WO2014050481A1 - Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci - Google Patents

Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci Download PDF

Info

Publication number
WO2014050481A1
WO2014050481A1 PCT/JP2013/073886 JP2013073886W WO2014050481A1 WO 2014050481 A1 WO2014050481 A1 WO 2014050481A1 JP 2013073886 W JP2013073886 W JP 2013073886W WO 2014050481 A1 WO2014050481 A1 WO 2014050481A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
character
ruby
character image
combined
Prior art date
Application number
PCT/JP2013/073886
Other languages
English (en)
Japanese (ja)
Inventor
浩教 矢野
Original Assignee
富士フイルム株式会社
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 富士フイルム株式会社 filed Critical 富士フイルム株式会社
Publication of WO2014050481A1 publication Critical patent/WO2014050481A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/60—Editing figures and text; Combining figures or text

Definitions

  • the present invention relates to a document image processing apparatus, its operation control method, and its operation control program.
  • Non-Patent Document 1 “development of document image layout reconstruction technology“ GT-Layout ”for portable terminals” (Non-Patent Document 1) is known. This GT-Layout makes it possible to view documents by scrolling in one direction by rearranging the character positions according to the display screen from the document image and character position information, and configuring the document image to match the display screen size. To do.
  • Patent Document 1 it is possible to rearrange character patterns without performing character recognition (Patent Document 1), but not for a document image, but prohibiting separation of ruby and parent characters (Patent Document) 2, 3)
  • the document image processing apparatus includes a character image cutout unit that cuts out a character image representing a character included in an image from a document image obtained by imaging the document, and a character represented by the character image cut out by the character image cutout unit.
  • Ruby determination means for determining whether or not it is ruby
  • parent character image detection for detecting a parent character image representing a parent character to which ruby determined by the ruby determination means is shaken from the character image cut out by the character image cutout means
  • a combined character image generating unit that generates a combined character image by combining the parent character image detected by the parent character image detecting unit and the ruby image determined to represent ruby by the ruby determining unit. It is characterized by being.
  • the present invention also provides an operation control method suitable for a document image processing apparatus. That is, in this method, the character image cutout means cuts out the character image representing the character included in the image from the document image obtained by imaging the document, and the ruby determination means uses the character image cut out in the character image cutout means. It is determined whether or not the character to be represented is ruby, and the parent character image detecting unit represents the parent character to which the ruby determined by the ruby determining unit is assigned from the character image cut out by the character image cutting unit. And the combined character image generation unit generates a combined character image by combining the parent character image detected by the parent character image detection unit and the ruby image determined to represent ruby by the ruby determination unit. Is.
  • the present invention also provides a computer readable program for executing the operation control method of the document image processing apparatus.
  • a recording medium storing such a program may also be provided.
  • a character image is cut out from a document image, and it is determined whether or not the cut out character image represents ruby.
  • a parent character image to which ruby is shaken is also detected. Then, the detected parent character image and the ruby character image are combined to generate a combined character image. Since the ruby image is combined with the parent character image to form one combined character image, when the document image is displayed again in the desired display area, the combined character image may be positioned, and the ruby image is positioned. There is no need. It can be displayed relatively easily.
  • the ruby determination means includes determination means for determining whether the character image cut out by the character image cutout means constitutes a row or a column, for example. In this case, the number of characters is smaller than the number of characters in the other rows or columns and the size of the character image in the other rows in response to the determination unit determining that the ruby image constitutes a row or column. Is determined to be a ruby image, the ruby image exists between rows or columns according to the determination that the ruby image does not constitute a row or column, and is smaller than the size of other character images. In this case, it will be determined as a ruby image.
  • the combined character image generation means for example, has a plurality of combined character images in which the parent character image and the ruby image are combined, and when these combined character images are adjacent, the adjacent combined character images are displayed. Furthermore, it is what is combined.
  • the character image clipped by the character image cutout means and the combined character image generated by the combined character image generation means are positioned in the display area of the display screen according to the character arrangement in the document image, and cut out by the character image cutout means.
  • the center line of the displayed character image is preferably positioned in the display area of the display screen so that the center line of the combined character image generated by the combined character image generating means matches.
