JPS62196778A - Graphic separating device - Google Patents

Graphic separating device

Info

Publication number
JPS62196778A
JPS62196778A JP61038168A JP3816886A JPS62196778A JP S62196778 A JPS62196778 A JP S62196778A JP 61038168 A JP61038168 A JP 61038168A JP 3816886 A JP3816886 A JP 3816886A JP S62196778 A JPS62196778 A JP S62196778A
Authority
JP
Japan
Prior art keywords
black
pattern
graphic pattern
black pixels
picture elements
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.)
Granted
Application number
JP61038168A
Other languages
Japanese (ja)
Other versions
JPH0816920B2 (en
Inventor
Masahisa Yano
矢野 雅久
Kenichiro Uchimura
内村 憲一朗
Yoshiyuki Yamashita
山下 義征
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.)
Oki Electric Industry Co Ltd
Original Assignee
Oki Electric Industry Co Ltd
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 Oki Electric Industry Co Ltd filed Critical Oki Electric Industry Co Ltd
Priority to JP61038168A priority Critical patent/JPH0816920B2/en
Publication of JPS62196778A publication Critical patent/JPS62196778A/en
Publication of JPH0816920B2 publication Critical patent/JPH0816920B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Abstract

PURPOSE:To extract all of continuous graphic by extracting black picture elements that continue more than specified number in horizontal (or vertical) direction from a binary picture image converted from an input picture image in which graphics, characters and symbols are mixed, and further extracting black elements and continuous black picture elements to all directions. CONSTITUTION:A black run deciding section 3 counts the number of continuous black picture elements in binary image data D1 and when it becomes a predetermined threshold value or above, outputs black picture elements, and when less than the threshold level, outputs white picture elements and forms a temporary graphic pattern D2. A graphic pattern memory 4 stores the temporary graphic pattern D2 and a graphic pattern. A black connecting and propagating section 5 scans the graphic pattern memory 4 and an original pattern memory 2 synchronously by a window having proper size, and extracts black picture elements in the binary picture image data D1 adjoining black picture elements of the temporary graphic pattern D2 and continuing black picture elements of all directions successively, and outputs them to the graphic pattern memory 4 as a graphic pattern D3.

Description

【発明の詳細な説明】 (産業上の利用分野) 本発明は、図形1文字、記号等が混在する入力画像より
図形のみを含む図形パタン、もしくは該図形パタンと文
字、記号等を含む文字パタンとを分l1ll[シ抽出す
る装置に関するものである。
Detailed Description of the Invention (Industrial Field of Application) The present invention is capable of generating a graphic pattern containing only a figure from an input image containing a mixture of figures, characters, symbols, etc., or a character pattern containing the figure pattern and characters, symbols, etc. This relates to a device that extracts

(従来の技術) 図形1文字、記号等が混在する入力画像を効率良く認識
しようとする場合、認識!i!II理に先だって、図形
と、文字、記号等(以下、文字等と称す。)とを分離J
る必要がある。
(Prior art) When trying to efficiently recognize an input image containing a mixture of figures, characters, symbols, etc., recognition! i! II Prior to the process, separate figures from characters, symbols, etc. (hereinafter referred to as characters, etc.).
It is necessary to

従来、この種の装置では、[文字等は閉ループ図形の内
側に書り」というような、図形と文字等との相対位置関
係を記入制限条項とし、記入制限条項そのものを図形と
文字等との分離・抽出の論理として図形と文字等とを分
離・抽出し、あるいは色水 他著「図面に出かれた文字
の一処理方式j(昭和52年度電子通信学会情報部門全
国大会論文集、173)に記載されたように「一定以下
の大きさの孤立図形jのみを文字等どして、図形と文字
等とを分離・抽出する如くなしでいた。
Conventionally, in this type of device, the writing restriction clause is based on the relative positional relationship between the figure and the character, such as ``write the text inside the closed-loop figure,'' and the writing restriction clause itself is defined as the relationship between the figure and the text. The logic of separation and extraction is to separate and extract figures and characters, or by Shikisui et al., "One Processing Method for Characters Appearing in Drawings" (Proceedings of the 1973 National Conference of the Information Division of the Institute of Electronics and Communication Engineers, 173). As described in ``The conventional method was to separate and extract figures and characters by converting only isolated figures j of a certain size or less into letters, etc.

