is a page common to all the plurality of albums.
A first generation step of generating common page data corresponding to the common page based on the at least one image data selected as the common image data, and
A second selection step of selecting at least one image data out of the plurality of image data as individual image data corresponding to an image arranged on an individual page which is a page not common to all the plurality of albums.
A second generation step of generating a plurality of individual page data corresponding to the individual page based on the at least one image data selected as the individual image data.
It has a third generation step of generating the plurality of album data based on the common page data and the plurality of individual page data.
The individual page data corresponding to the first album data among the plurality of album data and the individual page data corresponding to the second album data among the plurality of album data are different.
The common page data corresponding to the first album data among the plurality of album data and the common page data corresponding to the second album data among the plurality of album data are the same.
A control method characterized in that cover image data corresponding to an image arranged on the cover of an album is controlled so as to be selected as the individual image data.