WO2012138005A1 - Procédé et appareil de génération de contenus de livre électronique - Google Patents

Procédé et appareil de génération de contenus de livre électronique Download PDF

Info

Publication number
WO2012138005A1
WO2012138005A1 PCT/KR2011/002722 KR2011002722W WO2012138005A1 WO 2012138005 A1 WO2012138005 A1 WO 2012138005A1 KR 2011002722 W KR2011002722 W KR 2011002722W WO 2012138005 A1 WO2012138005 A1 WO 2012138005A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
text
picture
file
generating
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/KR2011/002722
Other languages
English (en)
Korean (ko)
Inventor
박상현
김유선
안재균
신은지
김현진
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industry Academic Cooperation Foundation of Yonsei University
Original Assignee
Industry Academic Cooperation Foundation of Yonsei University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industry Academic Cooperation Foundation of Yonsei University filed Critical Industry Academic Cooperation Foundation of Yonsei University
Publication of WO2012138005A1 publication Critical patent/WO2012138005A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/957—Browsing optimisation, e.g. caching or content distillation
    • G06F16/9577—Optimising the visualization of content, e.g. distillation of HTML documents
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting

Definitions

  • the present invention relates to an e-book, and more particularly, to separate a picture area and a text area from a page image of a picture book, and to generate a picture file and a text file from the separated picture area and a text area, through text recognition.
  • an object of the present invention is to separate the picture area and the text area from the page image of the picture book and generate a picture file and a text file from the separated picture area and the text area, the character recognition
  • the present invention provides an apparatus and method for generating e-book content by creating a text file and rearranging the same with a picture file.
  • an apparatus for generating e-book content when receiving a page image of a picture book, a region separating unit for separating the input page image into a picture area and a text area; A picture file generator for generating the separated picture area as a picture file; A text file generation unit generating the separated text area into a text file through text recognition; And a content generation unit for generating one e-book content by combining the generated picture file and the text file, wherein the content generation unit arranges the characters included in the text file according to the shape of the picture file.
  • Book content can be created.
  • the area separator converts a color page image into a gray page image, removes noise by applying an anisotropic diffusion filter to the converted gray page image, and noise
  • obtain row projection data and thermal projection data for binary data obtained through binarization and analyze the obtained row projection data and the thermal projection data to analyze a picture area and a picture.
  • a dividing reference line of an area may be obtained, and the picture area and the text area may be separated based on the obtained reference line.
  • the binary data may be set to 1 in an area where data exists and to 0 in an area where data does not exist.
  • the row projection data may indicate the number of regions in which binary data is set to 1 on the horizontal axis
  • the thermal projection data may indicate the number of regions in which binary data is set to 1 on the vertical axis.
  • the area separator may separate the picture area and the text area based on different reference lines when the picture area and the text area partially overlap each other.
  • the area separator may take the entire area as the picture area after separating the text area when all of the picture area and the text area overlap.
  • the text file generation unit may extract a text area from the text area in units of lines, and generate each of the extracted text areas as one text file by recognizing a character through an OCR (Optical Character Recognition) technique. .
  • OCR Optical Character Recognition
  • the content generation unit may generate the e-book content in an ePub (electronic publication) format having a feature capable of automatically adjusting the space to automatically fit the screen according to the aspect ratio and size of the screen.
  • ePub electronic publication
  • a method for generating e-book content includes: (a) receiving a page image of a picture book, separating the input page image into a picture area and a text area; (b) generating the separated picture area into a picture file; (c) generating the separated text area into a text file through text recognition; And (d) combining the generated picture file with the text file to generate a single e-book content, wherein step (d) includes the characters included in the text file according to the shape of the picture file.
  • the electronic book content may be generated by arranging.
  • the step (a) if the page image of the picture book is a color, the color page image is converted into a gray page image, and an anisotropic diffusion filter is applied to the converted gray page image to remove noise.
  • an anisotropic diffusion filter is applied to the converted gray page image to remove noise.
  • obtain row projection data and thermal projection data for binary data obtained through binarization After increasing the contrast of the noise-removed page image, obtain row projection data and thermal projection data for binary data obtained through binarization, and analyze the obtained row projection data and the thermal projection data to analyze a picture region.
  • a reference line that can be divided into a picture area and a picture area can be obtained, and the picture area and the text area can be separated based on the obtained reference line.
  • the binary data may be set to 1 in an area where data exists and to 0 in an area where data does not exist.
  • the row projection data may indicate the number of regions in which binary data is set to 1 on the horizontal axis