  • FIG. 1 shows an embodiment of the present invention, in which an electric image of a document image processing apparatus 1 for shaping a document image (an imaged document will be referred to as a document image) so that it can be displayed in a desired display area.
  • a document image an imaged document will be referred to as a document image
  • FIG. 1 shows an embodiment of the present invention, in which an electric image of a document image processing apparatus 1 for shaping a document image (an imaged document will be referred to as a document image) so that it can be displayed in a desired display area.
  • a document image processing apparatus 1 for shaping a document image an imaged document will be referred to as a document image
  • the overall operation of the document image processing apparatus 1 is controlled by the control apparatus 2.
  • the document image processing apparatus 1 includes an input device 3 such as a keyboard for inputting various commands, a communication device 4 for communicating with other client terminal devices, mobile phones, etc., a display device 5 for displaying a document image, etc. A memory 6 for storing the data is provided.
  • the document image processing apparatus 1 is provided with a CD (compact disk) driver 7. When a compact disk 8 storing a program for controlling operations to be described later is loaded into the CD driver 7 and the program stored in the compact disk 8 is read by the CD driver 7, the program is processed by the document image processing apparatus. 1 installed.
  • the communication device 4 may be used to receive a program, and the received program may be installed in the document image processing device 1.
  • the document image processing device 1 includes a character region acquisition device 11, a ruby extraction device 12, a region synthesis device 13, and a shaped image creation device 14.
  • the character area acquisition device 11 detects and extracts a character image area from a document image. Extraction of character images can use the function of OCR (Optical Character Reader). The coordinate position of the character image in the document image, the character type represented by the character image, the order of the characters, and whether the character is written horizontally or vertically are also detected.
  • OCR Optical Character Reader
  • the ruby extraction device 12 extracts a ruby image from the character image acquired by the character area acquisition device 11.
  • the extraction of ruby images can also use the OCR function.
  • the area composition device 13 combines the ruby image with the parent character image representing the parent character to which the ruby is shaken to generate a combined character image. Whether the image is a parent character image can use the OCR function. In addition, when viewed from the ruby character image, a vertical line is drawn downward for horizontal writing and to the left for vertical writing, and the closest character image in the closest row can be determined as the parent character image. The parent character image and the ruby image are combined to generate a combined character image. When the combined character images generated in this way are adjacent to each other, the adjacent combined character images are also combined. However, it goes without saying that the combined character images need not be combined.
  • the shaped image creation device 14 positions and shapes the character image obtained by the character region acquisition device 11 and the combined character image obtained by the region synthesis device 13 so as to be displayed on a display screen having a desired display area. An image is generated. The center line of the parent character is matched to balance the characters.
  • FIG. 2 is an example of an imaged document image 20.
  • the document image 20 includes characters 21 to 29, 31 to 39, and 41 and 42 represented by the image. These letters 21 to 29, 31 to 39 and 41 and 42 are represented by circles. These characters 21 to 29, 31 to 39 and 41 and 42 are not represented by text data, but are represented by images.
  • the document image 20 is shaped so as to be displayed on a display screen (display window) having a desired display area.
  • Characters 41 and 42 are ruby characters that are waved to characters 37 and 38.
  • Ruby is a character with a role such as phonetics, explanations, and different readings for any character in a sentence, usually written on the right side of a character in vertical writing and above the character in horizontal writing. Ruby is often given in Japanese or Chinese, but ruby may be given in other languages.
  • FIG. 3 is a flowchart showing the processing procedure of the document image processing apparatus 1.
  • document image data representing the document image 20 is stored in the memory 6.
  • processing such as extraction of a character image from the document image 20 is performed (step 81).
  • FIG. 4 shows a state in which character images 51 to 59, 61 to 69, 71 and 72 representing characters 21 to 29, 31 to 39, 41 and 42 are extracted from the document image 20.
  • the extraction of the character images 51 to 59, 61 to 69, and 71 and 72 uses the OCR function as described above.
  • the extracted character images 51 to 59, 61 to 69, 71 and 72 are surrounded by a rectangle.
  • the upper left coordinates of these rectangles are the coordinate positions of the character images 51 to 59, 61 to 69, 71 and 72.
  • the position of the character image 51 is represented by coordinates (x1, y1).
  • the position of the character image 61 is represented by coordinates (x11, y11).
  • the positions of the ruby images 71 and 72 are represented by coordinates (x17, y17) and (x18, y18), respectively.
  • Other character image positions are also represented by coordinates.