(発明が解決しようとする問題点) しかしながら、前者の装置では、融通性がなく認識対象
画像が限定きれると共に、記入制限事項を守ることは記
入者にとって困難であり、実用的でなく、また、後者の
装置では、文字と文字との接触等により、分離対象の孤
立図形の大きさが一定以上となった場合、文字等として
分離不可能であり、また、孤立図形を抽出するための手
段が複雑となる等の問題点があった。
(Problems to be Solved by the Invention) However, with the former device, there is no flexibility and images to be recognized are limited, and it is difficult for the filler to comply with entry restrictions, making it impractical. In the latter device, if the size of the isolated figure to be separated exceeds a certain level due to contact between characters, it is impossible to separate the isolated figure as a character, etc., and there is no means for extracting the isolated figure. There were problems such as complexity.

本発明は前記問題点を除去し、梱形のみを含む図形パタ
ン、もしくは該図形パタンと文字等を含む文字パタンと
を、簡単1つ確実に分離・抽出し得る装置を提供するこ
とを目的とする。
SUMMARY OF THE INVENTION An object of the present invention is to eliminate the above-mentioned problems and provide an apparatus that can easily and reliably separate and extract a graphic pattern containing only a packaging shape, or a character pattern containing characters and the like from the graphic pattern. do.

(問題点を解決するための手段) 前記問題点を解決するため、゛第1の発明では図形1文
字、記号等が混在Jる入力画像を2hffiiiiii
象に変換する第1の手段と、前記2値画像中より水平(
又は垂直)方向に所定数以上連続する黒画素を抽出し、
板間形パタンを作成する第2の手段と、前記2値画像中
より、njI記仮図仮図タン内の黒画素に隣接する黒画
素およびこれに連続するあらゆる方向の黒画素を抽出し
、これら全ての黒画素より図形パタンを作成する第3の
手段とを備え、また、第21!明では前記第1.第2お
よび第3の手段に加えて、前記2値画像中の黒画素のう
ら、前記図形パタン中に存在する黒画素を取除き、文字
(Means for Solving the Problem) In order to solve the above problem, in the first invention, an input image containing a mixture of figures, characters, symbols, etc.
a first means for converting into a horizontal image (
Extract a predetermined number or more consecutive black pixels in the (or vertical) direction,
a second means for creating an inter-board shape pattern; extracting from the binary image black pixels adjacent to black pixels in the njI-written temporary map and black pixels in all directions continuous thereto; A third means for creating a figure pattern from all these black pixels, and a twenty-first! In Akira, the above-mentioned 1. In addition to the second and third means, black pixels existing in the graphic pattern behind the black pixels in the binary image are removed to form characters.

記号等を含む文字パタンを作成する第4の手段とを備え
た。
and fourth means for creating a character pattern including symbols and the like.

(作用) 第1発明によれば、図形1文字、記号等が混在する入力
画像を変換しIC2値画像より、水平(又は垂直)方向
に所定数以上連続する黒画素を抽出することにより、図
形の一部が抽出され、さらに2値画像中より図形の一部
に相当する黒画素に隣接する黒画素およびこれに連続す
るあらゆる方向の黒画素を抽出することにより、前記抽
出した図形の一部に連続する図形の全てが抽出され、ま
た、第2発明によれば、前記2値画像中より前記図形と
して抽出された黒画素を取除くことにより、文字、記号
等が抽出される。
(Operation) According to the first invention, by converting an input image containing a mixture of graphic characters, symbols, etc., and extracting a predetermined number or more consecutive black pixels in the horizontal (or vertical) direction from the IC binary image, A part of the figure is extracted, and by further extracting black pixels adjacent to the black pixel corresponding to a part of the figure from the binary image and black pixels in all directions continuous to this, the part of the extracted figure is extracted. According to the second invention, characters, symbols, etc. are extracted by removing black pixels extracted as the figures from the binary image.

(実施例) まず、本発明の考え方を第2図(a)につい′C説明す
る。図中、10は図形や文字等が混在する入力画像、例
えば論理回路図を含む図面であり、また図面10中、1
1は抵抗、アンド回路等を示すシンボル、12は信号線
、13は文字等である。
(Example) First, the concept of the present invention will be explained with reference to FIG. 2(a). In the figure, 10 is a drawing including an input image containing a mixture of figures, characters, etc., for example, a logic circuit diagram, and in the drawing 10, 1
1 is a symbol indicating a resistor, an AND circuit, etc., 12 is a signal line, and 13 is a letter, etc.

