JPS58191078A - Display system for recognition result of character - Google Patents

Display system for recognition result of character

Info

Publication number
JPS58191078A
JPS58191078A JP57072874A JP7287482A JPS58191078A JP S58191078 A JPS58191078 A JP S58191078A JP 57072874 A JP57072874 A JP 57072874A JP 7287482 A JP7287482 A JP 7287482A JP S58191078 A JPS58191078 A JP S58191078A
Authority
JP
Japan
Prior art keywords
characters
character
register
read
value
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
Application number
JP57072874A
Other languages
Japanese (ja)
Inventor
Norio Kanemitsu
憲雄 金光
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.)
Fujitsu Ltd
Original Assignee
Fujitsu 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 Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP57072874A priority Critical patent/JPS58191078A/en
Publication of JPS58191078A publication Critical patent/JPS58191078A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/98Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/987Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns with the intervention of an operator

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Character Discrimination (AREA)

Abstract

PURPOSE:To aviod the fear for rereading or the reduction of efficiency, by comparing the reading factor to compare this measured value with the reference value which is set previously and then displaying whether this reference value is satisifed or not. CONSTITUTION:When the characters on a slip are read at a character recognizing part 1, the character codes corresponding to the read characters are written to a memory 2. At the same time, a rejection code is written to the memory 2 for an unreadable character. When the moemry 2 receives character codes equivalent to a sheet of slip, an MPU 3 writes the number of read characters and the number of unreadable characters to a character number recording part 4 and then calculates the reading factor to write it to a register 5. An operator writes a proper reading factor to a register 6. The value of the register 5 is compared with the value of the register 6 through a comparator 8. Then an information signal is fed to a display part 9 to show whether or not the reading factor of the register 5 satisfies the proper value.

Description

【発明の詳細な説明】 (1)発明の技術分野 本発明は光学式文字読取装置(OptlcalChar
aeter  Reader :以下OCRと呼ぶ)に
おいて、読み取るべき文字数に対する読み取った文字数
の割合(読取率という)を計測し、その計測値が基準を
越えているか否かを表示する文字認識結果表示方式に関
するものである。
Detailed Description of the Invention (1) Technical Field of the Invention The present invention relates to an optical character reading device (OptlcalChar).
Aeter Reader (hereinafter referred to as OCR) relates to a character recognition result display method that measures the ratio of the number of characters read to the number of characters to be read (referred to as reading rate) and displays whether the measured value exceeds a standard. be.

(2)技術の背景 OCRは事務処理の機械化の一つとして、伝票等の書類
に記載された文字を光学的に読み取る装置である。そし
て読み取るべき文字は手書きの場合と活字の場合の両者
がある。
(2) Background of the technology OCR is a device that optically reads characters written on documents such as slips, as part of the mechanization of office processing. The characters to be read can be both handwritten and printed.

前者の例としては郵便番号の記載があり、後者の例とし
ては公共機関での市民等多数の処理を要する例えば税や
水道料金の徴収にかかる伝票類がある。
An example of the former is the description of a postal code, and an example of the latter is a document for collecting taxes or water charges that requires multiple processing by citizens at public institutions.

ここで問題となるのは、読み取り不能の文字を絶無にす
ることかで色ないということである。このことは手書文
字の読み取りの場合には容易に想い至るところであり、
また活字であっても活字の摩耗による部分的不鮮明等に
起因する場合も考えられる。
The problem here is that it doesn't matter if we eliminate all unreadable characters. This is easily understood when reading handwritten characters.
In addition, even in the case of printed characters, there may be cases where the printed characters become partially unclear due to wear.

この他オペレータの誤操作、フォーマット指定の誤り及
びハードウェア障害等による読み取り不能という場合も
ある。
In addition, it may be impossible to read due to operator error, format specification error, hardware failure, etc.

