JP2584973B2 - Recognition result output method in character recognition device - Google Patents
Recognition result output method in character recognition deviceInfo
- Publication number
- JP2584973B2 JP2584973B2 JP61090037A JP9003786A JP2584973B2 JP 2584973 B2 JP2584973 B2 JP 2584973B2 JP 61090037 A JP61090037 A JP 61090037A JP 9003786 A JP9003786 A JP 9003786A JP 2584973 B2 JP2584973 B2 JP 2584973B2
- Authority
- JP
- Japan
- Prior art keywords
- character
- size
- information
- recognition
- recognition result
- 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.)
- Expired - Fee Related
Links
Description
【発明の詳細な説明】 技術分野 本発明は、文字認識装置における認識結果出力方法に
関するものである。Description: TECHNICAL FIELD The present invention relates to a recognition result output method in a character recognition device.
従来技術 従来、文字認識装置では、認識対象文字の大きさや書
体の違いを区別せず、認識結果は、どんな文字に対して
も文字コードだけであり、これを、出力装置(プリンタ
ー、ディスプレイ等)に印字する際には、元の文字の大
きさや書体にはかかわらず、同一のフォント(大きさ、
字体)だけであった。2. Description of the Related Art Conventionally, a character recognition device does not distinguish between the size of a character to be recognized and a difference in typeface, and the recognition result is only a character code for any character, and this is output to an output device (printer, display, etc.). When printing on the same font, regardless of the original character size and typeface, the same font (size,
Font).
第3図は従来の文字認識装置の認識結果を説明するた
めの図である。FIG. 3 is a diagram for explaining a recognition result of a conventional character recognition device.
例えば、第3図のような、見出しが大きなゴシック体
で書かれ、本文は明朝体で書かれた文書を文字認識装置
で読取ると、その結果は文字コード列だけであり、見出
し文字の大きさや、ゴシック体、明朝体の情報が付加さ
れていないために、出力装置(プリンター、ディスプレ
イ等)上では同一の文字となってしまう。For example, as shown in Fig. 3, when a heading is written in a large Gothic font and the text is read in a Mincho font using a character recognition device, the result is only a character code string. Since no Gothic type or Mincho type information is added, the same character is displayed on an output device (printer, display, etc.).
目的 本発明は、文字の大きさ情報あるいは書体情報を文字
認識結果に付加することができる文字認識装置における
認識結果出力方法を提供することを目的とするものであ
る。An object of the present invention is to provide a recognition result output method in a character recognition device capable of adding character size information or typeface information to a character recognition result.
構成 第1図は本発明の一実施例の構成を示すブロック図で
あり、1はスキャナー、2は文字切出し部、3は大きさ
判定部、4は特徴抽出部、5はフォント判定部、6は辞
書検索部、7は結果判定部、8は出力装置である。Configuration FIG. 1 is a block diagram showing the configuration of one embodiment of the present invention, wherein 1 is a scanner, 2 is a character cutout unit, 3 is a size determination unit, 4 is a feature extraction unit, 5 is a font determination unit, 6 Is a dictionary search unit, 7 is a result determination unit, and 8 is an output device.
これは、文字切出し部2から文字の大きさの情報を得
て、文字の大きさを判定する大きさ判定部3と、フォン
ト(書体)の判定を行うフォント判定部5とから出力さ
れる文字の大きさ、フォントの情報を付加して、結果を
出力する結果判定部7と、出力装置8を備えた文字認識
装置である。This is achieved by obtaining character size information from the character cutout unit 2 and determining the size of a character by a size determining unit 3 and a font determining unit 5 that determines a font (font). This is a character recognition device including a result determination unit 7 for adding the size and font information and outputting a result, and an output device 8.
文字の高さ、幅をそれぞれH,Wとし、予め与えられた
標準文字の高さ、幅をHst,Wstとし、倍率をHB,WBとすれ
ば、 HB=0の時、0<H<(3/4)Hst =1 (3/4)Hst≦H<(5/4)Hst =2 (5/4)Hst≦H<(7/4)Hst =3 (7/4)Hst≦H<(9/4)Hst となる。If the height and width of a character are H and W, respectively, the height and width of a standard character given in advance are H st and W st and the magnification is H B and W B , When H B = 0, 0 <H <(3/4) H st = 1 (3/4) H st ≦ H <(5/4) H st = 2 (5/4) H st ≦ H <( 7/4) H st = 3 (7/4) H st ≦ H <(9/4) H st
ここで、例としてHB=0〜7、WB=0〜7の8段階の
値を取るとし、文字コードに1バイトの大きさの情報を
付加すれば第3図の文書は第2図のようになる。Here, as an example, assuming that eight values of H B = 0 to 7 and W B = 0 to 7 are taken, and if information of 1 byte size is added to the character code, the document of FIG. become that way.
第2図は本発明におけるフォント情報付加の説明図で
あり、21はフォント情報(1byte)、22は文字コード(2
byte)を、また、00は明朝体、01はゴシック体、10はナ
ール体、11は教科書体を示す。FIG. 2 is an explanatory diagram of the addition of font information in the present invention, wherein 21 is font information (1 byte), and 22 is a character code (2 bytes).
byte), 00 indicates Mincho style, 01 indicates Gothic style, 10 indicates Nahl style, and 11 indicates textbook style.
フォント判定部5で、一般によく知られたフォント判
定法(各フォントの辞書との照合を行い、最も距離の小
さい文字のフォントと判定するなど)でその文字の書体
を判定し、例えば、明朝体、ゴシック体、ナール体、教
科書体の4種類の情報を付加したものである。The font determination unit 5 determines the typeface of the character by a well-known font determination method (for example, by collating with the dictionary of each font and determining the font of the character having the shortest distance). It adds four types of information: body, Gothic, Nar, and textbook.