各シンボル11は通常、信号FA12にて互いに連結さ
れており、その一部に必ず一定の長さ、例えばし5以上
の水平方向の線分を右している。これに対して、文字等
13にお番ノろ水平方向の線分の長さは、2つ又はそれ
以−ヒの文字等同士が接触した場合においてら前記長さ
Lt以上になることははとIνどない。また通常、文字
等13はシンボル11および信号線12より、やや離れ
た所に記入されている。
The symbols 11 are usually connected to each other by a signal FA12, and each symbol 11 always has a horizontal line segment of a certain length, for example, five or more, in a part thereof. On the other hand, the length of the horizontal line segment of the character 13 cannot exceed the above length Lt even when two or more characters, etc. touch each other. And what about Iν? Further, normally, the characters etc. 13 are written at a location slightly apart from the symbol 11 and the signal line 12.

従って、図面10中より前記長さLt以上の水平方向の
線分を検出し、その線分と連結している線分のみを抽出
することによって、信号線12およびシンボル11のみ
を抽出する、即ら図形と文字等とを分離することが可能
となる。
Therefore, it is possible to extract only the signal line 12 and the symbol 11 by detecting a horizontal line segment having the length Lt or more in the drawing 10 and extracting only the line segment connected to the line segment. This makes it possible to separate figures and characters.

第1図は本発明の一実施例を示すもの−C1図中、1は
画像入力部、2はオリジナルパタンメモリ、3は黒ラン
判定部、4は図形パタンメモリ、5は黒連結伝幅部、6
は文字パタン抽出部である。
Fig. 1 shows an embodiment of the present invention - In Fig. C1, 1 is an image input section, 2 is an original pattern memory, 3 is a black run determination section, 4 is a figure pattern memory, and 5 is a black connection propagation section. ,6
is a character pattern extraction part.

画像入力部1は、図形や文字等がi1N在する入力画像
、例えば前記図面10を光電変換し、第2図(b)に示
す走査方向■に沿ってラスタ走査し、2値画像データD
1を出力する。
The image input unit 1 photoelectrically converts an input image containing i1N figures, characters, etc., for example, the drawing 10, raster scans it along the scanning direction (■) shown in FIG. 2(b), and converts it into binary image data D.
Outputs 1.

オリジナルパタンメモリ2は、前記2値画像データD1
を前記ラスタ走査ど同期して記憶づ−る如くなっている
The original pattern memory 2 stores the binary image data D1.
is stored in synchronization with the raster scanning.

黒ラン判定部3は、前記2値画像データD1中の連続し
た黒画素数を計数し、予め定められた閾値以上どなった
場合は黒画素を出力し、閾値未満の場合は白画素を出力
し、敗因形パタンD2を作成する。
The black run determination unit 3 counts the number of consecutive black pixels in the binary image data D1, and outputs a black pixel if it is equal to or greater than a predetermined threshold, and outputs a white pixel if it is less than the threshold. Then, a losing cause pattern D2 is created.

図形パタンメモリ4は、前記敗因形パタンD2と、後述
づる図形パタンを記憶する。
The graphic pattern memory 4 stores the defeat pattern D2 and a graphic pattern to be described later.

黒連結伝幅部5は、適当な大きさのウィンドで図形パタ
ンメモリ4とオリジナルパタンメモリ2とを同期して走
査することによって、敗因形パタンD2の黒画素に隣接
する2111ijiii像データ1〕1中の黒画素およ
びこれに連続するあらゆる方向の黒画素を順次抽出し、
図形パタンD3として図形パタンメモリ4に出力する如
くなっている。
The black connection propagation unit 5 scans the graphic pattern memory 4 and the original pattern memory 2 in synchronization with a window of an appropriate size, thereby obtaining the 2111 ijiii image data 1]1 adjacent to the black pixel of the defeated pattern D2. Sequentially extract the black pixels in the middle and the black pixels that follow this in all directions,
The pattern is outputted to the graphic pattern memory 4 as a graphic pattern D3.