そこで、大量の伝票を処理する場合に、ある文字の読み
取シネ能が生じた時、逐一機械の動作を停止して修正す
るか、あるいは読み取り不能文字が成る程度存在しても
一定量の伝票は継続して一括処理してしまい、読み取り
不能文字を含んでいる伝票については後で一括修正する
かという問題がある。前者の方法では作業の流れが停滞
して効率が低下することが考えられ、後者の方法では、
一応の読み取シが終った後に大量の伝票の修正処理が生
ずる怖れがおる。このため効率的で且つ大量修正という
危険の少ない方法が模索されている状況にあった。
Therefore, when processing a large number of invoices, if the ability to read a certain character occurs, it is necessary to stop the operation of the machine one by one and correct it, or even if there are some unreadable characters, a certain amount of invoices cannot be There is a problem of continuing batch processing and whether documents containing unreadable characters should be corrected later. The former method may stagnate the work flow and reduce efficiency, while the latter method
There is a risk that a large number of vouchers will need to be corrected after some reading has been completed. For this reason, there has been a search for a method that is efficient and involves less risk of mass correction.

(3)従来技術と問題点 通常OCRを用いる場合には、大量の伝票例えば500
枚の帳票をホッパーに入れ、この帳票の堆積から1枚ず
つ自動的に取シ込まれていく。そして読まれた文字には
その文字コードが割当てられ、読み取り不能文字にはり
ジエクトコードが割当てられる。
(3) Conventional technology and problems When using normal OCR, a large number of slips, for example 500
A stack of documents is placed in a hopper, and the documents are automatically taken in one by one. Then, the read characters are assigned their character codes, and the unreadable characters are assigned their transfer codes.

そこで、読み取り不能文字に遭遇した場合にどのように
対処するかについては、従来二つの方法が採用されてお
りいずれによるかはキー操作により簡単に選択できるよ
うになっている。一つは一括処理と呼ばれる方法で、一
定量の伝票を処理する間は仮に読み取り不能の文字に遭
遇しても読み取り不能表示(リジェクト表示)や修正作
業を行なうことなくフロッピーディスクに書き込んだり
、ホストコンピュータへ情報を送るなどの動作を継続し
てしまう方法である。
Therefore, two methods have been conventionally adopted to deal with the situation when an unreadable character is encountered, and one can be easily selected by key operation. One is a method called batch processing, in which even if an unreadable character is encountered while processing a certain amount of invoices, it is written to a floppy disk without displaying an unreadable character (reject display) or making corrections, or This method continues operations such as sending information to a computer.

この方法は、効率の上る方法ではあるが、オペレータの
誤操作に基づく読み取シネ能が存在する場合には、通常
の読み取シ操作が終了し念後に、大量の読み取υ不能の
伝票の存在が判明する場合を生じ、その場合には、誤操
作を正常操作にした後再び読み取りをやり直さなければ
ならないという予期せぬ時間の浪費を来たすおそれが大
いにおる。
Although this method is more efficient, if there is a failure to read due to operator error, it will become clear that there are a large number of unreadable documents after normal reading operations are completed. In such a case, there is a great possibility that unexpected time will be wasted as the user will have to read again after correcting the erroneous operation.

他の一つの方法は即時修正読取あるいは逐時処理と呼ば
れる方法で、これはオペレータが常時読み取り不能の有
無を監視しており、読み取シネ能を生じた時にはオペレ
ータがキーで入力するという方法であるO この方法は、後で大量の読み取り不能伝票を発生すると
いう危険はないがオペレータが常時監視していなければ
ならないしその都度キー操作をするので効率が低下する
Another method is called immediate corrective reading or simultaneous processing, in which the operator constantly monitors for readability, and when the readability occurs, the operator inputs it using a key. O This method does not pose the risk of generating a large number of unreadable slips later, but the efficiency decreases because the operator must constantly monitor and perform key operations each time.

