JPH04124785A - Confirmation and correction method for ocr recognition result - Google Patents
Confirmation and correction method for ocr recognition resultInfo
- Publication number
- JPH04124785A JPH04124785A JP2244113A JP24411390A JPH04124785A JP H04124785 A JPH04124785 A JP H04124785A JP 2244113 A JP2244113 A JP 2244113A JP 24411390 A JP24411390 A JP 24411390A JP H04124785 A JPH04124785 A JP H04124785A
- Authority
- JP
- Japan
- Prior art keywords
- data
- ocr recognition
- confirmation
- ocr
- 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.)
- Granted
Links
- 238000012790 confirmation Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims description 12
- 238000012937 correction Methods 0.000 title abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 abstract 1
- 238000012795 verification Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Character Discrimination (AREA)
Abstract
Description
【発明の詳細な説明】
〔産業上の利用分野〕
１゜
２゜
本発明はＯＣＲ認識結果の確認方法及び補正方法にかか
り、特にＯＣＲ認識結果の確認の正確性を向上させ、さ
らにＯＣＲ認識結果の検証処理を行う場合に、その省力
化を図るのに好適なＯＣＲ認識結果の確認方法及び補正
方法に関する。[Detailed Description of the Invention] [Field of Industrial Application] 1゜2゜The present invention relates to a method for checking and correcting OCR recognition results, and particularly improves the accuracy of checking OCR recognition results, and further improves the accuracy of checking OCR recognition results. The present invention relates to a method for confirming and correcting OCR recognition results suitable for saving labor when performing verification processing.
従来のＯＣＲシステムにおいては、一般に特開昭５８−
１４４９７９号公報に記載されているように、ＯＣＲ認
識の認識辞書の強化を図ることにより、認識率の向上を
図っている。しかし、認識率、認識精度については限界
があり、オペレータによる確認および補正の負担は残る
。Conventional OCR systems generally use JP-A-58-
As described in Japanese Patent No. 144979, the recognition rate is improved by strengthening the recognition dictionary for OCR recognition. However, there are limits to the recognition rate and recognition accuracy, and the burden of confirmation and correction remains on the operator.
上記従来技術は、ＯＣＲ認識の認識辞書の強化を図るも
のであるが、いずれにしても認識率、認識精度について
は限界があり、認識不可の場合の補正の容易性、および
認識結果の確認（誤読の有無）の容品性については配慮
がされていない。The above-mentioned conventional technology aims to strengthen the recognition dictionary for OCR recognition, but in any case, there are limits to the recognition rate and recognition accuracy. No consideration was given to the quality of the product (whether there was any misreading).
本発明は、重要項目の認識結果確認の正確性を向上させ
るとともに、何段階ものｆ！認、検証処理を行う場合に
おける確認及び補正の省力化を提供することを目的とす
る。The present invention not only improves the accuracy of confirmation of recognition results for important items, but also provides f! The purpose is to provide labor-saving confirmation and correction when performing verification and verification processing.
上記目的を達成するために、ＯＣＲ認識したあるＡとい
う項目に対して、Ａのイメージデータを表示し、そのイ
メージデータから手入力でコードデータを入力し、ｏ
ＣＲｙ２識結果と手入力コードデータの比較処理を行う
。比較した結果、一致していればＯＣＲ処理と確認処理
が正常終了したものとして、以降の検証等ではＡの表示
を省略してｉ！認の省力化を図る。In order to achieve the above purpose, for a certain item A recognized by OCR, display the image data of A, input code data manually from the image data, and o
A comparison process is performed between the CRy2 recognition result and the manually input code data. As a result of the comparison, if they match, it is assumed that the OCR processing and confirmation processing have completed successfully, and in subsequent verifications, etc., the display of A will be omitted and i! We aim to save labor in recognition.
また不一致の場合は手入力データを優先入力し、以降の
検証等でイメージデータとの目視確認を行うよう、表示
させる。これにより、確認と補正の正確化を図る。If there is a discrepancy, the manual input data is given priority and displayed so that it can be visually checked against the image data during subsequent verification. This makes confirmation and correction more accurate.
（作用〕
比較処理で一致したものは、以降目視確認が不要になり
、ｉ認の省力化が図れる。(Function) If there is a match in the comparison process, there is no need for visual confirmation thereafter, which saves labor in i-identification.
また、不一致のものは手入力データでＯＣＲ結果を置き
かえるため、補正の正確化を図ることができる。In addition, since the OCR result is replaced with manually input data when there is a mismatch, the correction can be made more accurate.
