JP2019053362A - Electronic comic book digest generation device and method - Google Patents

Abstract

To create the digest of an electronic comic book.SOLUTION: A page image extraction unit 110 reads electronic book contents from a storage device 160 to extract page images constituting respective pages in sequence, and supplies the page images to a character unit corresponding area detection unit 120. The character unit corresponding area detection unit 120 acquires the page image from the storage device 160, and captures and detects a character unit corresponding area for each page. A counting unit 130 counts the number of times of detection of the character unit corresponding area for each page. A page selection unit 140 receives the number of times of detection of the character unit corresponding area of each page from the counting unit 130, and selects a prescribed number of pages on the basis of these values. An animation file generation unit 150 generates an animation file from the page selected by the page selection unit 140.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for generating a digest of an electronic comic book.

  Comic books (manga books) electronic books are widely distributed. Readers often use the digest animation when selecting a comic book to subscribe to. In the digest animation, a plurality of main pages of a comic book are selected in advance and displayed as an animation. At this time, since the quality of the digest animation depends on which page is used for animation, an animation producer actually browses and selects an electronic book. Such a selection operation is complicated, and it is very convenient if a page to be used for animation can be automatically selected.

  Patent Document 1 discloses that a still image of each scene selected from a moving image is distributed to each of a plurality of frames constituting one page and a moving image is displayed as a digest.

  The above-described prior art and its problems are described only to explain a part of the background of the present invention. It should be noted that the present invention is not limited to the above-described prior art and problems.

JP 2009-066542 A

  The present invention has been made in consideration of the above circumstances, and an object thereof is to provide a technique for easily generating a digest animation of a comic book electronic book.

  According to this invention, in order to achieve the above-mentioned object, the configuration as described in the claims is adopted. Here, prior to describing the invention in detail, supplementary explanations of the claims will be given.

  That is, according to one aspect of the present invention, in order to achieve the above-described object, the electronic comic book digest generation device detects: a character unit corresponding region included in the page for each of predetermined pages of the electronic comic book A character unit corresponding region detection unit that counts the character unit corresponding region detected by the character unit corresponding region detection unit; a page with a smaller count value by the counting unit has a higher priority when selecting. A page selection unit that selects a predetermined number of pages; and an animation file generation unit that generates an animation file for animation display including the predetermined number of pages selected by the page selection unit. .

  The character unit corresponding area is an area that individually encloses character units (kanji, kana, alphabet, symbols, etc.) included in a balloon or background. Symbols such as punctuation marks may be excluded from the character unit. The animation display may display pages according to the page order, but is not limited to this.

  In this configuration, an animation file can be generated by easily determining a page to be used for digest animation display based on the number of characters included in the page.

  An electronic book comic may be created in various electronic publication formats, such as EPUB, but is not limited thereto. The animation file may also be created in various formats, typically an animation GIF, but is not limited to this.

  In this configuration, the character unit corresponding region detection unit may include a character recognition unit. Character recognition can reliably detect the character unit corresponding area. However, only the character unit corresponding area may be cut out.

  In this configuration, the page selection unit may preferentially select the cover page.

  Also, in this configuration, the animation file generation unit synthesizes a transition page representing transition between pages from the page selected by the page selection unit, and includes the page selected by the page selection unit and the transition page An animated display may be generated. The transition page may be a page in which the preceding page and the succeeding page are arranged side by side and is slid by, for example, half a page. Alternatively, the succeeding page is covered so as to cover the preceding page, for example, half a page. The direction of sliding or covering may depend on the binding direction of the book. For example, in the case of right binding (transition from the right page to the left page), it may be slid from left to right.

  In this configuration, pages that are not suitable for digest may be determined and excluded from the predetermined pages. For example, a page that is not suitable for the digest may be determined by the area occupied by a single color in the page.

  In this configuration, the display time attribute of each of the selected predetermined number of pages may be determined based on the number of characters included in each.

  Further, in this configuration, the display time attribute of each of the selected predetermined number of pages is determined based on the time when the reader displayed each page.