従来の技術は以上のような問題を有している0 (4)発明の目的 本発明は簡単な構成によって上記のような読み取りのや
9直しの危険性おるいは効率の低下という二つの欠点を
除去した方法を提供しようとするものでおる0 (5)発明の構成 本発明の構成は特許請求の範囲に記載のとおシ光学式文
字読取装置において帳票記載の文字を読み取る場合に、
読み取るべき文字数に対する読み取った文字数の割合(
読取率という)を計測し、この計測値を予め設定された
妥当な読取率(基準値)と比較し、この基準値を満たし
ているか否かを表示することを特徴とする文字認識結果
表示方式である。
The conventional technology has the above-mentioned problems. (4) Purpose of the Invention The present invention has the above-mentioned two drawbacks, such as the danger of reading and correction and the decrease in efficiency, due to its simple configuration. (5) Structure of the Invention The structure of the present invention is as described in the claims.When reading characters written on a form with an optical character reading device,
The ratio of the number of characters read to the number of characters to be read (
A character recognition result display method characterized by measuring the reading rate (referred to as reading rate), comparing this measured value with a preset reasonable reading rate (reference value), and displaying whether or not this standard value is met. It is.

(6)発明の実施例 図に本発明の実施例の構成を示す。(6) Examples of the invention The figure shows the configuration of an embodiment of the present invention.

図中の番号1はOCRの文字認識部、2は記憶部(メモ
リと呼ぶ)、3はMPU、4は字数記録部、5及び6は
レジスタ、7はキーボード、8は比較器、9は表示部、
10はフロッピィディスクである。
In the figure, number 1 is the OCR character recognition section, 2 is the storage section (called memory), 3 is the MPU, 4 is the character number recording section, 5 and 6 are registers, 7 is the keyboard, 8 is the comparator, and 9 is the display Department,
10 is a floppy disk.

以下動作を説明する。The operation will be explained below.

文字認識部1で伝票の文字が読み取られるとその文字に
対応した文字コードがメモリ2ヘフオーマツトに従って
書き込まれる〇一方読み取9不能の文字に遭遇した場合
にはりジエクトコードが割シ当てられておシ該コービも
メ毎り2へ書色込まれる。メモリ2が伝1I41枚分の
文字コード及びリジェクトコードを受は終った時点でM
PU3は読み取った文字数と読み取り不能の文字数を字
数記録部4へ書き込み、その値より読取率を計算してそ
の値をレジスタ5へ書色込む。他方オペレータは妥当な
読取率値をキーボード7からMPU3を介してレジスタ
6へ書き込む。そしてレジスタ5及び同6の値は比較器
8で比較され、レジスタ5の読取率値が妥当読取率値を
満たしているか否かの情報信号が表示部!へ送られる。
When a character on a slip is read by the character recognition unit 1, a character code corresponding to that character is written into the memory 2 according to the format.On the other hand, if an unreadable character is encountered, a code is assigned to the corresponding character. Kobi was also written down to 2 for the first time. When memory 2 has received the character codes and reject codes for 41 pages of Den 1,
The PU 3 writes the number of read characters and the number of unreadable characters into the character number recording section 4, calculates the reading rate from these values, and writes the value into the register 5. On the other hand, the operator writes a valid reading rate value from the keyboard 7 to the register 6 via the MPU 3. The values of registers 5 and 6 are compared by a comparator 8, and an information signal indicating whether the reading rate value of register 5 satisfies the appropriate reading rate value is displayed on the display! sent to.

表示部!の表示形式としては、読取率が妥当読取率を満
たしている時には緑色の〉ンプを点灯し、然らざる時は
赤色ランプを点灯するランプ表示形式やディスプレイC
RT上にOK又はNoの文字を表示する形式等各種の方
式が考えられる。
Display section! The display format is a lamp display format that lights up a green lamp when the reading rate satisfies a reasonable reading rate, and a red lamp when it does not, and a display C.
Various methods are possible, such as displaying the characters OK or No on RT.