以下本発明の一実施例を図面を用いて説明する。 An embodiment of the present invention will be described below with reference to the drawings.
第１図は本発明の一実施例のシステム構成を示している
。第１図において、１は原帳票、２はＯＣＲ認識装置、
３は制御装置、４はイメージデータおよびＯＣＲ結果の
表示を行い、確認または補正を行う端末である。本発明
における重要項目の手入力は端末４において行われる。FIG. 1 shows a system configuration of an embodiment of the present invention. In Figure 1, 1 is the original document, 2 is the OCR recognition device,
3 is a control device, and 4 is a terminal that displays image data and OCR results and performs confirmation or correction. Manual input of important items in the present invention is performed on the terminal 4.
また、端末５は端末４から入力された手入力データとＯ
ＣＲ認識装置２による認識結果が不一致となった場合に
、端末４のオペレータ以外の第三者（例えば、上席者）
による再確認を受けるために、当該帳票データを表示す
る検証用端末である。In addition, the terminal 5 receives the manual input data input from the terminal 4 and the O
If the recognition result by the CR recognition device 2 does not match, a third party other than the operator of the terminal 4 (for example, a senior person)
This is a verification terminal that displays the form data in order to receive reconfirmation.
第２図は第１図に示す原帳票１０例として、銀行の振込
依頼票を示したものである。第２図において、各記入項
目は、ＯＣＲ認識項目として、ＯＣＲ認識装Ｗ２により
、ＯＣＲコード化される。FIG. 2 shows a bank transfer request form as an example of the ten original documents shown in FIG. In FIG. 2, each entry is converted into an OCR code by an OCR recognition device W2 as an OCR recognition item.
なお、第２図において、口座番号と金額については、特
にＯＣＲ認識の重要項目とされ、これらの項目の帳票上
の位置が、帳票フォーマット情報として、あらかじめＯ
ＣＲ認識装置２と制御装置３にシステム登録されている
。Note that in Figure 2, the account number and amount are particularly important items for OCR recognition, and the positions of these items on the form are set in advance as form format information.
The system is registered in the CR recognition device 2 and the control device 3.
第３図は、原帳票１の端末４における表示フォーマット
の一例を示し、第２図に示す振込依頼票の表示例である
。振込依頼票の各項目は、ＯＣＲ認識装置２によってＯ
ＣＲ認識されるとともに、各項目毎にイメージ切出し処
理を受け、端末４においては再配置された状態で表示さ
れる。すなわち、端末４においては、図示するように、
各項目の確認・補正を容易にするため、項目の上段に切
出されたイメージデータを、また下段にはＯＣＲ認識結
果をそれぞれ並列表示している。FIG. 3 shows an example of the display format of the original form 1 on the terminal 4, and is a display example of the transfer request form shown in FIG. Each item on the transfer request form is scanned by the OCR recognition device 2.
CR is recognized, each item undergoes image extraction processing, and is displayed in a rearranged state on the terminal 4. That is, in the terminal 4, as shown in the figure,
In order to facilitate confirmation and correction of each item, the extracted image data is displayed in the upper row of each item, and the OCR recognition results are displayed in parallel in the lower row.
なお、第３図においては、住所の項目をＯＣＲ認識装置
２の認識対象から外している。Note that in FIG. 3, the address item is excluded from the recognition target of the OCR recognition device 2.
また、端末４においては、前記重要項目である口座番号
、および金額について、ＯＣＲ認識結果を表示せず、オ
ペレータがイメージデータを目視して手入力するものと
する。Furthermore, in the terminal 4, the OCR recognition results are not displayed for the important items, such as the account number and the amount, but the operator manually inputs them by visually viewing the image data.
第４図は、第１図に示す実施例において行われる処理を
示すフローチャートである。第４図に示すように、ＯＣ
Ｒ認識装置２に入力された振込依頼票の画像は、イメー
ジデータの切出し、およびＯＣＲ認識処理された後、（
イメージデータ）＋（コードデータ）の形で制御装置３
に送られる（ステップＳｌ）。制御装置３では、受信し
たデータを端末４に表示させるために編集した後（ステ
ップＳ２）、端末４に送信するとともに、口座番号およ
び金額のＯＣＲ認識結果を記憶しておく（ステップＳ３
）。端末４では、切出された各項目のイメージデータと
ＯＣＲ認識認識コードテラを並列表示し、オペレータの
確認および補正を受ける（ステップＳ４）。重要項目で
ある口座番号と金額についてはイメージデータのみを表
示し、（ＯＣＲ認識結果は表示しない）、オペレータが
目視してイメージデータの下段エリアにデータを手入力
する（ステップＳ５）。FIG. 4 is a flowchart showing the processing performed in the embodiment shown in FIG. As shown in Figure 4, the OC
The image of the transfer request form input into the R recognition device 2 is processed by cutting out the image data and OCR recognition processing.
control device 3 in the form of image data) + (code data)
(step Sl). The control device 3 edits the received data to display it on the terminal 4 (step S2), and then sends it to the terminal 4 and stores the OCR recognition results of the account number and amount (step S3).