  • the thermal projection data may indicate the number of regions in which binary data is set to 1 on the vertical axis.
  • the picture area and the text area may be separated based on different reference lines.
  • the step (a) may take the entire area as the picture area after separating the text area when all of the picture area and the text area overlap.
  • the step (c) may extract a character area from the character area in units of lines, and generate each of the extracted character areas into a single character file by recognizing characters through OCR (Optical Character Recognition) technique.
  • OCR Optical Character Recognition
  • the step (d) may generate the e-book content in an ePub (electronic publication) format having an automatic space adjustment characteristic of automatically displaying the e-book content according to the aspect ratio and size of the screen.
  • ePub electronic publication
  • the present invention divides the picture area and the text area from the page image of the picture book and generates a picture file and a text file from the separated picture area and the text area, and generates a text file through character recognition and rearranges the picture file. In this case, text reading can be facilitated from the user's point of view.
  • the present invention by separating the picture area and the text area in the page image of the picture book and generates a picture file and a text file from the separated picture area and the text area, by creating a text file through the character recognition and rearranged with the picture file, There is an effect that can increase the utilization of the terminal screen to display the page image of the picture book.
  • FIG. 1 is an exemplary view showing an apparatus for generating e-book content according to an embodiment of the present invention.
  • FIG. 2 is an exemplary view for explaining a principle of separating a picture area and a text area according to an embodiment of the present invention.
  • FIG. 3 is an exemplary diagram for explaining a principle of generating a text file according to the present invention.
  • FIG. 4 is an exemplary diagram illustrating a type of e-book content according to an embodiment of the present invention.
  • FIG. 5 is an exemplary view for explaining a principle of generating e-book content according to an embodiment of the present invention.
  • FIG. 6 is an exemplary view illustrating a method for generating e-book content according to an embodiment of the present invention.
  • FIGS. 1 to 6 An apparatus and method for generating e-book content according to an embodiment of the present invention will be described with reference to FIGS. 1 to 6. It will be described in detail focusing on the parts necessary to understand the operation and action according to the present invention. Like reference numerals in the drawings denote like elements throughout.
  • a picture file and a text file are separated from a picture area and a text area in a page image of a picture book, and a picture file and a text file are generated from the separated picture area and a text area.
  • the page image of the picture book may mean an image generated by scanning or capturing each page of the picture book.
  • an e-book refers to a book published in digital form without the use of paper media for the content of knowledge and information.
  • Such an e-book refers to a PC or a program equipped with a program for reading an e-book. It can be seen through a portable terminal, and such a device is sometimes called an e-book. In other words, it can refer to all software and hardware media including content in a broad sense.
  • FIG. 1 is an exemplary view showing an apparatus for generating e-book content according to an embodiment of the present invention.
  • an apparatus for generating e-book content includes an input unit 110, an area separator 120, a picture file generator 130, a text file generator 140, and content. It may be configured to include a generator 150, a display 160, and a memory 170. The device thus configured may be applied to mobile devices such as mobile phones, personal digital assistants (PDAs), and notebook computers.
  • PDAs personal digital assistants
  • the input unit 110 may receive a page image of a picture book through a wired / wireless internet network.
  • the page image of the picture book means an image scanned or captured for each page of the picture book, and may be a color image or a gray image.
  • the page image may be stored in the memory 170 for each picture book received in this way.
  • the area extractor 120 may divide the page image of the input picture book into a picture area and a text area. This will be described in detail as follows.
  • the area extractor 120 may convert the color page image into a gray page image.
  • the region extractor 120 may remove noise by applying an anisotropic diffusion filter to the converted gray page image.
  • the noise may be noise existing in each page of the original picture book, or may be noise generated in the process of scanning or capturing the picture book.
  • the area extractor 120 may obtain binary data by iterative binarization based on a threshold value after increasing the contrast of the page image from which the noise is removed. For example, an area in which data exists may be set to '1', and an area in which data does not exist may be set to '0'.
  • the region extractor 120 may obtain horizontal or row projection data and vertical or column projection data with respect to the binary data thus obtained using Equation 1 below.
  • Row projection data h j the number of 255 in row i, 0 ⁇ i ⁇ N-1
  • the row projection data may indicate the number of regions in which binary data is set to '1' on the horizontal axis
  • the column projection data may indicate the number of regions in which binary data is set to '1' on the vertical axis.
  • the region extractor 120 may analyze the obtained row projection data and thermal projection data to obtain a dividing reference line between the image region and the image region, that is, the boundary line of the image region. That is, the reference line of the horizontal axis or the vertical axis can be obtained according to the ratio of continuous white parts.
