JPH039506B2 - - Google Patents
Info
- Publication number
- JPH039506B2 JPH039506B2 JP58081474A JP8147483A JPH039506B2 JP H039506 B2 JPH039506 B2 JP H039506B2 JP 58081474 A JP58081474 A JP 58081474A JP 8147483 A JP8147483 A JP 8147483A JP H039506 B2 JPH039506 B2 JP H039506B2
- Authority
- JP
- Japan
- Prior art keywords
- character
- pattern
- reading
- cutting
- line
- 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
Links
- 238000005520 cutting process Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
Landscapes
- Character Input (AREA)
- Character Discrimination (AREA)
Description
【発明の詳細な説明】
〔発明の技術分野〕
本発明は文字認識装置に係り、特に帳票の搬送
速度の変動等があつても確実に文字認識をおこな
うことのできる文字認識装置に関する。DETAILED DESCRIPTION OF THE INVENTION [Technical Field of the Invention] The present invention relates to a character recognition device, and more particularly to a character recognition device that can reliably perform character recognition even when there are fluctuations in the conveyance speed of documents.
従来の光学的文字認識装置においては帳票の搬
送速度の変動により、文字切出および認識を誤る
場合が少なくなく、特に帳票を搬送面に対し垂直
に保持し搬送をおこなうドキユメント型光学的文
字認識装置では搬送技術上の制約から搬送速度の
変動が大きく問題であつた。搬送速度の変動が大
きいと特に空白（スペース）の切出しおよび認識
が困難であつた。これは速度変動による白部分の
連続と、スペースによる白部分の連続とが区別し
にくいからである。
In conventional optical character recognition devices, there are many cases where characters are cut out and recognized incorrectly due to fluctuations in the conveyance speed of the form, especially in document-type optical character recognition devices that carry the form while holding it perpendicular to the conveyance surface. In this case, fluctuations in conveyance speed were a major problem due to limitations in conveyance technology. When the conveyance speed fluctuates greatly, it is particularly difficult to cut out and recognize blank spaces. This is because it is difficult to distinguish between a series of white parts due to speed fluctuations and a series of white parts due to spaces.
本発明は、上記事情を考慮してなされたもの
で、帳票の搬送速度の変動等があつても正しい文
字切出しおよび認識をすることができる文字認識
装置を提供することを目的とする。
The present invention has been made in consideration of the above circumstances, and it is an object of the present invention to provide a character recognition device that can correctly cut out and recognize characters even when there are fluctuations in the transport speed of documents.
この目的を達成するため本発明による文字認識
装置は、帳票の読取パターンのうち途中に空白が
なに連続文字行について１文字パターンずつ切出
し、この切出し位置と予め定められた仮切出し位
置との平均位置誤差を求め、他の文字行について
予め定められた仮切出し位置を前記平均位置誤差
により修正して他の文字行のパターンを切出すこ
とを特徴とする。
In order to achieve this object, the character recognition device according to the present invention cuts out one character pattern for each continuous character line with blank spaces in the middle of the reading pattern of a form, and averages this cutting position and a predetermined temporary cutting position. The present invention is characterized in that a positional error is determined, and a predetermined tentative cutting position for another character line is corrected by the average position error to cut out a pattern for another character line.
第１図に本発明の一実施例による文字認識装置
を示す。光電変換部１では文字等が記載された帳
票を読取り、２値化する。２値化された読取パタ
ーンは一帳票分がバツフアメモリ２に記憶され
る。制御部４はバツフアメモリ２に記憶された読
取パターンを１文字ずつ切出す他、文字認識装置
全体の制御をするものである。制御部４により切
出された１文字ずつのパターンは文字認識部３で
認識される。
FIG. 1 shows a character recognition device according to an embodiment of the present invention. The photoelectric conversion unit 1 reads a form containing characters and the like and converts it into a binary form. The binarized reading pattern for one form is stored in the buffer memory 2. The control section 4 not only cuts out the reading pattern stored in the buffer memory 2 character by character, but also controls the entire character recognition device. The character recognition unit 3 recognizes the character-by-character pattern cut out by the control unit 4 .