  In this configuration, the display time attribute of each of the selected predetermined number of pages is determined based on the total number of bookmarks to which the reader is attached.

  According to another aspect of the present invention, in order to achieve the above object, an electronic comic book digest generating device detects: a frame corresponding area included in a predetermined page of an electronic comic book A frame corresponding area detection unit that counts the frame corresponding area detected by the frame corresponding area detection unit; a page with a smaller count value by the counting unit is set to a higher priority when selecting A page selection unit that selects a number of pages; and an animation file generation unit that generates an animation file for animation display including the predetermined number of pages selected by the page selection unit.

  In this configuration, the frame corresponding area is typically a polygon such as a quadrangle, and may be detected by image binarization processing, straight line detection, intersection detection, intersection count, and the like. Detection is possible.

  In this configuration, an animation file can be generated by easily determining the page used for the animation display for the digest based on the number of frames included in the page.

  The present invention can be realized not only as an apparatus or a system but also as a method. Of course, a part of the invention can be configured as software. Of course, software products used to cause a computer to execute such software are also included in the technical scope of the present invention.

  These and other aspects of the invention are set forth in the appended claims and will be described in detail below with reference to examples.

It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 1 of this invention. It is a block diagram which shows the structural example of the character unit corresponding | compatible area | region detection part of the electronic comic book digest production | generation apparatus of FIG. 1 is a diagram illustrating a system configuration example that implements Embodiment 1. FIG. 3 is a flowchart illustrating an example of a processing flow according to the first embodiment. FIG. 3 is a diagram illustrating a format example of an electronic book used in Embodiment 1. 6 is a diagram illustrating a list of examples of pages used in Embodiment 1. FIG. FIG. 6 is a diagram for explaining an operation example of the first embodiment. It is a figure which shows the example of a format of the animation file produced | generated in Example 1. FIG. It is a figure explaining the cover image and page transition image which are used for the animation file of Example 1. FIG. It is a figure explaining a page transition image. It is a figure explaining the example which changes the kind of page transition image. It is a figure explaining extraction of a cover image and the image of the beginning of a chapter. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 2 of this invention. FIG. 10 is a diagram for explaining an operation example of the second embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 3 of this invention. 10 is a diagram for explaining an operation example of Embodiment 3. FIG. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 4 of this invention. FIG. 10 is a diagram for explaining an operation example of the fourth embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 5 of this invention. It is a figure explaining the structural example of the frame detection part of the electronic comic book digest production | generation apparatus of Example 5. FIG. FIG. 10 is a diagram for explaining an operation example of the fifth embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 6 of this invention. FIG. 10 is a diagram for explaining an operation example of the sixth embodiment. FIG. 12 is a diagram for explaining another operation example of the sixth embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 7 of this invention. FIG. 10 is a diagram for explaining an operation example of the seventh embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 8 of this invention. FIG. 10 is a diagram for explaining an operation example of the eighth embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 9 of this invention. FIG. 20 is a diagram for explaining an operation example of the ninth embodiment. It is a block diagram which shows the structural example of the electronic comic book digest production | generation apparatus of Example 10 of this invention. FIG. 20 is a diagram for explaining an operation example of the ninth embodiment.

Examples of the present invention will be described below.
[Example 1]
FIG. 1 shows an electronic comic book digest generation apparatus 100 according to a first embodiment of the present invention. In this figure, the electronic comic book digest generation apparatus 100 includes a page image extraction unit 110, a character unit corresponding area detection unit 120, a count. Unit 130, page selection unit 140, animation file generation unit 150, and storage device 160.

  The electronic comic book digest generation apparatus 100 of FIG. 1 is realized by installing an application 300 and a tool in a computer system 200 as shown in FIG. The computer system 200 is configured by connecting a CPU 210 and a main memory 220 to a bus 230, and an external storage device 240 and various input / output devices 250 are connected to the computer system 200 via an interface 230.

