JP2013046188A - Layout editing support device, layout editing support method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically generate layout candidates which can be desired by a user.SOLUTION: A content identification unit 304 identifies a data group to be a layout change object. A clustering condition determination unit 305 determines a condition for performing clustering processing on the basis of the data group identified by the content identification unit 304. A clustering unit 302 performs a clustering process on the data group according to the condition. A layout unit 303 performs a layout process on the data group on the basis of respective clusters generated by the clustering unit 302.

Description

  The present invention relates to a technique for editing a layout of a content data group.

  There are known services and applications for automatically laying out digital image data (hereinafter referred to as photos) to generate a photo print layout such as a photo album. The user can purchase a photo album using a print service or the like after selecting a favorite photo album generated by the service or the like and editing it as necessary. Note that the services and applications described above use a technique of automating a number of photos including the number of pages and the configuration in order to support a photo album composed of a plurality of pages (see Patent Document 1).

JP 2006-295887 A

  When a photo album is automatically generated using the above-described service or the like, it may be generated with a layout that the user does not want. If the generation result is different from what the user desires, the user changes the arrangement of the photos using an editing function provided by the application or the like. However, the editing work of a photo album composed of a plurality of photos and pages requires a very complicated operation.

  The present invention has been made in view of the above problems, and an object of the present invention is to automatically generate layout candidates that the user may desire by changing the photo page allocation processing based on a user instruction. .

  Accordingly, an object of the present invention is to automatically generate layout candidates that the user may desire.

  The layout editing support apparatus according to the present invention includes a specifying unit that specifies a data group that is a layout change target, a determination unit that determines a condition for clustering processing based on the data group specified by the specifying unit, Clustering means for performing clustering processing on the data group based on the condition determined by the determining means, and layout means for performing layout processing on the data group based on each cluster generated by the clustering means It is characterized by having.

  According to the present invention, it is possible to automatically generate layout candidates that the user may desire.

It is a figure for demonstrating the outline | summary of the layout edit assistance process in embodiment of this invention. It is a figure which shows the hardware constitutions of the layout edit assistance apparatus which concerns on embodiment of this invention. It is a figure which shows the functional structure of the layout editing assistance apparatus which concerns on embodiment of this invention. It is a flowchart which shows the flow of the photo album production | generation process in embodiment of this invention. 6 is a flowchart showing a flow of layout processing in step S4010 of FIG. It is a figure for demonstrating the page allocation process in step S5000 of FIG. It is a figure for demonstrating the template determination process in step S5010 of FIG. It is a figure for demonstrating the layout process in step S5020 of FIG. 6 is a flowchart showing the flow of editing processing in step S4020 of FIG. It is a figure for demonstrating an example of an edit instruction | indication. It is a figure for demonstrating an example of presentation of the layout process result in step S9060 and S9070, and layout selection operation. It is a figure for demonstrating an example of presentation of the layout process result in step S9060 and S9070, and layout selection operation. It is a flowchart which shows the flow of the content specific process in step S9010 of FIG. It is a figure which shows an example of the cluster tree of the photo album used as edit object. It is a flowchart which shows the flow of the clustering condition determination process in step S9020 of FIG. It is a figure which shows an example of the metadata which a photograph group hold | maintains. It is a flowchart which shows the flow of the clustering process in step S9030 of FIG. It is a flowchart which shows the flow of the correlation calculation process in step S17020 of FIG. It is a figure for demonstrating concretely about processing of Step S17020 and Step S17030.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments to which the invention is applied will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a diagram for explaining an outline of layout editing support processing in the embodiment of the present invention. In FIG. 1, reference numeral 101 denotes an example of a photo album automatically generated by an existing photo album creation application. In the layout editing support process according to the present embodiment, a photo album 102 that is an alternative candidate is generated from the photo album 101 based on a user instruction. Specifically, the user instructs a page whose layout is to be edited with respect to the photo album 101 generated by the existing photo album creation application. Reference numeral 103 denotes a page for which editing is instructed by the user. In the layout editing support process in the present embodiment, different layouts are automatically generated using the content data group group included in the page 103 and presented to the user. Reference numeral 104 denotes a page candidate automatically generated using the content data group included in the page 103. The generated page candidate is presented to the user. The user performs an editing operation by selecting a desired one from the presented page candidates. Hereinafter, the content data is referred to as a photograph.