  • the widths and heights of the character images 51 to 59, 61 to 69, 71 and 72 are also detected.
  • the detected coordinates of the character images 51 to 59, 61 to 69, 71 and 72, etc. are stored in the character information table.
  • FIG. 6 is an example of a character information table.
  • the character information table shown in FIG. 6 is for the document image 20.
  • the X-coordinate, Y-coordinate, width, height of the character image, the type of character represented by the character image, and the parent character Stores data indicating ruby.
  • the ID stored in the character information table identifies the character images 51 to 59, 61 to 69, 71 and 72, respectively.
  • ID is the arrangement order of the document image 20 except for the ruby images 71 and 72.
  • the ID of the character image 21 is ID1
  • the X coordinate is x1
  • the Y coordinate is y1
  • the width is w
  • the height is h.
  • the type of character detected by the OCR function (what character is represented) is also included.
  • character image 51 (character 21) is neither a parent character nor ruby. It can be seen that character images 67 and 68 (characters 37 and 38) specified by ID16 and ID17 are parent characters, and character images 71 and 72 (characters 41 and 42) specified by ID19 and ID20 are ruby.
  • ruby determination processing is performed on the extracted character image (step 82).
  • the ruby determination process can use the OCR function as described above, and can use other methods described above. If the extracted character image includes a ruby image (YES in step 83), a parent image corresponding to the ruby image is detected (step 84). As described above, the OCR function can be used to detect the parent image, and other methods described above can also be used.
  • the ruby image and the parent image are detected, the ruby image and the parent image are combined to generate a combined character image (step 85).
  • FIG. 5 shows how a combined character image is generated.
  • the ruby image 71 is combined with the parent character image 67 to generate a combined character image 81. Since the base character of the ruby 42 is the base character 38, the ruby image 72 is combined with the base character image 68 to generate a combined character image 82.
  • the combined character images 81 and 82 in which the ruby and the parent character are integrated are generated.
  • the combined character images 81 and 82 generated in this way are adjacent, these combined character images 81 and 82 are combined.
  • a combined character image 80 is generated.
  • the parent character image representing a plurality of parent characters to which ruby is shaken is displayed, the parent character image is separated.
  • the combined character images 81 and 82 need not be combined to generate the combined character image 80.
  • FIG. 7 shows an example of the corrected character information table.
  • the ruby image 71 and the parent image 67 are combined to generate a combined character image 81, and the ruby image 71 and the parent image 68 are combined to generate a combined character image 82. It is an example of the character information table after correction in the case of being done.
  • the combined character image 81 is generated by combining the ruby image 71 with the parent image 67, the character information about the ruby image 71 is deleted, and the character information about the parent image 67 indicated by ID16 is replaced with the combined character image 81.
  • the combined character image 81 is a combination of the ruby image 71 and the parent image 67, the new coordinate position is set to x31 for the X coordinate and y31 for the Y coordinate, the width does not change, and the height is 6h / Has been changed to 5.
  • Data (parent + ruby) indicating that a parent character and a ruby character are included is also recorded in the character information table.
  • the ruby image 72 is combined with the parent image 68 to generate the combined character image 82
  • the character information about the ruby image 72 is deleted, and the character information about the parent image 68 indicated by ID17 is combined.
  • the character information about the character image 82 is used.
  • the new coordinate position of the combined character image 82 is set to x32 for the X coordinate and y32 for the Y coordinate, the width is not changed, and the height is changed to 6h / 5.
  • Data (parent + ruby) indicating that a parent character and a ruby character are included is also recorded in the character information table.
  • the corrected character information table is as shown in FIG.
  • the corrected character information table is as shown in FIG.
  • the character information about the combined character image 82 is deleted, and the character information about the combined character image 81 indicated by ID16 is changed. , Character information about the new combined character image 80.
  • the width of the new combined character image 80 is changed from w to 2w.
  • a ruby image and a parent image are detected and a combined character image is generated, or if a ruby image is not detected, the detected character image is positioned in the display area of the display screen to be displayed. (Step 86). As a result, processing for creating a shaped image is performed.
  • FIG. 9 shows a state in which the character image is positioned in the display area 50 corresponding to the desired display screen.
  • the width of the display area 50 is narrower than the width of the document image 20. Assuming that ruby 41 and 42 are not included in the number of lines, the document image 20 displays all of the character images 51 to 59 and 61 to 69 in two lines. Images 51 through 59 and 61 through 69 cannot all be displayed.
  • Character images 51 to 55 are positioned on the first line of the display area 50, character images 56 to 59 and 61 are positioned on the second line of the display area 50, and the third line of the display area 50 is positioned on the third line.