効果 以上説明したように、本発明は、認識対象文字の認識
結果の文字コードに付加して、元の文章の文字の大きさ
情報や書体の情報を保存して出力することが可能とな
り、認識結果から文章を再生する場合に、ある程度忠実
に再現することが出来るという利点がある。Effect As described above, the present invention makes it possible to store and output the character size information and the typeface information of the original sentence in addition to the character code of the recognition result of the recognition target character. When the text is reproduced from the result, there is an advantage that the text can be reproduced with some fidelity.
第1図は本発明の一実施例の構成を示すブロック図、第
2図は本発明におけるフォント情報付加の説明図、第3
図は従来の文字認識装置の認識結果を説明するための図
である。 1……スキャナー、2……文字切出し部、 3……大きさ判定部、4……特徴抽出部、 5……フォント判定部、6……辞書検索部、 7……結果判定部、8……出力装置、 21……フォント情報、22……文字コード。FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention, FIG. 2 is an explanatory diagram of font information addition in the present invention, and FIG.
FIG. 1 is a diagram for explaining a recognition result of a conventional character recognition device. 1 scanner 2 character cutout unit 3 size determination unit 4 feature extraction unit 5 font determination unit 6 dictionary search unit 7 result determination unit 8 ... output device, 21 ... font information, 22 ... character code.
Claims (2)
り出して文字認識処理を行う文字認識装置における認識
結果出力方法において、予め指定された標準文字サイズ
と、実際に切り出された認識対象文字の文字パターンの
大きさとを比較して対象文字の大きさ情報を得て、この
文字の大きさ情報を認識対象文字の認識結果の文字コー
ドに付加して、元の文書の文字の大きさ情報を保存して
出力することを特徴とする文字認識装置における認識結
果出力方法。1. A recognition result output method for a character recognition apparatus for extracting a character pattern from an input document image and performing a character recognition process, wherein a standard character size specified in advance and a character of a recognition target character actually cut out. Compares the pattern size with the size of the target character to obtain the size information of the target character, adds this size information to the character code of the recognition result of the target character, and saves the size information of the character in the original document And outputting the recognition result in the character recognition device.
た認識対象文字の文字パターンの大きさとを照合して対
象文字の書体情報を得て、この書体情報を認識対象文字
の認識結果の文字コードに付加して、元の文書の書体情
報を保存して出力することを特徴とする特許請求の範囲
(1)記載の文字認識装置における認識結果出力方法。2. A method according to claim 1, wherein a predetermined font dictionary is collated with the size of the character pattern of the character to be recognized which is actually cut out to obtain typeface information of the target character. 2. A method according to claim 1, further comprising storing the typeface information of the original document in addition to the code and outputting the information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP61090037A JP2584973B2 (en) | 1986-04-21 | 1986-04-21 | Recognition result output method in character recognition device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP61090037A JP2584973B2 (en) | 1986-04-21 | 1986-04-21 | Recognition result output method in character recognition device |
Publications (2)
Publication Number | Publication Date |
---|---|
JPS62247485A JPS62247485A (en) | 1987-10-28 |
JP2584973B2 true JP2584973B2 (en) | 1997-02-26 |
Family
ID=13987453
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP61090037A Expired - Fee Related JP2584973B2 (en) | 1986-04-21 | 1986-04-21 | Recognition result output method in character recognition device |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2584973B2 (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01159723A (en) * | 1987-12-16 | 1989-06-22 | Fujitsu Ltd | Hand written character inputting device |
JPH03260886A (en) * | 1990-03-12 | 1991-11-20 | Fuji Facom Corp | Character recognizing method |
JPH0676117A (en) * | 1992-08-25 | 1994-03-18 | Canon Inc | Method and device for processing information |
JP2979109B2 (en) * | 1992-12-03 | 1999-11-15 | 日本アイ・ビー・エム 株式会社 | Recognition character information creating method and apparatus |
JP3362913B2 (en) * | 1993-05-27 | 2003-01-07 | 松下電器産業株式会社 | Handwritten character input device |
US10452904B2 (en) * | 2017-12-01 | 2019-10-22 | International Business Machines Corporation | Blockwise extraction of document metadata |
-
1986
- 1986-04-21 JP JP61090037A patent/JP2584973B2/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
JPS62247485A (en) | 1987-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2584973B2 (en) | Recognition result output method in character recognition device | |
JPH0630910B2 (en) | Printing method | |
KR960010410B1 (en) | Output method and apparatus | |
US5150108A (en) | Method for slanting a generic font format while inserting corrective pixels to improve print quality | |
US5878194A (en) | Method and device for outputting multicolor document | |
JPH0746352B2 (en) | Font conversion method | |
JPH0991371A (en) | Character display device | |
JPS6321158A (en) | Printer output device | |
JP2887928B2 (en) | Image data output device | |
JPS6120887B2 (en) | ||
JP2584973C (en) | ||
JPH07262317A (en) | Document processor | |
JPS61105666A (en) | Document processing device | |
JP2813191B2 (en) | Typeface automatic conversion method | |
JPH0581247A (en) | Method for shaping document | |
JPH09204511A (en) | Filing device | |
JPH0666066B2 (en) | Document processor with furigana addition function | |
JPS60109888A (en) | Character processor | |
KR950011809B1 (en) | Korean character compound writing method in laser printer | |
JPH0371028B2 (en) | ||
JP2745546B2 (en) | Printer device | |
JP3872111B2 (en) | Document creation device | |
JP3054157B2 (en) | Character processing device and character processing method | |
JPS62208090A (en) | Image processor | |
JPH0831092B2 (en) | Document processing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
LAPS | Cancellation because of no payment of annual fees |