  The storage device 160 stores an electronic book that is a digest creation target and an animation file that constitutes the generated digest. The electronic book is, for example, an EPUB (open format electronic book file format standard established by the International Electronic Publishing Forum IDPF) shown in FIG. 5, but is not limited thereto. A digest animation file of an electronic book is, for example, a GIF (Graphic Interchange Format) animation, and its format example is as shown in FIG. 8, but is not limited thereto. In FIG. 8, a plurality of image blocks (“Image”) are connected, and this is a compressed image of individual images constituting an animation, but is not limited to this.

  The page image extraction unit 110 reads out the electronic book content from the storage device 160, sequentially extracts the page images constituting each page, and supplies them to the character unit corresponding region detection unit 120. The character unit corresponding area detection unit 120 cuts out and detects an area (character unit corresponding area) surrounding individual character units including symbols such as kanji, kana, alphabets, and punctuation marks. For example, as shown in FIG. 2, the character unit corresponding region detection unit 120 may include a cutout unit 121, a feature amount extraction unit 122, and an identification unit 123. In the example of FIG. , The feature amount extraction unit 122 extracts the feature amount of the extracted region, and the identification unit 123 performs character recognition based on the feature amount. When the character recognition is completed successfully, the counting unit 130 counts this as one character unit corresponding area. The counting unit 130 counts the number of detections of the character unit corresponding area for each page. The page selection unit 140 receives the number of detections of the character unit corresponding area of each page from the counting unit 130, and selects a predetermined number of pages based on this. In this example, the smaller the number of detections (characters) of the character unit corresponding area, the higher the priority is selected. The character unit corresponding area detection unit 120 performs character recognition to verify the character unit corresponding area, but may simply cut out the character unit corresponding area. In the clipping, an area may be determined from a histogram or the like of the image.

  The animation file generation unit 150 generates an animation file from the page selected by the page selection unit 140. In this example, N pages (for example, 4 pages) with a small number of characters (number of character unit corresponding areas), cover pages are selected, these are arranged in page order, and transition is made from the image of the preceding page and the image of the subsequent page. Synthesize images and generate animation files from them. The transition image is an image that displays the transition from the preceding page to the subsequent page, and will be described in detail later.

  Next, the operation of the first embodiment will be described. FIG. 4 illustrates the operation of the first embodiment. First, the page image extraction unit 110 extracts one page image from the storage device 160 (step S01). Next, the character unit corresponding region detection unit 120 detects the character unit corresponding region in the page, further performs character recognition, verifies the character unit corresponding region (step S02), and the counting unit 130 determines the number of character unit corresponding regions. Is added to the number of characters table (storage device 160, FIG. 7) (step S03). Steps S01 to S03 are repeated for all pages (S04). When the processing of steps S01 to S03 is completed for all pages, page selection unit 140 refers to the character count table and selects the cover page and the top N page images (step S05). When the cover page is included in the top N pages, the top N + 1 page images are also selected. Next, the animation file generation unit 150 combines the page transition images and generates a GIF animation file (steps S06 and S07). The GIF animation file is stored in the storage device 160.

  FIG. 7 schematically illustrates an operation example of the first embodiment. In this example, the EPUB file of FIG. 5 is used, and the book composition page (cover, page 1 to page 11) shown in FIG. 6 is used. As shown in FIG. 7, the characters included in the balloon or background are counted, and the pages are selected in the order from the smallest number of characters in addition to the cover page. Further, in addition to the cover image, a transition image (slide, slide-in) shown in FIG. 9 is synthesized. The transition page may be a page in which the preceding page and the following page are arranged side by side and slid by, for example, half a page (slide in FIG. 9). Alternatively, the preceding page is, for example, half a page. A subsequent page may be arranged so as to cover (slide-in in FIG. 9). In any case, the direction of the slide (the direction of covering) may depend on the binding direction of the book. For example, as shown in FIG. 10, in the case of right binding (transition from the right page to the left page), it may be slid from left to right. In the case of left binding (transition from the left page to the right page), it may be slid from right to left. The binding direction of the book is the content. Information on the binding direction (“page-progression-direction”) in the of-file is used. The example of FIG. 10 uses an image in which the binding direction is right binding, the page transitions from right to left, and the subsequent left page slides (or slides in) to the preceding right page as the transition page. .

