JPH0337557U - - Google Patents
Info
- Publication number
- JPH0337557U JPH0337557U JP9917889U JP9917889U JPH0337557U JP H0337557 U JPH0337557 U JP H0337557U JP 9917889 U JP9917889 U JP 9917889U JP 9917889 U JP9917889 U JP 9917889U JP H0337557 U JPH0337557 U JP H0337557U
- Authority
- JP
- Japan
- Prior art keywords
- character
- coordinate
- division
- point determination
- barycenter
- 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.)
- Pending
Links
- 238000000605 extraction Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 238000000034 method Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Landscapes
- Character Discrimination (AREA)
Description
第1図Aは、実施例の文字認識装置の構成を示
すブロツク図、第1図Bは、実施例の分割点決定
部の構成を示すブロツク図、第2図は、従来の文
字認識装置の構成を示すブロツク図、第3図A及
びBは、ストローク位置の違う文字パターンを示
す図、第3図C及びDは、文字パターンをX軸に
投影して得た黒ビツト数分布を示す図、第3図E
及びFは、文字パターンをY軸に投影して得た黒
ビツト数分布を示す図、第4図は、活字文字及び
手書き文字が混在する帳票例を示す図である。
11…光信号、13…前処理部、13a…光電
変換部、13b…パターンレジスタ、13c…文
字切り出し部、17…特徴抽出部、17a…文字
線幅計算部、17b…文字枠検出部、17c…サ
ブパターン抽出部、17d…特徴マトリクス抽出
部、31…書式メモリ部、33…分割点決定部、
33a…第1の分割点決定段、33b…第2の分
割点決定段、33c…切換部、15a…文字投影
作成部、15b…重心検出部、15c…文字枠分
割点決定部。
FIG. 1A is a block diagram showing the configuration of a character recognition device according to an embodiment, FIG. 1B is a block diagram showing a configuration of a dividing point determining section of the embodiment, and FIG. A block diagram showing the configuration, Figures 3A and B are diagrams showing character patterns with different stroke positions, and Figures 3C and D are diagrams showing the distribution of the number of black bits obtained by projecting the character pattern onto the X axis. , Figure 3E
and F are diagrams showing the distribution of the number of black bits obtained by projecting the character pattern onto the Y axis, and FIG. 4 is a diagram showing an example of a form in which printed characters and handwritten characters are mixed. 11... Optical signal, 13... Preprocessing section, 13a... Photoelectric conversion section, 13b... Pattern register, 13c... Character cutting section, 17... Feature extraction section, 17a... Character line width calculation section, 17b... Character frame detection section, 17c ...Sub pattern extraction section, 17d... Feature matrix extraction section, 31... Format memory section, 33... Division point determination section,
33a...First dividing point determining stage, 33b...Second dividing point determining stage, 33c...Switching section, 15a...Character projection creating section, 15b...Gravity center detecting section, 15c...Character frame dividing point determining section.
Claims (1)
て文字パターンを得る前処理部、該文字パターン
を複数の領域に分割するための分割点を決定する
分割点決定部、前記文字パターンの前記分割点に
より分割された各領域毎の特徴量を抽出して被認
識文字の特徴マトリクスを作成する特徴抽出部、
及び、該特徴抽出部で抽出した被認識文字の特徴
と予め用意した標準文字マスクとを照合して被認
識文字を認識する識別部を具える文字認識装置に
おいて、 被認識文字の書式情報を格納する書式メモリ部
を設け、 前記分割点決定部を、前記書式メモリ部から出
力される書式情報に応じて分割点を決定する構成
としたこと を特徴とする文字認識装置。 (2) 前記分割点決定部は、 (a) 文字パターンに外接する文字枠内をX軸
方向についてN均等分割しY軸方向についてM均
等分割する座標を決定する第1の分割点決定段(
但し、N、Mは任意の正の整数)、 (b) 文字パターンをX軸とY軸とに夫々投影
して各々の黒ビツト数分布を求める文字投影作成
部と、 先ず、文字パターンに外接する文字枠の範囲を
対象として前記各黒ビツト数分布の夫々の重心座
標を検出し、次いで、それまでに検出した夫々の
重心座標で前記文字枠を分割し各分割範囲を対象
としてこの範囲の前記黒ビツト数分布の重心座標
を検出する過程を繰り返して夫々の重心座標系列
を検出する重心検出部と、 座標値の大きさの順に付した夫々の重心座標系
列における重心座標番号と座標値の大きさの順に
付したX軸、Y軸の分割座標系列における夫々の
分割座標番号とをほぼ均等に対応させて重心座標
系列における1つの重心座標を1つの分割座標に
対応づけて夫々の分割座標系列を決定する文字枠
分割点決定部と を具える第2の分割点決定段、及び (c) 前記書式メモリ部からの書式情報に応じ
前記第1の分割点決定段及び前記第2の分割点決
定段のうちのいずれかを有効とする切換部 を備えたことを特徴とする請求項1に記載の文
字認識装置。[Claims for Utility Model Registration] (1) A preprocessing unit that photoelectrically converts and quantizes the light from the characters to be recognized to obtain a character pattern, and a division unit that determines division points for dividing the character pattern into a plurality of regions. a point determination unit, a feature extraction unit that extracts feature amounts for each region divided by the division points of the character pattern to create a feature matrix of the character to be recognized;