  FIG. 2 is a diagram showing a hardware configuration of the layout editing support apparatus according to the embodiment of the present invention. In FIG. 2, 202 is a CPU (Central Processing Unit) that performs various processes, logical determinations, and the like, and controls various elements connected to the bus 201. The layout editing support apparatus according to the present embodiment includes a memory including a program memory and a data memory. The program memory stores a program for causing the CPU 202 to execute various processing procedures to be described later. The program memory may be a ROM (Read-Only Memory) 203 or a RAM (Random Access Memory) 204 into which a program is loaded from an external storage device or the like. Alternatively, it may be realized by a combination of these.

  Reference numeral 205 denotes a storage device such as a hard disk for storing data and programs according to the present embodiment. In the present embodiment, the storage device 205 is also used to hold a photograph or the like. Note that a recording device connected to an external connection or a network may be used as a device for holding a photograph. Further, the external storage device 206 may be used as the same role as the storage device 205. Here, the external storage device 206 can be realized by, for example, a medium (recording medium) and an external storage drive for realizing access to the medium. As the medium, for example, a flexible disk (FD), a CD-ROM, a DVD, a USB memory, an MO, a flash memory, or the like can be applied.

  Reference numeral 207 denotes an input device for inputting an instruction from the user. The user gives an instruction to the layout editing support apparatus according to the present embodiment via the input device 207. The input device 207 is configured by a keyboard or a pointing device, for example. Reference numeral 208 denotes an output device as display means for displaying processing results and the like. The output device 208 can be realized by a display device such as a CRT (Cathode-Ray Tube) or a liquid crystal display including a circuit for output. In the present embodiment, photographs, layout results, and the like are displayed on the output device (display device) 208. Reference numeral 209 denotes an interface (hereinafter referred to as I / F), which exchanges data with an external device via the I / F 209.

  FIG. 3 is a diagram showing a functional configuration of the layout editing support apparatus according to the present embodiment. Note that the input device 207 and the output device 208 in FIG. 3 have the same configuration as the input device 207 and the output device 208 in FIG.

  A clustering unit 302 performs clustering processing on a photo group input by a user or a photo group specified by a content specifying unit 304 described later. A layout unit 303 performs photo layout processing with each cluster generated by the clustering unit 302 as one page. As an example of this layout process, for example, a layout is made by arranging a photo on a template prepared in advance. A template used for layout processing is held in a template DB 306 described later.

  A content specifying unit 304 specifies a group of photos included in a page that the user desires to edit. Reference numeral 305 denotes a clustering condition determination unit that determines conditions used in the clustering process executed by the clustering unit 302. That is, the clustering unit 302 performs a clustering process based on the conditions determined by the clustering condition determining unit 305. A template DB 306 holds a re-template used in the layout unit 303.

  In the present embodiment, the content specifying unit 304 specifies a group of photos included in a page that the user desires to edit, and the clustering condition determining unit 305 determines a clustering process condition for the photo group. The clustering unit 302 performs clustering processing based on the determined conditions, and the layout unit 303 performs layout processing based on the clusters generated by the clustering processing. Through the above processing, in this embodiment, page candidates having a layout different from the original layout are generated. Each functional configuration described above is realized by the CPU 202 in FIG. 2 loading a program from the external recording device or the like into the RAM 204 and executing it.

  FIG. 4 is a flowchart showing a flow of photo album generation processing in the present embodiment. Hereinafter, the photo album generation process in the present embodiment will be described with reference to FIG.

  The user selects a photo group for which a photo album is to be created. In step S4000, the layout editing support apparatus selects a photo group according to a user's selection operation. In the photo group selection operation, an interface of a file management system provided by the OS or the like is used. The photo selection operation here is performed manually by the user, but the photo group may be selected by a different method. For example, the layout editing support apparatus may estimate a user's favorite browsing photograph as a user's favorite photograph and select the estimated favorite photograph group. In addition, the layout editing support apparatus may select a high-resolution photo group using the resolution held by the photo as metadata.

  In step S4010, the layout editing support apparatus generates a photo album layout using the photo group selected in step S4000, and presents the generated layout to the user. The user performs an editing operation on the layout generated in step S4010 as necessary. In this manner, the user creates a desired layout by performing an editing operation on the layout generated in step S4010. In step S4020, the layout editing support apparatus performs an editing process according to the user's editing operation on the layout generated in step S4010. In the present embodiment, the editing load on the user is reduced by presenting alternative page candidates in the editing operation.