一般にOCRにおいては読み取り不能を絶無にすること
は困難であり必ず付きまとう問題である。
Generally, in OCR, it is difficult to eliminate unreadability, and this is a problem that always occurs.

しかし、この読み取シネ能となる率は全くランダムなも
のであるかというと、そうではなく、伝票のフォーマッ
トが定まり、伝票への記入者のグループや職場の手順等
が定まって、通常の注意力をもって処理作業を継続して
いくと、統計的に一定の値に落ち着くことが知られてい
る。即ち通常の注意力をもって作業を行なっている場合
それだけの読み取り不能が出てもこれは止むを得ないこ
とであり特に異常ではないということである。
However, this is not to say that the rate at which this reading ability occurs is completely random; rather, the format of the slip is fixed, the group of people filling out the slip, the procedures of the workplace, etc. It is known that if the processing operation is continued after , the value will statistically settle to a constant value. In other words, if you are working with normal attentiveness, even if reading becomes impossible, this is unavoidable and is not abnormal.

そこで本件発明はこの点に着眼し、経験的・統計的に得
られた妥当な読取率を設定し、OCR作動中の読取率が
この妥当読取率を越えている場合には伝票記入作業やO
CRの操作及び動作には異常がないものとして一括処理
を継続する。これに対して作動中の読取率が妥当読取率
よりも低下した場合には、何らかの異常が存在するもの
として、OCRの作動を一時停止して点検を行なう。
Therefore, the present invention focuses on this point, sets a reasonable reading rate obtained empirically and statistically, and if the reading rate during OCR operation exceeds this reasonable reading rate, the work of filling out slips and
The batch processing is continued assuming that there is no abnormality in the operation and operation of the CR. On the other hand, if the reading rate during operation falls below the appropriate reading rate, it is assumed that some abnormality exists, and the operation of the OCR is temporarily stopped and an inspection is performed.

本実施例においては、妥当読取率の値はオペレータによ
ってキーボード7から大刀され、作動中の読取率が妥当
読取率を越えているが否かは表示部9によって容易に認
識されるようになっている。
In this embodiment, the value of the appropriate reading rate is entered by the operator from the keyboard 7, and whether or not the reading rate in operation exceeds the appropriate reading rate can be easily recognized from the display unit 9. There is.

(7)  発明の効果 本発明によれば、OCRを作動中常時、1枚の伝票毎の
、あるいは他の区分毎の読取率が計測され、その値が予
め大刀された妥当読取率を満足しているか否かが表示さ
れるので、OCRの動作を停止させて点検する必要が有
るか否かの効果的な判断が可能となる。
(7) Effects of the Invention According to the present invention, the reading rate is measured for each slip or for each other category at all times while the OCR is in operation, and the reading rate is measured if the reading rate satisfies a predetermined reasonable reading rate. It is possible to effectively judge whether or not it is necessary to stop the OCR operation and inspect it.

仁のため、逐次処理におけるようなオペレータの監視や
効率の低下を除去することができ、i九一方、一括処理
における如く、大量の伝票を処理してしまった後に、大
量の読み取り不能を発見し作業のやり直しに至るような
無駄を除去することが可能となる。なお、妥当読取率内
に入っている程度の読み取り不能を、一括処理後に修正
処理をすることは殆んど作業効率に悪影響を及ぼさない
Because of this, it is possible to eliminate the operator supervision and loss of efficiency as in serial processing, and on the other hand, as in batch processing, it is possible to detect a large number of unreadable documents after processing a large number of documents. This makes it possible to eliminate waste that would lead to redoing work. It should be noted that correcting unreadable problems that are within a reasonable reading rate after batch processing has almost no negative effect on work efficiency.