  The number of transition pages between the original pages is not limited as long as it is 2 or more, and is 2 in the example of FIG.

  In the example of FIG. 7, page 11, cover, page 2, page 1, and page 10 are selected, and these are taken out in page order. That is, the cover page, page 1, page 2, page 10, and page 11 are taken out, transition pages between the previous and next pages are synthesized from the previous and next pages, and each of these pages is compressed to generate an image block. Then, the GIF animation file shown in FIG. 8 is generated. The generated GIF animation file is stored in the storage device 160.

  When the transition page is generated, the composite type can be selected as a slide type or a slide-in type. For example, as shown in the upper right part of FIG. As shown in the lower right part of FIG. 11, the slide-in may be carried out when discontinuous as shown in the lower right part of FIG. 11, but is not limited to this. It is also possible to obtain the number of consecutive pages before and after the original page constituting the animation, and determine slide-in or slide from this number.

  Note that the first page (including the cover) of the chapter may be selected regardless of the number of characters included in the page. FIG. 12 shows this example. In this example, the path of the first page of the chapter is acquired from the index information (“navigation.html”) of the EPUB file, and these images are extracted to generate a GIF animation file.

[Example 2]
Next, a second embodiment of the present invention will be described. FIG. 13 shows the configuration of the second embodiment. In FIG. 13, portions corresponding to those in FIG. In FIG. 13, a single color dominant page detection unit 115 is provided so that the page selection unit 140 is prohibited from selecting a page in which a single color is dominant. In books, a single color page is often added for page alignment. Since such a page has a small number of characters, when a digest page is selected based on the number of characters, noise is generated, which can be avoided.

  FIG. 14 shows an operation example of the second embodiment. The page image is divided into squares, and the number of squares filled with a specific color is counted to determine whether the specific color is dominant when a predetermined threshold is exceeded. To do. In this example, the threshold is ½ of the total number of cells. It is not limited to this.

[Example 3]
Next, a second embodiment of the present invention will be described. FIG. 15 shows the configuration of the third embodiment. In FIG. 15, portions corresponding to those in FIG. In FIG. 15, a color page determination unit 116 is provided to preferentially select a color page.

  FIG. 16 shows an operation example of the third embodiment. In this example, color information is used to preferentially select pages. This is because color images are more appealing than monochrome images. This is especially useful when the number of pages used in the digest is large.

[Example 4]
Next, a fourth embodiment of the present invention will be described. FIG. 17 shows the configuration of the fourth embodiment. In FIG. 17, parts corresponding to those in FIG. In FIG. 17, a display time determination unit 117 is provided to determine the display time of each page of the animation according to the number of character unit corresponding regions (number of characters).

  FIG. 18 shows an operation example of the fourth embodiment. In this example, the display time is 2 seconds for pages with less than 200 characters, and the display time is 5 seconds for pages with more than 200 characters. In this example, the transition page is not particularly mentioned, but the time during which the transition page is displayed may be fixed, or may be variable according to the number of characters on the front and back pages.

[Example 5]
Next, a fifth embodiment of the present invention will be described. FIG. 19 shows the configuration of the fifth embodiment. 19, portions corresponding to those in FIG. 1 are denoted by corresponding reference numerals, and description thereof is omitted. In FIG. 19, a frame number counting unit 170 detects and counts the number of frames included in a page (regions divided by frame lines in the page and in which pictures are drawn). The page selection unit 140 selects a page with a higher priority order as the number of frames is smaller. At the same time, the cover page, the first page of the chapter, and the color page may be prioritized (Examples 1 and 3), and the selection of a page with priority on a single color may be prohibited (Example 2). The display time may be determined according to the number of frames.