  FIG. 5 is a flowchart showing the flow of layout processing in step S4010 of FIG. In step S5000, the layout unit 303 performs page assignment processing for the designated photo group. In the page allocation process, the number of pages in the photo album and which photo is allocated to each page are determined. Specifically, the clustering unit 302 performs clustering processing based on the shooting time held as metadata such as Exif in a photograph. Then, the layout unit 303 identifies a cluster to be used for layout from the generated cluster. Hereinafter, a cluster used for layout is referred to as a layout cluster. The layout unit 303 determines the specified number of layout clusters as the number of pages in the photo album, and performs page allocation processing by allocating a group of photos included in the layout cluster to each page. Details of the page allocation processing will be described later with reference to FIG. Here, the reference for the clustering process is the shooting time, but a different reference may be used. For example, if a photographing position that can be acquired by GPS or the like is given to a photograph as metadata, clustering processing may be performed based on the photographing position.

  In step S5010, the layout unit 303 determines a template to be used for each page based on the result of the page allocation process in step S5000. This template determination process is performed based on the number of photos assigned to each page. Details of the template determination process will be described later with reference to FIG.

  In step S5020, the layout unit 303 performs layout using the template determined in step S5010. Specifically, the layout unit 303 arranges the photos assigned in step S5000 on the template. Details of this layout processing will be described later with reference to FIG. Through the above processing, the layout editing support apparatus according to the present embodiment can automatically generate a photo album layout from a group of photos and present it to the user.

  Next, the page allocation processing in step S5000 in FIG. 5 will be described with reference to FIG. FIG. 6A shows an example of a photograph group selected by the user. ID 601 is identification information for uniquely identifying a photograph. The shooting time 602 is information indicating the shooting time of the photograph. In the page allocation process, the clustering process is performed based on the shooting time as described above. First, in the clustering process, the photographs are arranged in order of shooting time, and then the photographs are defined as clusters. And the clustering part 302 produces | generates a cluster tree as shown in FIG.6 (b) by integrating sequentially the cluster with the near imaging | photography time.

  Next, the layout unit 303 identifies a layout cluster based on the distance between each cluster included in the cluster tree. Specifically, the layout unit 303 calculates a distance between clusters having the same parent cluster with respect to all end clusters, and the distance is larger than a predetermined distance (hereinafter referred to as a distance specified value). If it is smaller, the parent cluster is set as a layout cluster candidate. On the other hand, when the calculated distance is equal to or greater than the distance specified value, the layout unit 303 identifies the cluster as a layout cluster. Next, when there is a cluster as a layout cluster candidate, the layout unit 303 calculates the distance between the clusters having the same parent cluster with respect to all the cluster as the layout cluster candidates. Specify the layout cluster. The layout unit 303 identifies a layout cluster by repeating such processing until there is no cluster that is a layout cluster candidate. FIG. 6C shows the specified layout cluster. That is, since the distance between cluster A (photo A) and cluster B (photo B) is smaller than the distance specified value, it is not specified as a layout cluster. Since the distance between the cluster AB (cluster A + cluster B) and the cluster CDE (cluster C + cluster D + cluster E) is equal to or greater than the distance specified value, it is specified as a layout cluster.

  The page allocation process is completed by setting each layout cluster thus identified as one page. Specifically, association is performed in which a group of photographs included in each layout cluster is arranged on one page. The result of this association is held in a page allocation table (not shown). In the example of FIG. 6C, since there are two layout clusters, the number of pages of the photo album is two. The page order is the same as the cluster order. That is, the page order is determined in the order of the layout cluster with the earlier shooting time to the layout cluster with the later shooting time. Here, Photo A and Photo B are associated with the first page, and Photo C, Photo D, and Photo E are associated with the second page.

  In the present embodiment, the distance regulation value is determined in advance, but the distance regulation value may be calculated. For example, a restriction may be provided on the number of pages in the photo album, and the distance regulation value may be determined according to the restriction on the number of pages. That is, the distance regulation value is calculated so that the number of layout clusters matches the page number constraint. The photo album creation service may be charged depending on the number of pages. Therefore, it is conceivable that the user determines the number of pages according to the budget and sets the number of pages as a page number constraint. By obtaining the distance specified value by the above-described method, it is possible to determine a layout cluster according to the page number constraint, and it is possible to generate a photo album having the number of pages specified by the user.