  • Character images 62 to 66 are positioned, and a combined character image 80 and a character image 69 are positioned in the fourth line of the display area 50. Positioning of these character images 51 to 59, 61 to 65 and 69 and the combined character image 80 is performed using the character information table shown in FIG. 8 so as to fit in the display area according to the character arrangement of the document image 20. Needless to say.
  • the combined character image 80 obtained by combining the combined character images 81 and 82 is positioned at the end of the line, and the combined character image 80 does not fit in the line, the combined character image 80 is Positioning may be performed so as to be positioned at the end of the line, and the character image of the entire line may be reduced at a predetermined reduction rate.
  • the character image positioned in the display area 50 in this way is displayed on the display screen 6 of the display device 5 (step 87).
  • FIG. 10 is a flowchart showing the ruby determination processing procedure, and shows the processing procedure of step 82 in FIG.
  • step 91 it is confirmed whether or not the extracted character image constitutes a line (step 91). Whether or not the character image forms a line can be determined by whether or not a plurality of character images having the same detected Y-coordinate position are arranged and the character images are arranged in the line direction at regular intervals. If it is determined that the character image constitutes a line (YES in step 91), the number of characters per line is counted (step 92). The number of characters per line can be easily determined from the character information table. When the number of characters per line is obtained, the average value of the number of characters per line is calculated, and the average value is used as the character number threshold value (step 93).
  • Ruby is rarely applied to all characters that make up a line, and the ruby for one line is generally less than the average number of characters in the line, so it is greater than the character count threshold. It is determined that the character in the character number line is not ruby (NO in step 94).
  • Step 95 it is further checked whether the size of the character image is smaller than the average character image size obtained from the character information table. Since the ruby is smaller than the average size of the characters included in the document image 20, if the size of the character image is smaller than the average size of the character image (YES in step 95), the character image is the ruby image. Is determined (step 96). If it is larger than the average character image size (NO in step 95), the character image is not a ruby image.
  • Whether or not a character image exists between lines can be determined from the sequence of Y coordinate positions of the character image obtained from the character information table. For example, when there are a plurality of character images having the same Y coordinate, they are considered to be character images constituting a line, and a character at a position sandwiched between such character images in the line direction (Y-axis direction). It can be determined that the image is a character image existing between lines.
  • FIG. 11 and FIG. 12 show a method for positioning the character image and the combined character image.
  • FIG. 11 shows how the combined character images 81 and 82 and the character image 69 are positioned in a state where the combined character image 81 and the combined character image 82 are not combined.
  • FIG. 12 shows a state in which the combined character image 80 and the character image 69 obtained by combining the combined character image 81 and the combined character image 82 are positioned.
  • the centers of the parent characters (parent character images) 37 and 38 included in the combined character image 80 and the centers of the characters 39 (character image 69) included in the character image 69 are displayed. Through a center line C extending in the horizontal direction. If the center of the parent character 37 and the center of the parent character 38 do not coincide with each other in the Y direction, the average Y coordinate of those centers and the Y coordinate of the center of the character image 60 are aligned.
  • one character image or combined character image is sequentially positioned in the display area 50 one by one.
  • a plurality of character images (including combined character images) corresponding to the width of the display area 50 are included. May be cut out from the document image, and the cut out character image group may be positioned in the display area 50.
  • the document image processing apparatus 1 performs processing for extracting a character image from the document image, processing for determining whether the extracted character image is ruby or a parent character, processing for generating a combined character image, and formatting.
  • Image creation processing and display processing on the display device 5 are performed.
  • Data representing the created shaped image is transmitted from the document image processing device 1 to another terminal device such as a mobile phone, and the terminal device.
  • the display process may be performed at.
  • the shaping image creation process may be performed in another terminal device.
  • the processing in the document image processing apparatus 1 may be executed by software using a server instead of a dedicated apparatus, or may be executed by a mobile phone such as a smartphone.
  • the horizontally written document image has been described.
  • the embodiment can be similarly applied to a vertically written document image instead of horizontally written.
  • vertical writing it may be read as a column instead of a row.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Document Processing Apparatus (AREA)