  As shown in FIG. 20, the frame number counting unit 170 may include, for example, a binarization processing unit 171, a quadrangle detection unit 172, and a counting unit 173. The binarization processing unit 171 binarizes the page image, If necessary, the line is thinned, and the quadrangle detection unit 172 performs straight line detection and intersection detection, and detects an object including four intersections as a rectangle (not limited to a square or a rectangle but may be a trapezoid). It is not limited. It may be detected including polygons such as triangles and pentagons.

  FIG. 21 shows an operation example of the fifth embodiment. In this example, pages are selected in ascending order of the number of frames. Also in this example, it is preferable to prohibit selection of a page (page 11) for page alignment or the like where a single color is dominant.

[Example 6]
Next, a sixth embodiment of the present invention will be described. FIG. 22 shows a configuration of the sixth embodiment. In FIG. 22, portions corresponding to those in FIG. In FIG. 22, the fixed page selection unit 145 fixes and selects a range of pages. The pages in the fixed range may be the first N pages including the cover, or may be a predetermined number of pages continuously from a predetermined page. The image of the page in the predetermined range is contents. The path can be acquired and extracted from the page ID of op.

  FIG. 23 shows an example of extracting pages (cover, page 1 to page 4) included in a predetermined range from the top including the cover, and FIG. 24 is an example of extracting a predetermined number of pages (page 5 to page 8) from the predetermined page. Indicates.

[Example 7]
Next, a seventh embodiment of the present invention will be described. FIG. 25 shows the configuration of the seventh embodiment. In FIG. 25, parts corresponding to those in FIG. In FIG. 25, a designated page selection unit 146 includes metadata for designating an image used for a digest in the book content so that the digest can be designated on the book content side.

  FIG. 26 shows an operation example of the seventh embodiment. In this example, the contents. The extension data (ext: digest = “yes”) is embedded in the opf file. The page including the extension data is designated as an image constituting an animation, and the path image is acquired to extract the page image. In the example of FIG. 26, the cover, page 1, page 3, and page 6 are taken out.

[Example 8]
Next, an eighth embodiment of the present invention will be described. FIG. 27 shows the configuration of the eighth embodiment. In FIG. 27, parts corresponding to those in FIG. In FIG. 27, the electronic comic book digest generation apparatus 100 (computer system 200) can access the user information management server 400 via a communication network. A user terminal 500 is also connected to the communication network 300. The user terminal 500 browses book contents, and the user information management server 400 manages a reading information database of the user of the user terminal 500.

  The electronic comic book digest generation apparatus 100 accesses the reading information database 401 from the user information management server 400 (this may be stored in the storage device 160 as appropriate), or the display time determination unit 117 displays the average display time of the reader. To determine the display time.

  FIG. 28 shows an operation example of the eighth embodiment, in which an average display time per user is obtained for each page from the reading information database 401, and when this display time is less than 5 seconds, the display time is set to 2 seconds. If this is 5 seconds or longer, the display time is 5 seconds. Of course, various changes are possible.

[Example 9]
Next, a ninth embodiment of the present invention will be described. FIG. 29 shows the configuration of the ninth embodiment. In FIG. 29, portions corresponding to those in FIG. 1 or FIG. In FIG. 29, the average display time acquisition unit 118 acquires the average display time of the reader from the user information management server 400, and the page selection unit 140 preferentially selects a page having a long average display time.

  FIG. 30 shows an operation example of the ninth embodiment, in which an average display time per user is calculated for each page from the reading information database 401, and a page with a long average display time is preferentially selected. In this example, cover page, page 1, page 3, page 4, and page 6 are selected. Of course, various changes are possible.

[Example 10]
Next, a tenth embodiment of the present invention will be described. FIG. 31 shows the configuration of the tenth embodiment. In FIG. 31, portions corresponding to those in FIG. 1 or FIG. In FIG. 31, a bookmark number accumulating unit 119 accumulates the number of bookmarks added by the user for each page from the user information management server 400 and preferentially selects a page with a large number of bookmarks.