). The terminal 4 displays the extracted image data of each item and the OCR recognition recognition code TERRA in parallel, and receives confirmation and correction from the operator (step S4). For important items such as account number and amount, only image data is displayed (OCR recognition results are not displayed), and the operator visually enters the data into the lower area of the image data (step S5).
重要項目の入力、その他の項目のｉ認および補正が終り
、オペレータが終了キーを押下する出、当該帳票データ
は制御装置３に送信される。制御装置３では、重要項目
についてＯＣＲ認識結果と手入力データとの比較処理を
行い、一致した場合はＯＣＲ認識が正常に行われたもの
とし、当該帳票データの確認処理を終了する（ステップ
Ｓ６゜Ｓ７）。一方、不一致となった場合、制御装置３
はＯＣＲ認識結果を手入力データで置き替えるとともに
、当該帳票データを検証要データと判断し、検証用の端
末５に送信する（ステップ３８）。端末５では、当該帳
票データの表示を行い、手入力を行ったオペレータとは
別の人の再確認を受ける（ステップＳ９）。この場合、
手入力データを表示させるとともに不一致結果も表示す
る。不一致結果は文字色を変えること、またはマークを
表示することにより検証者にわかるようにし、これによ
り検証者は目視確認を行う。After inputting important items, checking and correcting other items, the operator presses the end key, and the form data is transmitted to the control device 3. The control device 3 compares the OCR recognition results with the manually input data for important items, and if they match, it is assumed that the OCR recognition has been performed normally, and the confirmation process for the form data is ended (step S6゜S7). On the other hand, if there is a mismatch, the control device 3
replaces the OCR recognition result with manually input data, determines that the form data is data requiring verification, and transmits it to the verification terminal 5 (step 38). The terminal 5 displays the form data and receives reconfirmation from an operator other than the operator who manually entered the data (step S9). in this case,
Displays manually input data and also displays discrepancies. The mismatch results are made visible to the verifier by changing the font color or displaying a mark, and the verifier visually confirms the results.
ＯＣＲ認識結果の確認および検証方法として、まず第一
次オペレータによってＯＣＲ認識結果の目視確認を行っ
た後、別の第二次オペレータまたは検証者によって、再
度目視確認を行う方法がある。上記実施例は、このうち
の第一次オペレータによる目視確認を手入力処理に置き
かえ、システムによってＯＣＲ認識結果の確認および検
証を行うものである。従って、目視ｉ認のみの場合と比
較して、確認の正確化が図れるとともに、ＯＣＲ認識が
正常に行われた場合は、第二次オペレータの目視による
検証確認が不要となるので省力化が図れる。As a method for checking and verifying the OCR recognition results, there is a method in which the OCR recognition results are first visually checked by a primary operator, and then visually checked again by another secondary operator or verifier. In the above embodiment, the visual confirmation by the primary operator is replaced with manual input processing, and the OCR recognition result is confirmed and verified by the system. Therefore, compared to the case of only visual recognition, confirmation can be made more accurate, and if OCR recognition is performed normally, there is no need for visual verification by the secondary operator, resulting in labor savings. .
本発明によれば、ＯＣＲ認識結果と手入力データが一致
すれば、以降の再確認が不要となり、確認の省力化、容
易化が図れる。According to the present invention, if the OCR recognition result and the manually input data match, subsequent reconfirmation is unnecessary, and confirmation can be labor-saving and facilitated.
また、不一致の場合は手入力データを優先させると共に
、以降の処理で目視再確認を行わせるので、補正の正確
化が図れる。Further, in the case of a mismatch, priority is given to manually input data, and visual reconfirmation is performed in subsequent processing, so that correction can be made more accurate.
第１図は本発明の一実施例であるシステム構成を示すブ
ロック図、第２図は第１図に示す原帳票の一例である銀
行の振込依頼票を示す説明図、第３図は第１図に示す端
末４の表示画面に原帳票上のＯＣＲ認識項目のイメージ
データとＯＣＲ認識結果を表示した場合の一例を示す説
明図、第４図は第１図に示す実施例において実行される
処理の一例を示すフローチャートである。
１・・・原帳票、２・・・Ｏ’ＣＲ認識装置、３・・・
制御装置、４・・・端末、５・・・検証用端末。FIG. 1 is a block diagram showing a system configuration that is an embodiment of the present invention, FIG. 2 is an explanatory diagram showing a bank transfer request slip, which is an example of the original document shown in FIG. 1, and FIG. An explanatory diagram showing an example of a case where the image data of the OCR recognition items on the original document and the OCR recognition results are displayed on the display screen of the terminal 4 shown in the figure. FIG. 4 is a process executed in the embodiment shown in FIG. 1. It is a flowchart which shows an example. 1...Original form, 2...O'CR recognition device, 3...
Control device, 4... terminal, 5... verification terminal.
Claims (1)
比較し、一致した場合には、ＯＣＲ認識処理が正確に行
われ、その認識結果を正しいと判定することを特徴とす
るＯＣＲ認識結果の確認方法。 ２、ＯＣＲ認識結果とオペレータによる入力データとを
比較し、一致した場合には、ＯＣＲ認識処理が正確に行
われ、認識結果を正しいと判定し、不一致の場合には、
ＯＣＲ認識結果をオペレータによる入力データに置き換
え、さらに上記入力データとＯＣＲ認識処理の対象とな
ったイメージデータとを表示して、目視による確認を行
うことを特徴とするＯＣＲ認識結果の補正方法。[Claims] 1. An OCR system that compares an OCR recognition result with data input by an operator, and if they match, the OCR recognition process is performed accurately and the recognition result is determined to be correct. How to check recognition results. 2. Compare the OCR recognition result and the data input by the operator, and if they match, the OCR recognition process is correctly performed and the recognition result is determined to be correct; if they do not match,
A method for correcting OCR recognition results, which comprises replacing the OCR recognition results with input data by an operator, and further displaying the input data and image data subjected to OCR recognition processing for visual confirmation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP24411390A JP3191217B2 (en) | 1990-09-17 | 1990-09-17 | OCR recognition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP24411390A JP3191217B2 (en) | 1990-09-17 | 1990-09-17 | OCR recognition system |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2000071724A Division JP2000298700A (en) | 2000-01-01 | 2000-03-15 | Method for correcting ocr recognition result |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH04124785A true JPH04124785A (en) | 1992-04-24 |
| JP3191217B2 JP3191217B2 (en) | 2001-07-23 |
Family
ID=17113954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP24411390A Expired - Lifetime JP3191217B2 (en) | 1990-09-17 | 1990-09-17 | OCR recognition system |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP3191217B2 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0668122A (en) * | 1992-08-21 | 1994-03-11 | Nec Corp | Monetary amount verification system at transfer registration |
| JP2008009771A (en) * | 2006-06-29 | 2008-01-17 | Canon Marketing Japan Inc | Information processor, operation system, control method, program, and recording medium |
| JP2010231256A (en) * | 2009-03-25 | 2010-10-14 | Hitachi Ltd | Data recognition device, method of recognizing data, and program |
| US8026657B2 (en) | 2006-12-18 | 2011-09-27 | Industrial Technology Research Institute | Electron emission light-emitting device and light emitting method thereof |
| JP2016194958A (en) * | 2014-12-11 | 2016-11-17 | 株式会社リコー | Personal information collection system, information collection system, personal information collection method, information collection method, information processing apparatus, program, and recording medium |
| US9785831B2 (en) | 2014-12-11 | 2017-10-10 | Ricoh Company, Ltd. | Personal information collection system, personal information collection method and program |
| CN109359878A (en) * | 2018-10-26 | 2019-02-19 | 珠海市时杰信息科技有限公司 | Procedure file data digitalized processing method, computer installation and computer readable storage medium |
| JP2019133717A (en) * | 2019-05-07 | 2019-08-08 | 富士ゼロックス株式会社 | Information processor and information processing program |
| CN110991279A (en) * | 2019-11-20 | 2020-04-10 | 北京灵伴未来科技有限公司 | Document image analysis and recognition method and system |
| JP2020173610A (en) * | 2019-04-10 | 2020-10-22 | グローリー株式会社 | Currency processing device, currency processing system, and currency processing method |
-
1990
- 1990-09-17 JP JP24411390A patent/JP3191217B2/en not_active Expired - Lifetime
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0668122A (en) * | 1992-08-21 | 1994-03-11 | Nec Corp | Monetary amount verification system at transfer registration |