and a character recognition device comprising an identification unit that recognizes the recognized character by comparing the characteristics of the recognized character extracted by the feature extraction unit with a standard character mask prepared in advance, storing format information of the recognized character. What is claimed is: 1. A character recognition device comprising: a format memory section for determining division points, the division point determining section determining division points according to format information output from the format memory section. (2) The division point determination unit includes: (a) a first division point determination stage (a) for determining coordinates for dividing the character frame circumscribing the character pattern into N equal parts in the X-axis direction and M equal parts in the Y-axis direction;
(N and M are arbitrary positive integers). The barycentric coordinates of each of the black bit number distributions are detected for the range of the character frame to be detected, and then the character frame is divided by the barycenter coordinates detected so far, and the range of this range is calculated for each divided range. a barycenter detection unit that repeats the process of detecting barycenter coordinates of the black bit number distribution to detect each barycenter coordinate series; and a barycenter coordinate number and coordinate value in each barycenter coordinate series assigned in order of the magnitude of the coordinate value The respective divided coordinate numbers in the X-axis and Y-axis divided coordinate series assigned in order of size are almost equally matched, and one barycentric coordinate in the barycenter coordinate series is associated with one divided coordinate, and each divided coordinate is determined. (c) a second division point determination stage comprising a character frame division point determination unit for determining a series; and (c) a character frame division point determination stage that determines the first division point determination stage and the second division according to format information from the format memory unit. The character recognition device according to claim 1, further comprising a switching section that enables one of the point determination stages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP9917889U JPH0337557U (en) | 1989-08-25 | 1989-08-25 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP9917889U JPH0337557U (en) | 1989-08-25 | 1989-08-25 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH0337557U true JPH0337557U (en) | 1991-04-11 |
Family
ID=31648236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP9917889U Pending JPH0337557U (en) | 1989-08-25 | 1989-08-25 |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0337557U (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58123171A (en) * | 1982-01-18 | 1983-07-22 | Oki Electric Ind Co Ltd | Character recognizing system |
| JPS60122474A (en) * | 1983-12-06 | 1985-06-29 | Ricoh Co Ltd | Normalization method |
-
1989
- 1989-08-25 JP JP9917889U patent/JPH0337557U/ja active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58123171A (en) * | 1982-01-18 | 1983-07-22 | Oki Electric Ind Co Ltd | Character recognizing system |
| JPS60122474A (en) * | 1983-12-06 | 1985-06-29 | Ricoh Co Ltd | Normalization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2627928B2 (en) | Image recognition device | |
| JPS5580183A (en) | On-line recognition processing system of hand-written character | |
| JPH0337557U (en) | ||
| JPH0147835B2 (en) | ||
| JPH0147829B2 (en) | ||
| JPH02206894A (en) | Character recognizing method | |
| JPH0547871B2 (en) | ||
| JPH0127474B2 (en) | ||
| JPH0664629B2 (en) | Character recognition method | |
| JPS5837780A (en) | Character recognizing method | |
| JPH10187886A (en) | Character recognition device and character recognition method | |
| JPH0545992B2 (en) | ||
| JPS63233486A (en) | Feature extracting system | |
| JPH0799536B2 (en) | Character figure recognition method | |
| JPS62154079A (en) | Character recognition system | |
| JPH0799534B2 (en) | Character figure recognition method | |
| JPS58178486A (en) | Character recognition device | |
| JP2616995B2 (en) | Character recognition device | |
| JPH0147830B2 (en) | ||
| JPS58123173A (en) | Character recognizing system | |
| JPH0545991B2 (en) | ||
| JPS60201485A (en) | Handwritten character recognizing device | |
| JPH0799535B2 (en) | Character figure recognition method | |
| JPS6318787B2 (en) | ||
| JPS63236182A (en) | Feature extracting system |