  • the area extractor 120 may separate the picture area and the text area based on the obtained reference line.
  • the picture area and the text area may be clearly distinguished and do not overlap, but the picture area and the text area may partially overlap. This will be described with reference to FIG. 2.
  • FIG. 2 is an exemplary view for explaining a principle of separating a picture area and a text area according to an embodiment of the present invention.
  • the figure region and the text region may be separated based on a reference line when the figure region and the text region do not overlap.
  • Figure (b) when the picture area and the text area are partially overlapped, the picture area and the text area can be separated based on different reference lines.
  • the picture file generation unit 130 converts the separated picture area into formats such as Joint Photographic Coding Experts Group (JPEG), Graphics Interchange Format (GIF), Bitmap image (BMP), and Portable Network Graphics (PNG). Can be generated.
  • JPEG Joint Photographic Coding Experts Group
  • GIF Graphics Interchange Format
  • BMP Bitmap image
  • PNG Portable Network Graphics
  • the text file generator 140 may generate the separated text area as a text file, for example, a text file, through an optical character recognition (OCR) technique. This will be described with reference to FIG. 3.
  • OCR optical character recognition
  • FIG. 3 is an exemplary diagram for explaining a principle of generating a text file according to the present invention.
  • the text file generation unit 140 extracts a text area from a separated text area in a row unit, and recognizes text through each OCR technique. To create a single text file.
  • the content generation unit 150 may generate one e-book content by combining the generated picture file and the text file. That is, the content generation unit 150 may combine the picture file and the text file, and generate the e-book content by placing the characters included in the text file according to the shape of the picture file.
  • the e-book content may be a format such as ePub (electronic publication), pdf, azw, etc., it is preferable to use the ePub format.
  • the ePub format is a standard established by the IDPF (International Digital Publishing Forum). It is a zip packaging format based on XHTML, CSS, and XML. It can be automatically space-adjusted. When viewing an e-book through the viewer, it is automatically displayed according to the aspect ratio and size of the screen.
  • FIG. 4 is an exemplary diagram illustrating a type of e-book content according to an embodiment of the present invention.
  • the figure (a) shows the form where the letters are placed upside and the figure is placed below
  • the figure (b) shows the form where the figures are placed above and the letters are placed below
  • the figure (c) In Figure 2, the text is placed on the left and the picture is placed on the right. In Figure (d), the picture is placed on the left and the text is placed on the right.
  • the picture when the screen size of the terminal is 7 ⁇ 13 cm 2 , the picture may be arranged at the bottom with a size of 7 ⁇ 7, and the characters may be arranged at the top with a size of 7 ⁇ 6.
  • the content generation unit 150 generates one e-book content by combining the generated picture file and the text file, but generates all types of e-book content.
  • the screen may be displayed as shown in (a) or (b), and when viewed horizontally, the screen may be displayed as shown in (c) or (d).
  • the screen of the terminal is smaller than the actual picture book characters and pictures, the picture is fixed by adding a scroll and the text can be viewed through the scroll according to the content.
  • FIG. 5 is an exemplary view for explaining a principle of generating e-book content according to an embodiment of the present invention.
  • the content generation unit 150 may combine the picture file and the text file, and generate the e-book content by arranging characters included in the text file according to the shape of the picture file.
  • FIG. 6 is an exemplary view illustrating a method for generating e-book content according to an embodiment of the present invention.
  • the electronic book content generating apparatus when the electronic book content generating apparatus receives a plurality of page images of a picture book (S610), the input page image may be divided into a picture area and a text area (S611). .
  • the e-book content generating apparatus may convert the color page image into a gray page image if the page image of the picture book is color.
  • the e-book content generating device removes noise by applying an anisotropic diffusion filter to the converted gray page image, and increases the contrast of the noise-removed page image.
  • Binarization yields binary data.
  • the e-book content generating device may acquire horizontal or row projection data and vertical or column projection data on the obtained binary data.
  • the e-book content generating device analyzes the acquired row projection data and the thermal projection data to obtain a dividing reference line of the drawing area and the drawing area, that is, the boundary of the drawing area, and separates the drawing area and the text area based on the obtained reference line. Can be.
  • the e-book content generating apparatus may generate the separated picture area as a picture file (S612), and may generate the separated text area as a text file through an OCR (Optical Character Recognition) technique.
  • OCR Optical Character Recognition
  • the e-book content generating apparatus extracts the text areas from the separated text areas in units of lines (S613), and recognizes each of the extracted text areas in units of lines through the OCR technique (S614). Can be generated as (S615).
  • the e-book content generation device may generate one e-book content by combining the generated picture file and the text file according to a preset combination type (S616).