本実施例による文字認識装置は、複数行記載さ
れた帳票を一度に読取り、認識するものである
が、この帳票は、記載された複数行のうち少なく
とも１行は途中に空白白がなく連続して文字等が
記載されているものとする。ここでは例えば帳票
の第１行目にそのような連続文字行があるものと
して説明する。 The character recognition device according to the present embodiment reads and recognizes a form in which multiple lines are written at once, but in this form, at least one line out of the multiple lines written is continuous and has no white space in between. It is assumed that characters, etc. are written on it. Here, explanation will be given assuming that such a continuous character line exists in the first line of the form, for example.
次にこの文字認識装置の動作を第２図、第３図
により説明する。まず外部制御装置５より帳票の
文字行位置や読取開始位置、字種等の読取制御情
報（以下「FC」という）を制御部４が受取る
（ブロツク１１）。次に帳票を１枚フイードして、
第２図に示すようと帳票全体の読取パターンをバ
ツフアメモリ２に格納する（ブロツク１２）。次
に制御部４によりバツフアメモリ廉を走査して帳
票左端アドレスを検出する（ブロツク１３）。さ
らにFCより認識する文字行の各文字位置のアド
レスを計算し、先に求めた帳票左端アドレスを加
え、バツフアメモリ２内のアドレスCA1，CA2，
…，CAo（ｎは文字数）に変換する（ブロツク１
４）。次にブロツク１５で認識すべき文字行が１
行目か否か判断し、１行目の場合はブロツク１６
へ処理が移る。ブロツク１６では、FCにより与
えられた読取開始位置MS1より所定値ｅ前のアド
レスよりバツフアメモリ２を走査し、文字の検
出、切出し動作を開始する。この所定値ｅは帳票
搬送速度誤差、帳票印刷精度等により決定される
値である。文字の検出、切出し動作は、バツフア
メモリ２を走査して黒部分を検出すると、その黒
部分が文字の１部であるか否か判定し、文字であ
れば第１文字目の始まりとして第１文字目の切出
しをおこなう。２文字目以後も同様にして切出し
をおこなう。その後、実際に切出された各文字の
中心位置のアドレスTA1，TA2，…，TAoと先
に計算で求めたアドレスCA1，CA2，…，CAoと
の誤差d1，d2，…，doを求め、その平均値Ｄを次
式により求める。 Next, the operation of this character recognition device will be explained with reference to FIGS. 2 and 3. First, the control section 4 receives reading control information (hereinafter referred to as "FC") such as character line position, reading start position, character type, etc. of the form from the external control device 5 (block 11). Next, feed one sheet of paper,
As shown in FIG. 2, the reading pattern of the entire document is stored in the buffer memory 2 (block 12). Next, the control section 4 scans the buffer memory to detect the left end address of the form (block 13). Furthermore, the address of each character position in the character line recognized by FC is calculated, the previously obtained left end address of the form is added, and the address CA 1 , CA 2 , CA 2 in the buffer memory 2 is calculated.
..., CA o (n is the number of characters) (block 1
4). Next, the number of character lines to be recognized in block 15 is 1.
Determine whether it is the 1st line or not, and if it is the 1st line, block 16
Processing moves to In block 16, the buffer memory 2 is scanned from an address a predetermined value e before the reading start position MS1 given by FC, and character detection and cutting operations are started. This predetermined value e is a value determined based on the form conveyance speed error, form printing accuracy, and the like. In the character detection and cutting operation, when the buffer memory 2 is scanned and a black part is detected, it is determined whether the black part is part of a character or not. Cut out the eyes. Cut out the second and subsequent characters in the same manner. After that, the error d 1 , d between the address TA 1 , TA 2 , ..., TA o of the center position of each character actually cut out and the previously calculated address CA 1 , CA 2 , ..., CA o is calculated. 2 ,...,d o are determined, and the average value D is determined using the following formula.