Abstract

Selon la présente invention, même si les caractères ruby ont été placés dans une image de caractères qui a été reproduite, il est possible d'effectuer un réaffichage de manière relativement facile sur une zone d'affichage voulue. Une image de caractère est extraite à partir d'une image de document (étape 81), et un processus de détermination ruby est effectué par rapport à l'image de caractères extraite (étape 82). Si l'image de caractère est une image ruby, l'image de caractère mère de l'image ruby est également détectée (étape 84). L'image ruby et l'image de caractère mère sont jointes, ce qui génère une image de caractères joints (étape 85). L'image de caractère détectée ou l'image de caractères joints générée est positionnée sur une zone d'affichage voulue (étape 86), et est affichée (étape 87). L'image ruby et l'image de caractère mère sont jointes de manière à empêcher la séparation de l'image ruby et de l'image de caractère mère.
PCT/JP2013/073886 2012-09-26 2013-09-05 Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci WO2014050481A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2012-211632 2012-09-26
JP2012211632 2012-09-26

Publications (1)

Publication Number Publication Date
WO2014050481A1 true WO2014050481A1 (fr) 2014-04-03

Family

ID=50387889

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2013/073886 WO2014050481A1 (fr) 2012-09-26 2013-09-05 Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci

Country Status (1)

Country Link
WO (1) WO2014050481A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018142286A (ja) * 2017-02-28 2018-09-13 シナノケンシ株式会社 電子図書製作用プログラム

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0594511A (ja) * 1991-10-02 1993-04-16 Ricoh Co Ltd 画像処理装置
JPH1031716A (ja) * 1996-05-13 1998-02-03 Matsushita Electric Ind Co Ltd 文字行抽出方法および装置
JP2004005453A (ja) * 2002-03-01 2004-01-08 Xerox Corp 文書画像レイアウトの解体と再表示の方法およびシステム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0594511A (ja) * 1991-10-02 1993-04-16 Ricoh Co Ltd 画像処理装置
JPH1031716A (ja) * 1996-05-13 1998-02-03 Matsushita Electric Ind Co Ltd 文字行抽出方法および装置
JP2004005453A (ja) * 2002-03-01 2004-01-08 Xerox Corp 文書画像レイアウトの解体と再表示の方法およびシステム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018142286A (ja) * 2017-02-28 2018-09-13 シナノケンシ株式会社 電子図書製作用プログラム

Similar Documents

Publication Publication Date Title
US20230394428A1 (en) Information processing apparatus, control method, and program
US10489051B2 (en) Handwriting input apparatus and control method thereof
US20160202887A1 (en) Method for managing application icon and terminal
US20130187923A1 (en) Legend indicator for selecting an active graph series
KR101272867B1 (ko) 모바일 단말기의 그리드 출력 장치 및 그 방법
US20150170392A1 (en) Electronic device and method for outputting handwriting fonts
JP2006079220A (ja) 画像検索装置および方法
JP5654851B2 (ja) 文書画像表示装置ならびにその動作制御方法およびその制御プログラム
EP2718799A1 (fr) Procédé et dispositif de détermination d'un mode d'affichage de documents électroniques
CN108874285B (zh) 一种用户终端上书写字迹的显示方法及用户终端
JP2015052864A (ja) 帳票読取装置およびプログラム
US8824806B1 (en) Sequential digital image panning
WO2014050481A1 (fr) Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci
JP6287498B2 (ja) 電子ホワイトボード装置、電子ホワイトボードの入力支援方法、及びプログラム
US9377853B2 (en) Information processing apparatus and information processing method
CN106940615A (zh) 一种表格处理方法及装置、用户设备
JP5794154B2 (ja) 画像処理プログラム、画像処理方法、及び画像処理装置
JP6160359B2 (ja) 情報処理装置、プログラム、および情報提示方法
JP6476732B2 (ja) 文書処理装置、その制御方法、およびプログラム
CN108346126B (zh) 基于内存拷贝方式绘制手机图片的方法及装置
US20130104014A1 (en) Viewer unit, server unit, display control method, digital comic editing method and non-transitory computer-readable medium
WO2014050480A1 (fr) Dispositif de traitement d'image de document, procédé de commande de fonctionnement de celui-ci, et programme pour commander le fonctionnement de celui-ci
JP2015038670A (ja) 電子機器および方法
KR102419695B1 (ko) 스크롤 제어 방법, 장치, 프로그램 및 컴퓨터 판독가능 기록매체
JP6146222B2 (ja) 手書き入力装置およびプログラム

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: 13841061

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: 13841061

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP