JPS5985581A - Test system of recognition processor - Google Patents
Test system of recognition processorInfo
- Publication number
- JPS5985581A JPS5985581A JP57195679A JP19567982A JPS5985581A JP S5985581 A JPS5985581 A JP S5985581A JP 57195679 A JP57195679 A JP 57195679A JP 19567982 A JP19567982 A JP 19567982A JP S5985581 A JPS5985581 A JP S5985581A
- Authority
- JP
- Japan
- Prior art keywords
- image signal
- recognition processing
- recognition
- sample scanning
- scanning 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Input (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Character Discrimination (AREA)
Abstract
Description
【発明の詳細な説明】
（１） 発明の属する分野の説明
本発明は、認識処理装置の機能試験を行なう方式に関す
るものである。DETAILED DESCRIPTION OF THE INVENTION (1) Description of the field to which the invention pertains The present invention relates to a method for performing a functional test of a recognition processing device.
（２）従来の技術の説明
認識処理装置の機能試験においては、マークあるいは数
字等の認識対象の情報を含んだ画信号を制御装置から認
識処理装置に送出し、認識結果を認識処理装置から制御
装置に返送し、制御装置は受取った認識結果を正解デー
タと照合する必要がある。ここで８機能試験に必要とさ
れる画信号のデニタ量は膨大なものであり、制御装置に
画信号を記憶するためには多くのメモリ量を必要とする
欠点があった。(2) Description of conventional technology In a functional test of a recognition processing device, an image signal containing information to be recognized, such as marks or numbers, is sent from the control device to the recognition processing device, and the recognition results are controlled by the recognition processing device. It is necessary for the control device to check the received recognition results against the correct data. Here, the amount of image signals required for the 8-function test is enormous, and there is a drawback that a large amount of memory is required to store the image signals in the control device.
そこで・従来のこの種の機能試験においては。Therefore, in conventional functional tests of this type.
制御装置に磁気テープ装置等の外部記憶装置またはファ
クシミリ端末等の画信号入力装置を接続することにより
、認識処理装置の機能試験を行っていた。The functionality of the recognition processing device was tested by connecting an external storage device such as a magnetic tape device or an image signal input device such as a facsimile terminal to the control device.
しかし、前者の方法においては、制御装置に磁気テープ
装置等の外部記憶装置が必要となる欠点があった。また
、後者の方法においても、制御装置にファクシミリ端末
等の画信号入力装置が必要となる欠点があり、かつ画信
号入力装置に試験用紙を用いて試験データを投入するの
に人手を要する欠点があり、かつ試験データ投入により
常に一定の画信号を得ることは困難であるという欠点が
あった。However, the former method has the disadvantage that the control device requires an external storage device such as a magnetic tape device. In addition, the latter method also has the drawback that it requires an image signal input device such as a facsimile terminal in the control device, and also requires human labor to input test data using test paper into the image signal input device. However, there was a drawback in that it was difficult to always obtain a constant image signal by inputting test data.
（３）発明の目的
本発明は、制御装置に試験用画信号の部分要素である走
査線（サンプル走査線と呼ぶ）を必要最少限だけ記憶し
、サンプル走査線を組み合せることにより試験用画信号
を作成し、認識処理装置の試験を行なうことを特徴とし
、その目的は制御装置における画信号データエリアの削
減をはかることにある。(3) Purpose of the Invention The present invention stores only the necessary minimum number of scanning lines (referred to as sample scanning lines), which are partial elements of a test image signal, in a control device, and combines the sample scanning lines to generate a test image. It is characterized by creating a signal and testing the recognition processing device, and its purpose is to reduce the image signal data area in the control device.
（４）発明の構成および作用の説明
第１図は２本発明にかかわる画信号作成方法の一例を示
す図であって、■乃至５は画信号作成に用いるサンプル
走査線、６，７はサンプル走査線１乃至５を組み合せて
作成することが可能な画信号の一例であり、数字情報を
含む画信号を例に説明する。(4) Description of structure and operation of the invention FIG. 1 is a diagram showing an example of the image signal generation method according to the present invention, in which 1 to 5 are sample scanning lines used for image signal generation, and 6 and 7 are sample scanning lines. This is an example of an image signal that can be created by combining scanning lines 1 to 5, and will be explained using an example of an image signal that includes numerical information.