第２図の場合には計算で求めたアドレスCAiよ
り実際に切出されたアドレスTAiの方が右にずれ
ていることがわかる。次に平均値Ｄを所定のメモ
リに格納し（ブロツク１７）た後、切出された文
字の認識をおこなう（ブロツク１８）。次にブロ
ツク２０で次行があるか否か判断し、あればブロ
ツク１３に処理を移し次行の文字認識をおこな
う。 In the case of FIG. 2, it can be seen that the actually extracted address TA i is shifted to the right from the calculated address CA i . Next, after storing the average value D in a predetermined memory (block 17), the extracted characters are recognized (block 18). Next, in block 20, it is determined whether there is a next line, and if so, the process moves to block 13, where character recognition for the next line is performed.
次行の文字認識はまずFCに従つて各文字位置
の計算上のアドレスCAiを求め（ブロツク１３，
１４）、１行目ではないのでブロツク１８に処理
を移し（ブロツク１５）、各文字位置のアドレス
CAiに先に求めた平均位置誤差Ｄを加えて修正
し、文字の切出しをおこなう。次にその切出した
文字の認識をおこなう（ブロツク１９）。さらに
次行があればブロツク１３に処理を移して（ブロ
ツク２０）、上述した処理を繰り返すが、その帳
票のすべての文字行について認識を終了している
場合はブロツク１２に処理を移して（ブロツク２
０）、新たな帳票について以上の処理を繰り返す。 To recognize the next line of characters, first calculate the calculated address CA i of each character position according to FC (block 13,
14), since it is not the first line, the process is moved to block 18 (block 15), and the address of each character position is
Correct the CA i by adding the previously determined average position error D, and cut out the characters. Next, the cut out characters are recognized (block 19). If there is a next line, the process moves to block 13 (block 20) and the above-mentioned process is repeated; however, if recognition has been completed for all character lines in the form, the process moves to block 12 (block 20). 2
0), repeat the above process for a new form.
このように本実施例によれば、連続文字行の文
字切出しの実際の切出し位置に従つて、他の文字
行の切出し位置を修正することとしているため、
帳票の搬送速度等に変動があつても正しく文字を
切出すことができる。 As described above, according to this embodiment, the cutting positions of other character lines are corrected according to the actual cutting positions of character cutting of continuous character lines.
Characters can be cut out correctly even if there are fluctuations in the transport speed of the form.
なお、文字の検出、切出しについては、バツフ
アメモリを直接走査するのではなく、各文字行の
垂直射影パターンによりおこなつてもよい。 Note that character detection and extraction may be performed using a vertical projection pattern of each character line instead of directly scanning the buffer memory.
また、連続文字行が１行目にない場合は、その
連続文字行から文字の検出、切出しをおこなう必
要があることはいうまでもない。 Furthermore, if there is no continuous character line in the first line, it goes without saying that it is necessary to detect and extract characters from the continuous character line.
以上の通り、本発明によれば、帳票の搬送速度
の変動、帳票における印字または手書文字の位置
変動等があつても、非常に高い精度で文字の切出
し、認識をおこなうことができる。特に空白（ス
ペース）の切出し、認識に有効である。
As described above, according to the present invention, it is possible to cut out and recognize characters with extremely high precision even when there are fluctuations in the transport speed of a form, changes in the position of printed or handwritten characters on a form, and the like. It is particularly effective for cutting out and recognizing blank spaces.
第１図は本発明の一実施例による文字認識装置
のブロツク図、第２図は同装置の読取パターンの
一具体例を示すパターン図、第３図は同装置の動
作を示すフローチヤートである。
１…光電変換部、２…バツフアメモリ、３…文
字認識部、４…制御部、５…外部制御装置。
FIG. 1 is a block diagram of a character recognition device according to an embodiment of the present invention, FIG. 2 is a pattern diagram showing a specific example of a reading pattern of the device, and FIG. 3 is a flowchart showing the operation of the device. . DESCRIPTION OF SYMBOLS 1... Photoelectric conversion part, 2... Buffer memory, 3... Character recognition part, 4... Control part, 5... External control device.