文字パタンメモリ6は、オリジナルパタンメモリ2と前
記図形パタンD3が格納された図形パタンメモリ4とを
同期して走査し、1qられるデータ同士の間で排他的論
理和をとって、文字等を含む文字パタンD4を出力する
The character pattern memory 6 scans the original pattern memory 2 and the graphic pattern memory 4 in which the graphic pattern D3 is stored in synchronization, performs an exclusive OR between the 1q data, and selects a pattern containing characters, etc. Output character pattern D4.

次に細部の構成、動作について説明する。Next, the detailed configuration and operation will be explained.

黒ラン判定部3は、連続する黒画素数の個数を計数りる
t1数手段(以下、黒ラン計数器と称す、、)を内蔵し
、第3図に示す動作の流れ図に従って、2値画像データ
D1のうち、図形の一部である黒画素のみを抽出し、図
形パタンメモリ4へ格納する。
The black run determination unit 3 has a built-in t1 number means (hereinafter referred to as black run counter) for counting the number of consecutive black pixels, and calculates a binary image according to the operation flowchart shown in FIG. Of the data D1, only black pixels that are part of the figure are extracted and stored in the figure pattern memory 4.

まず、2値画像データD1が白画素の場合、黒ラン計数
器をリセットするとともに、敗因形パタンD2として白
画素を出力する(81〜33)。
First, when the binary image data D1 is a white pixel, the black run counter is reset, and the white pixel is output as the failure pattern D2 (81 to 33).

2値画像データD1が黒画素の揚台、黒ラン計数器をカ
ウントアツプ(+1)L、(34)、その際の黒ラン計
数器の計数値が予め定められた閾値、例えば前記長さし
 に対応するり未満の場合、を 板間形パタンO2として白画素を出力でる(S5゜33
)。黒ラン計数器の計数値が閾値l0以上になった場合
は、敗因形パタンD2として黒画素を出力する(S6)
When the binary image data D1 is a black pixel platform, the black run counter counts up (+1) L, (34), and the count value of the black run counter at that time is set to a predetermined threshold, for example, the length If the value is less than or equal to , a white pixel is output as the plate pattern O2 (S5゜33
). When the count value of the black run counter exceeds the threshold l0, black pixels are output as the defeat pattern D2 (S6).
.

ここで閾値へ (長さLL)は、図面10に記入される
文字の横幅の最大値と、図形に存在する水平線分の長さ
の最小値で決まる値である。
Here, the threshold (length LL) is a value determined by the maximum width of characters written in drawing 10 and the minimum length of horizontal line segments existing in the figure.

第4図は、2値画像データD1と敗因形パタンD2との
対応を示すもので、ここでは閾htJI−よ便宜上「1
0」に設定しである。図中、2値画像データD1におけ
る白画素はO印、黒画素は・印および■印で示し、敗因
形パタンD2における白画素はO印および・印、黒画素
は[相]印で示ず。
FIG. 4 shows the correspondence between the binary image data D1 and the losing cause pattern D2.
0". In the figure, white pixels in the binary image data D1 are indicated by O marks, black pixels are indicated by * marks and ■ marks, white pixels in the defeat pattern D2 are shown by O marks and * marks, and black pixels are not shown by [phase] marks. .

黒連結伝幅部5は、第5図(a)〜(d)に示すような
(2X2)画素のウィンド(以下、単にウィンドと称す
。)5aを右し、該ウィンド5aで図形パタンメモリ4
とオリジナルパタンメモリ2上を、第5図(a)〜(d
)に示す走査方向◎、■、■。
The black connection propagation unit 5 has a (2×2) pixel window (hereinafter simply referred to as a window) 5a as shown in FIGS. 5(a) to 5(d), and the graphic pattern memory 4
and on the original pattern memory 2 in Figs. 5(a) to (d).
) Scanning direction shown in ◎, ■, ■.

■の順に走査し、後述する如くして板間形パタンD2中
の黒画素に隣接する2値画像データD1上の黒画素を検
出し、順次、図形パタンメモリ4に格納する。
Scanning is performed in the order of (2), and as will be described later, black pixels on the binary image data D1 adjacent to black pixels in the interboard pattern D2 are detected and sequentially stored in the graphic pattern memory 4.

まず、図形パタンメモリ4上におかれたウィンド5a内
に黒画素が存在するか盃か、即ち下記式(1)をi!2
寸かどうかを調べ、満たさない場合は走査を進め、満た
づ場合tよオリジナルパタンメモリ2上のウィンド5a
内の黒画素が存在する桝に対応した図形パタンメモリ4
上のウィンド5aの桝を黒画素とする、即ち下記式(2
)の処理を行なう。
First, whether there are black pixels in the window 5a placed on the graphic pattern memory 4 or not, that is, the following equation (1) is expressed as i! 2
If the size is not satisfied, the scanning is continued, and if it is, the window 5a on the original pattern memory 2 is checked.
Figure pattern memory 4 corresponding to the cell in which the black pixel exists
The square of the upper window 5a is assumed to be a black pixel, that is, the following formula (2
).

Z (x、y)=R(x、y)    ・・・・・・・
・・(2)前記式(1) 、 (2)において、X、y
はウィンド5a内の座標であり、その値は1又は2、Z
 (x。
Z (x, y) = R (x, y) ・・・・・・
...(2) In the above formulas (1) and (2), X, y
is the coordinate within the window 5a, and its value is 1 or 2, Z
(x.

yHよ図形パタンメモリ4上におかれたウィンド5aの
各座標点の値であって黒画素の時に11」、白画素の時
に「O」である。@ (x、y)はオリジナルパタンメ
モリ2上におかれたウィンド5aの各座標点の値であっ
て黒画素の時に「1」、白画素の時に「0」である。
yH is the value of each coordinate point of the window 5a placed on the graphic pattern memory 4, which is 11'' for a black pixel and ``O'' for a white pixel. @(x, y) is the value of each coordinate point of the window 5a placed on the original pattern memory 2, and is "1" for a black pixel and "0" for a white pixel.

第6図(a)〜(C)は黒連結伝幅部5のv1作のにう
すを示すものである。第6図(a)はある時点における
図形パタンメモリ4上のウィンド5a内の内容20を示
し、また、第6図(b)は同一時点におけるオリジナル
パタンメモリ2上のウィンド5a内の内容30を示す。
FIGS. 6(a) to 6(C) show the v1 construction of the black connecting transmission portion 5. 6(a) shows the contents 20 in the window 5a on the figure pattern memory 4 at a certain point in time, and FIG. 6(b) shows the contents 30 in the window 5a in the original pattern memory 2 at the same point in time. show.

この際、内容21内の黒画素21 (x=1.y=1)
に対し、内容30内の黒画素31 (x=2.y=1)
が隣接しl’ J3す、さらにこの黒画素31に黒画素
32 (x=2.y−2)が隣接しているため、図形パ
タンメモリ4上の内容20は、第6図(C)に示すよう
に画素22 (x=2.V=1 )と画素23 (x=
2.y・・2)の点が黒画素に変換される。
At this time, black pixel 21 in content 21 (x=1.y=1)
For, black pixel 31 in content 30 (x=2.y=1)
Since the black pixel 32 (x=2.y-2) is adjacent to the black pixel 31, the contents 20 on the figure pattern memory 4 are as shown in FIG. 6(C). As shown, pixel 22 (x=2.V=1) and pixel 23 (x=
2. The point y...2) is converted to a black pixel.

第7図は黒連結伝幅部5によって青られた図形パタンの
一例を示ず。図中、○印は白画素、■印は黒ラン判定部
3にJ:って仮図形パタンとして抽出された黒画素、k
印は第6図における走査方向◎の走査によって抽出され
た黒画素、4印は走査方向■の走査によって抽出された
黒画素である。
FIG. 7 does not show an example of a graphic pattern colored blue by the black connection propagation portion 5. In the figure, the ○ mark is a white pixel, the black pixel is a black pixel extracted as a temporary figure pattern by the black run determination unit 3, and k
The marks are black pixels extracted by scanning in the scanning direction ◎ in FIG. 6, and the 4 marks are black pixels extracted by scanning in the scanning direction ■.

なお、前記走査方向@の走査と、画像入力部1にJハブ
る走査とを同時に行なうことによって処理時間の短縮を
図ることができる。
Note that by simultaneously performing the scanning in the scanning direction @ and the scanning in the image input section 1, the processing time can be shortened.

文字パタン抽出部6は、黒連結伝幅部5の処理の終了後
、オリジナルパタンメモリ2と図形パタンメモリ4とを
同期して走査し、得られたデータをデータ毎に梼他的論
理和の演算を論ずことによって文字パタンD4を抽出す
る。
After the processing of the black connection propagation section 5 is completed, the character pattern extraction section 6 synchronously scans the original pattern memory 2 and the graphic pattern memory 4, and performs a transversal OR on the obtained data for each data. Character pattern D4 is extracted by discussing the calculation.

(発明の効果) 以上説明したように第1発明によれば、従来のように文
字等の記入制限条項を設ける必要がなく、文字等の大き
さにもあまり左右されずに図形のみを含む図形パタンを
抽出でき、また、第2発明によれば、図形パタンととも
に文字等を含む文字パタンを抽出でき、安価″c確実な
図形分離装置を提供できる等の利点がある。
(Effects of the Invention) As explained above, according to the first invention, there is no need to set restrictions on the entry of characters, etc., as in the past, and figures containing only figures are not affected much by the size of characters, etc. Further, according to the second invention, character patterns including characters and the like can be extracted together with graphic patterns, and there are advantages such as being able to provide an inexpensive and reliable graphic separation device.

【図面の簡単な説明】[Brief explanation of drawings]

第1図は本発明の図形分離装置の一実施例を示す構成図
、第2図(a)(b)は入力図面の一例とその走査方向
を示す図、第3図は黒ラン判定部の動作の流れ図、第4
図は2値画像データと仮図形パタンとの対応を示す図、
第5図(a)〜(d)は黒連結伝幅部における走査方向
を示す図、第6図(a)〜(C)は図形パタンへの変換
のよう−りを示す図、第7図は抽出された図形パタンの
一例を示す図である。 1・・・画像入力部、2・・・オリジナルパタンメモリ
、3・・・黒ラン判定部、4・・・図形パタンメモリ、
5・・・黒連結伝幅部、6・・・文字パタン抽出部。 特許出願人 沖電気工業株式会社 代理人弁理士 古  1) 精  4 第1図 (a) 入力図面の一例とその走査方向を示す図へ32図 第3図 oOoOooooooooooooOoO・・ooo。 00000oOoooOooo00oOo・・ooo。 2値画像テ―りと敗因形A?ンとの月応牙示す図第4図 ooooooooooooo oooooo44<II
ooo。 第7図
FIG. 1 is a block diagram showing an embodiment of the figure separation device of the present invention, FIGS. 2(a) and 2(b) are diagrams showing an example of an input drawing and its scanning direction, and FIG. 3 is a diagram showing an example of an input drawing and its scanning direction. Operation flowchart, 4th
The figure shows the correspondence between binary image data and temporary figure patterns.
Figures 5 (a) to (d) are diagrams showing the scanning direction in the black connection propagation section, Figures 6 (a) to (C) are diagrams showing how it is converted into a figure pattern, and Figure 7. FIG. 2 is a diagram showing an example of an extracted graphic pattern. 1... Image input section, 2... Original pattern memory, 3... Black run determination section, 4... Graphic pattern memory,
5...Black connection width part, 6...Character pattern extraction part. Patent applicant Oki Electric Industry Co., Ltd. Patent attorney Furu 1) Sei 4 Figure 1 (a) To the diagram showing an example of the input drawing and its scanning direction Figure 32 oOoOooooooooooooooooooo...ooo. 00000oOoooOooo00oOo...ooo. Binary image style and defeat form A? Diagram 4 showing the monthly relationship with N
ooooo. Figure 7

Claims (2)

【特許請求の範囲】[Claims] (1)図形、文字、記号等が混在する入力画像を2値画
像に変換する第1の手段と、 前記2値画像中より水平(又は垂直)方向に所定数以上
連続する黒画素を抽出し、仮図形パタンを作成する第2
の手段と、 前記2値画像中より、前記仮図形パタン内の黒画素に隣
接する黒画素およびこれに連続するあらゆる方向の黒画
素を抽出し、これら全ての黒画素より図形のみを含む図
形パタンを作成する第3の手段と を備えたことを特徴とする図形分離装置。
(1) A first means for converting an input image containing a mixture of figures, characters, symbols, etc. into a binary image, and extracting a predetermined number or more consecutive black pixels in the horizontal (or vertical) direction from the binary image. , the second step to create a temporary figure pattern.
means for extracting from the binary image black pixels adjacent to the black pixels in the temporary figure pattern and black pixels in all directions continuous thereto, and forming a figure pattern containing only figures from all these black pixels; A figure separation device characterized by comprising: third means for creating.
(2)図形、文字、記号等が混在する入力画像を2値画
像に変換する第1の手段と、 前記2値画像中より水平(又は垂直)方向に所定数以上
連続する黒画素を抽出し、仮図形パタンを作成する第2
の手段と、 前記2値画像中より、前記仮図形パタン内の黒画素に隣
接する黒画素およびこれに連続するあらゆる方向の黒画
素を抽出し、これら全ての黒画素より図形のみを含む図
形パタンを作成する第3の手段と、 前記2値画像中の黒画素のうち、前記図形パタン中に存
在する黒画素を取除き、文字、記号等を含む文字パタン
を作成する第4の手段と を備えたことを特徴とする図形分離装置。
(2) A first means for converting an input image containing a mixture of figures, characters, symbols, etc. into a binary image, and extracting a predetermined number or more consecutive black pixels in the horizontal (or vertical) direction from the binary image. , the second step to create a temporary figure pattern.
means for extracting from the binary image black pixels adjacent to the black pixels in the temporary figure pattern and black pixels in all directions continuous thereto, and forming a figure pattern containing only figures from all these black pixels; and a fourth means for removing black pixels existing in the graphic pattern from among the black pixels in the binary image to create a character pattern including characters, symbols, etc. A figure separation device characterized by comprising:
JP61038168A 1986-02-25 1986-02-25 Figure separation device Expired - Lifetime JPH0816920B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP61038168A JPH0816920B2 (en) 1986-02-25 1986-02-25 Figure separation device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP61038168A JPH0816920B2 (en) 1986-02-25 1986-02-25 Figure separation device

Publications (2)

Publication Number Publication Date
JPS62196778A true JPS62196778A (en) 1987-08-31
JPH0816920B2 JPH0816920B2 (en) 1996-02-21

Family

ID=12517867

Family Applications (1)

Application Number Title Priority Date Filing Date
JP61038168A Expired - Lifetime JPH0816920B2 (en) 1986-02-25 1986-02-25 Figure separation device

Country Status (1)

Country Link
JP (1) JPH0816920B2 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS57211674A (en) * 1981-06-23 1982-12-25 Ricoh Co Ltd Frame recognizing method
JPS58163076A (en) * 1982-03-23 1983-09-27 Fujitsu Ltd Extracting system of character region
JPS59788A (en) * 1982-06-28 1984-01-05 Nippon Telegr & Teleph Corp <Ntt> Figure processing system distinguishing character region from figure region
JPS5971583A (en) * 1982-09-25 1984-04-23 Fujitsu Ltd Character string extracting system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS57211674A (en) * 1981-06-23 1982-12-25 Ricoh Co Ltd Frame recognizing method
JPS58163076A (en) * 1982-03-23 1983-09-27 Fujitsu Ltd Extracting system of character region
JPS59788A (en) * 1982-06-28 1984-01-05 Nippon Telegr & Teleph Corp <Ntt> Figure processing system distinguishing character region from figure region
JPS5971583A (en) * 1982-09-25 1984-04-23 Fujitsu Ltd Character string extracting system

Also Published As

Publication number Publication date
JPH0816920B2 (en) 1996-02-21

Similar Documents

Publication Publication Date Title
US7170647B2 (en) Document processing apparatus and method
JP2001109844A (en) Character string extracting method, handwritten character extracting method, character string extraction device, and image processor
JPH0721310A (en) Document recognizing device
EP2166741A1 (en) Image processing apparatus, image forming apparatus and program
JP3936436B2 (en) Table recognition method
JPS62196778A (en) Graphic separating device
JPH06187489A (en) Character recognizing device
JP2558668B2 (en) Character pattern extraction method
JPS63304387A (en) Document reader
JP4763113B2 (en) High speed labeling method
JPH0916713A (en) Image area dividing method
JPH02273884A (en) Detecting and correcting method for distortion of document image
JPH03142691A (en) Table format document recognizing system
JPS62202287A (en) Graphic separating device
JP3275475B2 (en) Character string recognition device with known character sequence
JP2789622B2 (en) Character / graphic area determination device
JPH05274472A (en) Image recognizing device
JPH0660220A (en) Area extracting method for document image
JP2586117B2 (en) Character recognition device
JPS6327752B2 (en)
JPH0560876B2 (en)
US6142374A (en) Optical character reader
JPH08321942A (en) Image processing unit and method for linking image of split pattern
JP2929919B2 (en) Optical character extraction device
JPH02187883A (en) Document reader