  Next, the template determination process in step S5010 of FIG. 5 will be described with reference to FIG. FIG. 7 is a diagram illustrating a template table that holds templates. The template table is stored in the template DB 306 in FIG. 3, and a usable template is managed for each number of photos. In the template table shown in FIG. 7, a template ID 702 for uniquely specifying a template is stored for each number of photos defined by the number of photos 701. For example, it can be seen that the template IDs of the layout templates that can be used when the number of photos in a certain layout cluster is two are T0003, T0004, and T0005. In the template determination process, the layout unit 303 determines a template by referring to the template table based on the number of photos assigned to each page. Information indicating the template allocated to the page is added to the page allocation table (not shown). When there are a plurality of usable templates, the templates are selected at random using an existing random value generation technique. However, the template selection process is not random, and a different method may be used. For example, a suitable photo condition may be assigned to the template, and the template may be selected based on the condition. Specifically, it is possible to define a template with the representative color of the photo as a condition, and specify the template using the representative color of the photo group. This method makes it possible to select an appropriate template according to the color of the photograph.

  Next, the layout process in step S5020 in FIG. 5 will be described with reference to FIG. FIG. 8 shows an example of a template. The template shown in FIG. 8 includes a page area 801 that shows the entire page and a slot 802 that is an area in which a photo is placed. In the layout process, a photograph is placed in a slot 802 in the template. In the photo placement process for the slot 802, the photos are randomly placed using an existing random value generation technique. Here, the photos are randomly arranged, but other methods may be used. For example, an arrangement order may be defined for the slot 802 and the slots may be arranged so that the arrangement order matches the order of shooting times. Further, instead of generating one pattern, it is possible to generate all possible combinations of arrangements and allow the user to select the layout result.

  FIG. 9 is a flowchart showing the flow of the editing process in step S4020 of FIG. Hereinafter, the flow of the editing process will be described in detail with reference to FIG. In step S9000, the layout editing support apparatus receives an instruction to be edited by the user. The editing target can be specified in units of pages, and the user selects a page whose layout is to be changed. When there are a plurality of pages to be changed, a plurality of pages can be selected. The layout of the photo album is displayed in a format similar to that of the existing layout application, and the user can specify a page to be edited for the display.

  Here, an example of an editing instruction will be described with reference to FIG. FIG. 10A shows a layout editing screen in the present embodiment. The layout editing screen includes a menu 1001, a layout display screen 1002, and a scroll bar 1003. The menu 1001 provides access means to functions provided by the application, such as a file for instructing to save the layout result. The layout display screen 1002 displays the layout of the photo album generated by the layout editing support apparatus according to this embodiment. When the number of pages is large and the layout does not fit on one screen, the page to be displayed can be controlled by the scroll bar 1003.

  The user designates a page to be changed from the layout displayed on the layout display screen 1002 using the mouse. As indicated by 1004 in FIG. 10B, the instructed layout is highlighted. When the mouse is right-clicked in a state where the instructed layout exists, an edit menu is displayed as shown at 1005 in FIG. 10C. The user instructs layout change by instructing automatic editing in the editing menu 1005.

  In step S9010, the content specifying unit 304 performs content specifying processing based on the user instruction in step S9000. The content identification process is a process for identifying a group of photographs whose layout is to be changed. Details of step S9010 will be described later with reference to FIG.

  In step S9020, the clustering condition determining unit 305 determines a clustering condition for the photograph group specified in step S9010. In the clustering condition determination process, metadata and a prescribed distance value are determined as clustering conditions used as a reference in the clustering process in step S9030 described later. Details of step S9020 will be described later with reference to FIG.

  In step S9030, the clustering unit 302 performs clustering processing on the photo group specified in step S9010 based on the clustering condition determined in step S9020. Step S9030 is processing similar to step S5000 in FIG. 5, and page allocation is determined for the photo group. Details of step S9030 will be described later with reference to FIG.

  In step S9040, the layout unit 303 determines a template based on the processing result in step S9030. Step S9040 is the same processing as step S5010 in FIG.

  In step S9050, the layout unit 303 performs layout based on the processing results in steps S9030 and S9040. Step S9050 is the same processing as step S5020 in FIG. 5, and the photo arrangement in the page is determined.