Claims (1)
い連続文字行である複数の文字行が記録された帳
票を読取る読取部と、この読取部により読取られ
た帳票の読取パターンを記憶する記憶部と、この
記憶部に記憶された前記読取パターンの各文字行
のパターンを１文字ずつ切出す切出部と、この切
出部により切出された文字パターンを認識する認
識部とを備えた文字認識装置において、 前記切出部は、前記読取パターンのうち前記連
続文字行について１文字パターンずつ切出し、こ
の切出し位置と予め定められた仮切出し位置との
平均位置誤差を求め、他の文字行について予め定
められた仮切出し位置を前記平均位置誤差により
修正して他の文字行のパターンを切出すことを特
徴とする文字認識装置。[Scope of Claims] 1. A reading section for reading a document in which at least one character line is a continuous character line with no spaces in between, and a reading pattern of the document read by the reading section. a storage section for storing, a cutting section for cutting out the pattern of each character line of the reading pattern stored in the storage section one character at a time, and a recognition section for recognizing the character pattern cut out by the cutting section; In the character recognition device, the cutting unit cuts out each character pattern of the continuous character lines from the reading pattern, calculates an average positional error between this cutting position and a predetermined temporary cutting position, and performs other operations. A character recognition device characterized in that a predetermined temporary cutting position for a character line is corrected by the average position error to cut out patterns of other character lines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP58081474A JPS59206987A (en) | 1983-05-10 | 1983-05-10 | Letter recognizing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP58081474A JPS59206987A (en) | 1983-05-10 | 1983-05-10 | Letter recognizing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS59206987A JPS59206987A (en) | 1984-11-22 |
| JPH039506B2 true JPH039506B2 (en) | 1991-02-08 |
Family
ID=13747396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP58081474A Granted JPS59206987A (en) | 1983-05-10 | 1983-05-10 | Letter recognizing device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS59206987A (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH065551B2 (en) * | 1986-11-12 | 1994-01-19 | 三洋電機株式会社 | Print character recognition method |
| JPS6419488A (en) * | 1987-07-15 | 1989-01-23 | Nec Corp | Type recognizing device |
-
1983
- 1983-05-10 JP JP58081474A patent/JPS59206987A/en active Granted
Also Published As
| Publication number | Publication date |
|---|---|
| JPS59206987A (en) | 1984-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20070230784A1 (en) | Character string recognition method and device | |
| JPS6115284A (en) | Optical character reader | |
| JPH039506B2 (en) | ||
| JPH0340430B2 (en) | ||
| JPS58186261A (en) | Facsimile device | |
| JPH0557632B2 (en) | ||
| JPH0373916B2 (en) | ||
| JPS6027083A (en) | Optical character reader | |
| JPH036552B2 (en) | ||
| JPH11250179A (en) | Character reocognition device and its method | |
| JPH0782524B2 (en) | Optical character reader | |
| JP3022655B2 (en) | Character recognition device | |
| JP2506142B2 (en) | Character reader | |
| JPS5860381A (en) | Skew detecting system | |
| JPH07192087A (en) | Optical character reader | |
| JPS6139172A (en) | Character detecting and cutting out system | |
| JP2570571B2 (en) | Optical character reader | |
| JP2812392B2 (en) | Character processing apparatus and method | |
| JPS59128677A (en) | Optical character reader | |
| JP3047857B2 (en) | Optical character reader | |
| JPH0696273A (en) | Recognition field retrieving method in business form reader | |
| JP2925270B2 (en) | Character reader | |
| JPH0426153B2 (en) | ||
| JPH0437969A (en) | Optical character reader | |
| JPH04195274A (en) | Document terminal detecting method for optical character reader |