| JP2008009771A (en) * | 2006-06-29 | 2008-01-17 | Canon Marketing Japan Inc | Information processor, operation system, control method, program, and recording medium |
| US8026657B2 (en) | 2006-12-18 | 2011-09-27 | Industrial Technology Research Institute | Electron emission light-emitting device and light emitting method thereof |
| JP2010231256A (en) * | 2009-03-25 | 2010-10-14 | Hitachi Ltd | Data recognition device, method of recognizing data, and program |
| JP2016194958A (en) * | 2014-12-11 | 2016-11-17 | 株式会社リコー | Personal information collection system, information collection system, personal information collection method, information collection method, information processing apparatus, program, and recording medium |
| US9785831B2 (en) | 2014-12-11 | 2017-10-10 | Ricoh Company, Ltd. | Personal information collection system, personal information collection method and program |
| CN109359878A (en) * | 2018-10-26 | 2019-02-19 | 珠海市时杰信息科技有限公司 | Procedure file data digitalized processing method, computer installation and computer readable storage medium |
| JP2020173610A (en) * | 2019-04-10 | 2020-10-22 | グローリー株式会社 | Currency processing device, currency processing system, and currency processing method |
| JP2023058752A (en) * | 2019-04-10 | 2023-04-25 | グローリー株式会社 | Currency processor |
| JP2019133717A (en) * | 2019-05-07 | 2019-08-08 | 富士ゼロックス株式会社 | Information processor and information processing program |
| CN110991279A (en) * | 2019-11-20 | 2020-04-10 | 北京灵伴未来科技有限公司 | Document image analysis and recognition method and system |
| CN110991279B (en) * | 2019-11-20 | 2023-08-22 | 北京灵伴未来科技有限公司 | Document Image Analysis and Recognition Method and System |
Also Published As
| Publication number | Publication date |
|---|---|
| JP3191217B2 (en) | 2001-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPH04124785A (en) | Confirmation and correction method for ocr recognition result | |
| EP0552392B1 (en) | Method for mutual authentification of an IC-card and a terminal | |
| US20060274945A1 (en) | System and method for automatically extracting a picture of a person from a government issued identification piece for use on a badge | |
| JP2908187B2 (en) | Confirmation and correction method of OCR recognition result | |
| JPH10320488A (en) | Method and device for entering data | |
| JP2000298700A (en) | Method for correcting ocr recognition result | |
| JPH05274467A (en) | Data input device | |
| JP2002123793A (en) | Slip reading method and terminal equipment | |
| JP2007249630A (en) | Financial transaction system | |
| JPH06274679A (en) | Character reader | |
| JP2002074263A (en) | System for reading facsimile character | |
| JP4466018B2 (en) | Seal verification system and program | |
| JP2003256664A (en) | Method and system for collating slips | |
| JP7435010B2 (en) | Information processing device, information processing method, information processing program | |
| JPH11328285A (en) | Monetary system | |
| JPH09161053A (en) | Fingerprint collating device | |
| JPH0830700A (en) | Inputting and journalizing device for slip data | |
| JPS62263523A (en) | Input data correcting system | |
| JP2002259711A (en) | Transfer payment name identicalness collating system and program | |
| JP2002092545A (en) | Character recognition method | |
| JP4244630B2 (en) | Seal verification system and control program thereof | |
| JPH0668122A (en) | Monetary amount verification system at transfer registration | |
| JPH0355679A (en) | Collating method between character recognition result and character input result | |
| JP3259938B2 (en) | Form processing method and form processing apparatus by facsimile | |
| JPS62229485A (en) | Reservation inquiring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| S111 | Request for change of ownership or part of ownership |
Free format text: JAPANESE INTERMEDIATE CODE: R313115 |
|
| S531 | Written request for registration of change of domicile |
Free format text: JAPANESE INTERMEDIATE CODE: R313531 |
|
| R350 | Written notification of registration of transfer |
Free format text: JAPANESE INTERMEDIATE CODE: R350 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080525 Year of fee payment: 7 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090525 Year of fee payment: 8 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100525 Year of fee payment: 9 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110525 Year of fee payment: 10 |
|
| EXPY | Cancellation because of completion of term | ||
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110525 Year of fee payment: 10 |