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Character Input (AREA)

Abstract

La présente invention concerne un procédé et un appareil pour générer des contenus de livre électronique. Selon la présente invention, un appareil pour générer des contenus de livre électronique comprend : une unité de division en zones divisant l'entrée de la page d'image en une zone d'image et une zone de texte si une image de page d'un livre électronique est entrée ; une unité de génération de fichier d'image générant un fichier d'image à partir de la zone d'image divisée ; une unité de génération de fichier de texte générant un fichier de texte à partir de la zone de texte divisée par une reconnaissance de texte ; et une unité de génération de contenus combinant le fichier d'image généré et le fichier de texte généré pour générer un ensemble de contenus de livre électronique, l'unité de génération de contenus pouvant agencer le texte inclus dans le fichier de texte pour générer le contenu de livre électronique selon le format du fichier d'image. Par conséquent, selon la présente invention, une meilleure utilisation peut être effectuée d'un écran de terminal affichant une image de page d'un livre d'image, et la lecture d'un texte du point de vue d'un utilisateur peut être facilitée.
PCT/KR2011/002722 2011-04-04 2011-04-15 Procédé et appareil de génération de contenus de livre électronique Ceased WO2012138005A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2011-0030826 2011-04-04
KR20110030826 2011-04-04

Publications (1)

Publication Number Publication Date
WO2012138005A1 true WO2012138005A1 (fr) 2012-10-11

Family

ID=46969379

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2011/002722 Ceased WO2012138005A1 (fr) 2011-04-04 2011-04-15 Procédé et appareil de génération de contenus de livre électronique

Country Status (1)