  In step S9060, the layout unit 303 presents the layout processing result in step S9050 to the user. When a plurality of layouts are generated as the layout processing result in step S9050, the plurality of layout processing results are presented as a list. The order of presentation may be arranged randomly using an existing random value generation technique, or may be arranged in the processing order in step S9050. It is also possible to calculate a layout score using an existing technique for evaluating layout quality, and to arrange the score in the calculated score order. As a layout quality evaluation technique, a technique for quantitatively evaluating quality based on a margin amount or the like is known.

  In step S9070, the layout unit 303 accepts a user selection operation for the layout processing result presented in step S9060. The layout unit 303 presents a layout processing result of a new photo album to which the layout selected by the user is applied.

  An example of layout processing result presentation and layout selection operations in steps S9060 and S9070 will be described with reference to FIGS. FIG. 11A shows a display screen of the layout processing result. As shown in FIG. 11A, the layout processing result display screen includes a candidate display area 1101 in which a plurality of generated layout candidates are displayed. In the candidate display area 1101, the generated layout candidates are displayed in a list format in the candidate list 1102. The user selects a desired layout candidate from the candidate list 1102. As shown in FIG. 11B, the selected layout candidate 1103 is highlighted. A determination menu 1104 is displayed by right-clicking the mouse in a state where the selected layout candidate 1103 exists. When the user instructs the decision menu 1104, a new photo album layout using the selected layout candidate is displayed as shown in FIG.

  The user can perform the editing operation with a simple operation by causing the layout editing support apparatus to execute the editing process described above as necessary.

  As described above, the number of photos assigned to a page is changed by newly generating a clustering condition. Changing the number of photos also changes the template used, resulting in a different layout. The generated layout is given meaning by the clustering condition, and unlike the randomly arranged layout, a layout that is easy to understand for humans is realized.

  FIG. 13 is a flowchart showing the flow of content specifying processing in step S9010 of FIG. In step S13000, the content specifying unit 304 specifies a layout cluster associated with the page selected by the user. The layout cluster specifying process is performed using the above-described page allocation table (not shown).

  In step S13010, the content specifying unit 304 specifies a cluster that includes all the layout clusters specified in step S13000. In this process, the content specifying unit 304 sequentially searches for a parent cluster of each layout cluster, and specifies a cluster including all layout clusters.

  Here, step S13010 will be specifically described with reference to FIG. FIG. 14 shows an example of a cluster tree of photo albums to be edited. When the layout clusters associated with the page designated by the user are the clusters 1401 and 1402, the cluster including these layout clusters is identified as the cluster 1403. This makes it possible to change the layout for a plurality of pages at once. Here, the method of collectively performing layout for a plurality of pages by specifying a cluster including all layout clusters instructed by the user has been described. However, a different method may be used. That is, the layout change process may be performed for each layout cluster instructed by the user.

  In step S13020, the content specifying unit 304 specifies a group of photos that are subject to layout change based on the cluster specified in step S13010. Specifically, the content specifying unit 304 determines all photos included in the cluster specified in step S13010 as layout targets.

  FIG. 15 is a flowchart showing the flow of the clustering condition determination process in step S9020 of FIG. In step S15000, the clustering condition determining unit 305 specifies metadata common to the photo group specified in step S9010 of FIG. FIG. 16 is a diagram illustrating an example of metadata held by a photograph group. As shown in FIG. 16, each photo holds metadata. In step S15000, the clustering condition determination unit 305 identifies metadata common to all the photos by referring to the metadata of each photo. In the example illustrated in FIG. 16, the shooting time, the shooting location, and the favorite degree are specified as common metadata.

  In step S15010, the clustering condition determination unit 305 acquires the clustering condition when the instructed layout is generated. The clustering conditions are metadata and distance specification values used in the clustering process as described above. For example, all layouts that are generated first are subjected to clustering processing based on the shooting time, and the prescribed distance value is prescribed in advance. Accordingly, in the case of the layout generated first, the clustering condition acquired in step S15010 is the shooting time and the distance specified value specified in advance. On the other hand, when the layout change is performed once or more by the user, the clustering process is performed with different metadata and distance specification values. Therefore, metadata and distance specification values different from the shooting time are acquired. Each clustering condition is stored in a clustering condition table (not shown) for each clustering process. In step S15010, the clustering condition is acquired by referring to the clustering condition table.

  In step S15020, the clustering condition determination unit 305 generates a new clustering condition based on the information acquired in steps S15000 and S15010. Specifically, the clustering condition determination unit 305 generates a new clustering condition for each piece of metadata specified in step S15000.