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

図は本発明の実施例の構成を示すブロック図である。 1・・・・−・・文字認識部、2・・−・−・・記憶部
(メモリ)、5・・−・−・・MPU、4・・−・−・
・字数記録部、5.6・・−・・・・レジスタ、7・・
−・−・・キーボード、8・・−・−・・比較器、9・
・−・−・・表示部、10・・−・−・・フロッピィデ
ィスク。
The figure is a block diagram showing the configuration of an embodiment of the present invention. 1...Character recognition section, 2...--Storage section (memory), 5...---MPU, 4...----
・Character number recording section, 5.6...Register, 7...
−・−・・Keyboard, 8・・−・−・・Comparator, 9・
・−・−・・Display section, 10・・−・−・・Floppy disk.

Claims (1)

【特許請求の範囲】[Claims] 帳票記載の文字を読み取る光学式文字読取装置において
、読み取った文字数と読み取り不能の文字数を記録する
記録部と、該記録部に記録された値に基づき読み取るべ
き文字数に対する読み取った文字数の割合を算出する演
算部と、該演算結果を記録するレジスタと、オペレータ
が設定する基準値を記録するレジスタと、前記2つのレ
ジスタの値を比較する比較器とを有し、前記算出結果が
前記基準値を満たしているか否かを表示部に表示するこ
とを特徴とする文字認識結果表示方式。
An optical character reader that reads characters on a form includes a recording section that records the number of characters read and the number of unreadable characters, and a ratio of the number of characters read to the number of characters that should be read based on the values recorded in the recording section. The computer comprises a calculation unit, a register for recording the calculation result, a register for recording a reference value set by an operator, and a comparator for comparing the values of the two registers, and the calculation result satisfies the reference value. A character recognition result display method characterized by displaying on a display unit whether or not the recognition result is correct.
JP57072874A 1982-04-30 1982-04-30 Display system for recognition result of character Pending JPS58191078A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP57072874A JPS58191078A (en) 1982-04-30 1982-04-30 Display system for recognition result of character

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP57072874A JPS58191078A (en) 1982-04-30 1982-04-30 Display system for recognition result of character

Publications (1)

Publication Number Publication Date
JPS58191078A true JPS58191078A (en) 1983-11-08

Family

ID=13501908

Family Applications (1)

Application Number Title Priority Date Filing Date
JP57072874A Pending JPS58191078A (en) 1982-04-30 1982-04-30 Display system for recognition result of character

Country Status (1)

Country Link
JP (1) JPS58191078A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63147757U (en) * 1987-03-20 1988-09-29

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63147757U (en) * 1987-03-20 1988-09-29

Similar Documents

Publication Publication Date Title
JPS61141056A (en) Intermittent error detection for volatile memory
US20010011282A1 (en) Apparatus and method for processing various form documents to meet respective form,and recording medium storing a program to execute the process
WO2018073986A1 (en) Operation assistance device and operation assistance program
JPS58191078A (en) Display system for recognition result of character
JPH08329187A (en) Document reader
JPH04183066A (en) Picture processor
JP2650682B2 (en) How to read encoded data
JPS58106665A (en) Character line cutout method
JP2722550B2 (en) Optical character reader
JP4232316B2 (en) Validity verification system for print data for OCR
JPS5845061B2 (en) Data processing method in data processing device
JPH09259223A (en) Image data recognition system
JPH06231162A (en) Method for processing magnetic card
TWM602682U (en) Bill verification system
TW307860B (en) Device for testing data reading reliability of CD-ROM drive and method thereof
JPS6115478B2 (en)
CN117711553A (en) Multifunctional electronic medical record file generation system
JPH0544060B2 (en)
JPS61224084A (en) Inspecting system for read character data
JP2009064227A (en) Form reader
JPH0236435A (en) Module test system
JPS60217191A (en) Recorder
JPS5966787A (en) Character recognizing and control system of ocr facsimile
JPS62295192A (en) Optical character image reader
Poloniecki et al. Administrative databases and the quality of data in a myocardial infarction database