Country Link
WO (1) WO2012138005A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060088175A (ko) * 2005-02-01 2006-08-04 장완호 멀티 포맷을 갖는 전자책 파일 생성 방법 및 시스템
JP2008519329A (ja) * 2004-11-01 2008-06-05 スロムコウスキ、スティーヴン 印刷本を補完する電子コンテンツの提供およびそのアクセス制御を行うためのシステムおよび方法［関連する出願］本出願は、２００４年１１月１日に出願された米国特許出願第１０／９７９，５４３号「印刷本を補完する電子コンテンツの提供およびそのアクセス制御を行うためのシステムおよび方法」に基づく優先権を主張するものであり、当該出願は、米国オレゴン州ポートランド市のＺｕｒｉｍｅｄｉａ社（以降、単にＺｕｒｉ（登録商標）とする）に譲渡されており、当該出願の内容はこの引用によりここに全て含まれているものとする。
KR20080069887A (ko) * 2007-01-24 2008-07-29 퍼듀 리서치 파운데이션 이미지 처리장치 및 그 이미지 처리방법
KR20100065694A (ko) * 2008-12-08 2010-06-17 (주)서전미디어텍 이-북 단말 및 이를 이용한 온라인 교육 시스템 및 방법
KR100980748B1 (ko) * 2005-08-23 2010-09-07 가부시키가이샤 리코 혼합 미디어 환경을 생성 및 사용하는 시스템 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008519329A (ja) * 2004-11-01 2008-06-05 スロムコウスキ、スティーヴン 印刷本を補完する電子コンテンツの提供およびそのアクセス制御を行うためのシステムおよび方法［関連する出願］本出願は、２００４年１１月１日に出願された米国特許出願第１０／９７９，５４３号「印刷本を補完する電子コンテンツの提供およびそのアクセス制御を行うためのシステムおよび方法」に基づく優先権を主張するものであり、当該出願は、米国オレゴン州ポートランド市のＺｕｒｉｍｅｄｉａ社（以降、単にＺｕｒｉ（登録商標）とする）に譲渡されており、当該出願の内容はこの引用によりここに全て含まれているものとする。
KR20060088175A (ko) * 2005-02-01 2006-08-04 장완호 멀티 포맷을 갖는 전자책 파일 생성 방법 및 시스템
KR100980748B1 (ko) * 2005-08-23 2010-09-07 가부시키가이샤 리코 혼합 미디어 환경을 생성 및 사용하는 시스템 및 방법
KR20080069887A (ko) * 2007-01-24 2008-07-29 퍼듀 리서치 파운데이션 이미지 처리장치 및 그 이미지 처리방법
KR20100065694A (ko) * 2008-12-08 2010-06-17 (주)서전미디어텍 이-북 단말 및 이를 이용한 온라인 교육 시스템 및 방법

Similar Documents

Publication Publication Date Title
CN101558425B (zh) 图像处理设备和图像处理方法
US9544473B2 (en) Information processing system and information processing method
CN102196130B (zh) 图像处理装置及图像处理方法
JP6119992B2 (ja) 画像処理装置およびコンピュータプログラム
JP6559415B2 (ja) 文書画像処理装置、それを備えた情報処理装置、プログラム、及び記録媒体
CN1967567A (zh) 自动创建索引的图像形成装置及其方法
WO2014003520A1 (fr) Afficheur à del de publicité en extérieur, et procédé d'interaction
WO2013061674A1 (fr) Dispositif de sortie de fichiers documents, procédé de sortie de fichiers documents et programme informatique
CN104391886A (zh) 一种电子书发送方法及装置
US8867050B2 (en) Image processing apparatus, non-transitory computer readable medium storing program and image processing method for restoring a single table from a plurality of pages
JP2009145963A (ja) 文書処理装置および文書処理方法
Lakshmi Design and Implementation of Text to Speech conversion using Raspberry pi
KR102300475B1 (ko) 표가 삽입된 이미지를 전자 문서로 변환할 수 있는 전자 장치 및 그 동작 방법
WO2011049408A2 (fr) Procédé de lecture de code affiché sur des matériaux imprimés
WO2012138005A1 (fr) Procédé et appareil de génération de contenus de livre électronique
CN119720946A (zh) 文档内容提取方法、装置、设备及计算机可读存储介质
WO2011093568A1 (fr) Procédé de reconnaissance de page de support d'impression basée sur une mise en page
JP2012049860A (ja) 画像処理装置、画像処理方法およびプログラム
WO2010134692A1 (fr) Méthode de création d'un fichier image à des fins de vérification de contrefaçons et méthode de vérification de contrefaçons de fichiers images
WO2011007970A1 (fr) Procédé et appareil pour traiter une image
WO2022255558A1 (fr) Code qr dans lequel est insérée une image de logo et son procédé de fabrication
CN105516538A (zh) 一种扫描过程显示扫描内容的方法和系统
AU2011253923A1 (en) Image processing apparatus, image processing method, and program
WO2023191182A1 (fr) Système et procédé de conversion automatique d'animation en bandes dessinées en ligne par une touche
WO2022255557A1 (fr) Code qr dans lequel une image est insérée, et procédé de génération associé

Legal Events

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

Ref document number: 11862979

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 11862979

Country of ref document: EP

Kind code of ref document: A1