  FIG. 32 shows an operation example of the tenth embodiment, in which user bookmark additional data is obtained from the reading information database 401, a bookmark added cumulative value for each page is obtained, and a page with a large cumulative value is selected. In this example, cover page, page 1, page 3, page 4, and page 6 are selected. Of course, various changes are possible.

  This is the end of the description of the embodiment. In addition, this invention is not limited to the above-mentioned Example, A various change is possible.

DESCRIPTION OF SYMBOLS 100 Electronic comic book digest production | generation apparatus 110 Page image extraction part 115 Single color dominant page detection part 116 Color page determination part 117 Display time determination part 118 Average display time acquisition part 119 Bookmark number accumulation part 120 Character unit corresponding | compatible area detection part 121 Cutout part 122 feature amount extraction unit 123 identification unit 130 counting unit 140 page selection unit 145 fixed page selection unit 146 designated page selection unit 150 animation file generation unit 160 storage device 170 frame number counting unit 171 binarization processing unit 172 quadrangle detection unit 173 counting Part

Claims (12)

A character unit corresponding region detection unit that detects a character unit corresponding region included in the predetermined page of each electronic comic book;
A counting unit that counts the character unit corresponding region detected by the character unit corresponding region detection unit;
A page selection unit that selects a predetermined number of pages with a higher priority when selecting a page with a smaller count value by the counting unit;
An electronic comic book digest generation device, comprising: an animation file generation unit that generates an animation file for animation display including the predetermined number of pages selected by the page selection unit.   The electronic comic book digest generation device according to claim 1, wherein the character unit corresponding region detection unit includes a character recognition unit.   The electronic comic book digest generation apparatus according to claim 1, wherein the page selection unit preferentially selects a cover page.   The animation file generation unit synthesizes a transition page representing transition between pages from the page selected by the page selection unit, and generates an animation display including the page selected by the page selection unit and the transition page. The electronic comic book digest production | generation apparatus in any one of claim | item 1-3.   The electronic comic book digest production | generation apparatus in any one of Claims 1-4 which discriminate | determine the page which is not suitable for a digest and excludes it from the said predetermined page.   6. The electronic comic book digest generation device according to 5, wherein the page not suitable for the digest is determined by an area occupied by a single color in the page.   The electronic comic book digest production | generation apparatus in any one of Claims 1-6 which determines the display time attribute of each of the said selected predetermined number of pages based on the number of characters contained in each.   The electronic comic book digest production | generation apparatus in any one of Claims 1-6 which determines the display time attribute of each of the said selected predetermined number of pages based on the time when the reader displayed each.   The electronic comic book digest production | generation apparatus in any one of Claims 1-6 which determines the display time attribute of each of the said predetermined number of selected pages based on the total number of the bookmark which each attached. A frame corresponding area detection unit for detecting a frame corresponding area included in the predetermined page of each electronic comic book;
A counting unit for counting the frame corresponding areas detected by the frame corresponding area detecting unit;
A page selection unit that selects a predetermined number of pages with a higher priority when selecting a page with a smaller count value by the counting unit;
An electronic comic book digest generation device, comprising: an animation file generation unit that generates an animation file for animation display including the predetermined number of pages selected by the page selection unit. In an electronic comic book digest generation method executed on a computer,
A character unit corresponding area detection unit detecting a character unit corresponding area included in the page for each of predetermined pages of the electronic comic book;
A counting unit counting the character unit corresponding region detected by the character unit corresponding region detecting unit;
A step of selecting a predetermined number of pages by increasing the priority when the page selection unit selects a page with a smaller count value by the counting unit;
And a step of generating an animation file for displaying an animation including the predetermined number of pages selected by the page selection unit. Computer
A character unit corresponding region detection unit that detects a character unit corresponding region included in the predetermined page of each electronic comic book;
A counting unit that counts the character unit corresponding region detected by the character unit corresponding region detection unit;
A page selection unit that selects a predetermined number of pages with a higher priority when selecting a page with a smaller count value by the counting unit;
A computer program for generating an electronic comic book digest for use as an animation file generation unit for generating an animation file for animation display including the predetermined number of pages selected by the page selection unit.