  First, the clustering condition determining unit 305 determines whether the metadata is the same as that used in the clustering condition acquired in step S15010. The determination process is realized by matching a word with a metadata name as a word. The matching process may be a complete match, or may be determined to be a match if it is a similar word using a dictionary or the like.

  As a result of the determination, if the metadata is the same as that used in the clustering condition acquired in step S15010, the clustering condition determining unit 305 changes the distance specified value of the clustering condition acquired in step S15010 to Clustering conditions are generated. For example, when the original clustering condition is metadata: photographing time, distance specified value: 1 hour, the new clustering condition is that the distance specified value is changed, although the metadata is not changed. The method for changing the distance specified value may be changed at a rate specified in advance or may be changed randomly. In the example described above, as an example of a new clustering condition, metadata: photographing time, distance specified value: 5 minutes, etc. can be considered. This makes it possible to perform page allocation with a granularity different from that of the original layout. For example, consider the case of creating a travel record photo album. In the initial layout, page allocation was performed with 1 hour as a guide, but it becomes possible to partially perform page split with 5 minutes as a guide. In the case of sightseeing in a city with many famous places, it may be possible to take a number of photographs in a short time. In the original layout, many photos are placed on one page, so it is not possible to effectively arrange shooting records at famous places, but by changing the clustering conditions, the number of placements per page can be changed easily. It becomes possible to do.

  On the other hand, as a result of the determination, if the metadata is different from that used in the clustering condition acquired in step S15010, the clustering condition determining unit 305 updates the metadata and the distance specification value as a new clustering condition. . For example, when the metadata under the original clustering condition is the favorite level and the metadata to be determined at the shooting time is the favorite level, the metadata under the new clustering condition is set as the favorite level. The distance setting value setting process may be set at random in the same manner as described above, or a distance setting value for each metadata specified in advance may be used.

  FIG. 17 is a flowchart showing the flow of clustering processing in step S9030 of FIG. In step S17000, the clustering unit 302 acquires a clustering condition. The clustering condition acquisition process is realized by acquiring the clustering condition determined in step S9020 in FIG. When there are a plurality of clustering conditions, the following steps S17010 to S17030 are performed for each clustering condition.

  In step S17010, the clustering unit 302 performs clustering processing based on the clustering condition acquired in step S17000. The clustering process is the same process as step S5000 in FIG. That is, the clustering unit 302 performs a clustering process based on metadata defined in the clustering condition, and generates a cluster tree. Then, the clustering unit 302 performs layout cluster specifying processing on the generated cluster tree based on the distance specified value specified by the clustering condition.

  In step S17020, the clustering unit 302 calculates the degree of correlation between the layout cluster generated in step S17010 and the cluster related to the layout cluster. The correlation degree calculation process will be described later with reference to FIG. In step S17030, the clustering unit 302 changes the order of the layout clusters based on the correlation calculated in step S17020, and updates the cluster tree.

  Here, the processing of step S17020 and step S17030 will be specifically described. FIG. 19A shows a cluster tree showing the entire photo album, and a cluster for which a change instruction is given by the user is cluster B. FIG. FIG. 19B shows the result of clustering processing performed on cluster B based on the new clustering conditions, and cluster X and cluster Y are generated as new clusters. The clustering unit 302 calculates the degree of correlation with the cluster A for each of the cluster X and the cluster Y when the immediately preceding cluster A is specified as the related cluster of the cluster B for which the change instruction has been issued. FIG. 19C illustrates a cluster tree that is finally generated when the degree of correlation with the cluster A is higher in the cluster X. On the other hand, FIG. 19D shows a cluster tree generated when the degree of correlation with cluster A is higher in cluster Y. A cluster having a high degree of correlation with cluster A is determined to be close to cluster A.

  Through the above processing, different page allocations for a part of the original layout are realized under new clustering conditions. Since the clustering condition is partially changed by the processing, the generated layout may give a strange feeling to humans. For example, in the entire photo album, the page is configured based on the shooting time, but the page may be configured partially based on the shooting location. In order to solve such a problem, in the present embodiment, new page allocation is realized by the processing in steps S17020 and S17030 so that the correlation with the original layout is close. That is, it is possible to reduce the possibility that a newly generated partial layout will give a person a sense of incongruity.

  FIG. 18 is a flowchart showing the flow of correlation degree calculation processing in step S17020 of FIG. In step S18000, the clustering unit 302 identifies the related cluster of the cluster designated as the layout change target. In the related cluster specifying process, a cluster to be laid out and a cluster before and after the layout change target are specified. In step S18010, the clustering unit 302 determines metadata serving as a reference for calculating the degree of correlation. In the reference metadata acquisition process, common metadata is extracted between the photo included in the cluster specified in step S18000 and the photo included in the cluster generated in step S17010 in FIG. For example, when the metadata given to the photos included in the related cluster is the shooting time and the favorite degree, and the metadata included in the cluster generated in step S17010 in FIG. 17 is the shooting time and the shooting position. The shooting time is extracted as reference metadata. In this example, a single piece of metadata is extracted, but when there are a plurality of common metadata, a plurality of pieces of metadata are extracted. Here, the extraction of the common metadata is used as the reference metadata determination method, but a different method can be used. For example, the metadata used when the cluster specified in step S18000 is generated may be used. That is, when the original photo album is clustered by shooting time, the shooting time may be used as the reference metadata.

  In step S18020, the clustering unit 302 calculates the degree of correlation between the related cluster and the cluster generated in step S17010 in FIG. 17 based on the reference metadata determined in step S18010. The correlation degree calculation is realized by calculating the distance between the clusters based on the metadata. The distance between clusters is calculated using existing technology. For example, a method is known in which the distance between clusters is calculated using an average value of metadata held by photographs in the cluster.

  In the present embodiment, the method of using the reference for obtaining the degree of correlation as metadata has been described, but a different method may be used. For example, it is possible to focus on the hue (hue / saturation / lightness) of a photograph and use the compatibility of the hue as a correlation. Color compatibility is generally known as knowledge of layout design, and can be realized by using this knowledge. Specifically, similar colors (those with the same hue but different saturation / lightness), similar colors (those with similar hues and similar hues), and complementary colors (those with symmetrical hues) are compatible. It is known as an example of good color. Therefore, the compatibility can be determined by using the distances of hue, saturation, and brightness.

  Further, as a method of calculating the degree of correlation, a method of paying attention to the page configuration when obtaining the degree of correlation can be considered. In the case of a photo album, there is a high possibility that a strong correlation is required for a combination that becomes a spread page, but when page turning occurs, there is a possibility that humans will not feel uncomfortable even if the correlation degree of consecutive pages is low. For example, this can be realized by a method of multiplying the correlation degree by a coefficient in accordance with whether the page is spread or turning, and determining the correlation degree considering the page configuration.

  In this embodiment, by changing the clustering condition based on the metadata of the photo group specified by the user and performing layout processing according to the change result, layout candidates that the user may desire are automatically selected. Can be generated.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

  302: Clustering unit, 303: Layout unit, 304: Content specifying unit, 305: Clustering condition determining unit, 306: Template DB

Claims (6)

A specifying means for specifying a data group to be changed in layout,
Determining means for determining a condition for clustering processing based on the data group specified by the specifying means;
Clustering means for performing a clustering process on the data group based on the condition determined by the determining means;
A layout editing support apparatus, comprising: layout means for performing layout processing on the data group based on each cluster generated by the clustering means.   The layout editing support apparatus according to claim 1, wherein the determination unit determines the condition based on metadata of the data group.   The layout means determines the order of the clusters based on the degree of correlation between the generated clusters and the clusters related to the data group to be changed in layout, and the layout means The layout editing support apparatus according to claim 1, wherein a layout process is performed on the data group based on the determined order of the clusters.   4. The layout unit according to claim 1, wherein the layout unit performs layout processing on the data group by allocating data included in each cluster generated by the clustering unit for each page. The layout editing support apparatus according to 1. A layout editing support method executed by a layout editing support device,
A specific step of identifying a data group to be changed in layout,
A determination step of determining a condition for clustering processing based on the data group specified by the specifying step;
A clustering step of performing a clustering process on the data group based on the condition determined in the determination step;
A layout editing support method comprising: a layout step for performing layout processing on the data group based on each cluster generated by the clustering step. A specific step of identifying a data group to be changed in layout;
A determination step of determining a condition for clustering processing based on the data group specified by the specifying step;
A clustering step of performing a clustering process on the data group based on the condition determined in the determination step;
A program for causing a computer to execute a layout step for performing a layout process on the data group based on each cluster generated by the clustering step.

Images