第１図のサンープル走査遣１は数字情報を含まない走査
線（白ライン）を表わし、サンプル走査線２は数字の横
線分情報を含む走査線、サンプル走査線３は数字の左右
２本の縦線分情報を含む走査線、サンプル走査線４は数
字の左１本の縦線分情報を含む走査線、サンプル走査線
５は数字の右１本の縦線分情報を含む走査線を表わす。Sample scanning line 1 in Figure 1 represents a scanning line (white line) that does not include numerical information, sample scanning line 2 represents a scanning line that contains horizontal line segment information of the number, and sample scanning line 3 represents the two vertical lines on the left and right of the number. Sample scanning line 4, a scanning line containing line segment information, represents a scanning line containing information on one vertical line segment to the left of the number, and sample scanning line 5 represents a scanning line containing information on one vertical line segment to the right of the number.
画信号６は数字情報「２」を含む画信号で２０走査線か
らなり、上より順に、サンプル走査線１を２本、サンプ
ル走査線２を２本、サンプル走査線５を５本、サンプル
走査線２を２本、サンプル走査線４を５本、サンプル走
査線２を２本、サンプル走査線１を２本と配列すること
により形成される。また画信号７は、数字情報ｒ４Ｊを
含む画信号で２０走査線からなり、上より順にサンプル
走査線１を２本、サンプル走査線３を７本、サンプル走
査線２を２本、サンプル走査線５を７本、サンプル走査
線１を２本と配列することにより形成される。The image signal 6 is an image signal containing the numerical information "2" and consists of 20 scanning lines, in order from the top: 2 sample scanning lines 1, 2 sample scanning lines 2, 5 sample scanning lines 5, and 2 sample scanning lines. It is formed by arranging two lines 2, five sample scanning lines 4, two sample scanning lines 2, and two sample scanning lines 1. The image signal 7 is an image signal including numerical information r4J and consists of 20 scanning lines, starting from the top: 2 sample scanning lines 1, 7 sample scanning lines 3, 2 sample scanning lines 2, and 2 sample scanning lines. It is formed by arranging seven sample scanning lines 5 and two sample scanning lines 1.
同様の方式でサンプル走査線１〜５を用いると。Using sample scan lines 1-5 in a similar manner.
画信号６，７と同様にｒＯＪ〜「９」の数字情報を含む
画信号を容易に作成できる。したがって少量の″サンプ
ル走査線データを記憶することで複数種類かつ多量の画
信号を作成でき、データ量の大幅な削減が可能である。Similar to image signals 6 and 7, image signals containing numerical information from rOJ to "9" can be easily created. Therefore, by storing a small amount of "sample scanning line data", it is possible to create a large number of image signals of a plurality of types, and it is possible to significantly reduce the amount of data.
第２図は２本発明の実施例システムの構成図であって、
８は制御装置、９は認識処理装置である。FIG. 2 is a configuration diagram of a system according to two embodiments of the present invention,
8 is a control device, and 9 is a recognition processing device.
また、制御装置８は、制御部と各種データメモリより構
成され、１０は制御部、１１は画信号作成情報データメ
モリ、１２は前述したサンプル走査線１乃至５が記憶さ
れているサンプル走査線データメモリ、１３は画信号バ
ッファ、１４は正解データメモリである。Further, the control device 8 is composed of a control section and various data memories, 10 is a control section, 11 is an image signal creation information data memory, and 12 is sample scanning line data in which the above-mentioned sample scanning lines 1 to 5 are stored. A memory 13 is an image signal buffer, and 14 is a correct data memory.
つぎに、牙２図の動作を説明する。ただし９本説明では
第１図に例示した画信号６のＩ’２Ｊを作成するものと
仮定する。まず制御部１０は１画信号作成情報データメ
モリ１１より１画信号の作成に必要なサンプル走査線番
号とそのサンプル走査線の配列順序を読み出す。サンプ
ル走査線の配列順序は画信号６の「２」の場合、１−１
−２−２−５−５−５−５−５−２−２−４−４−４−
４−４−２−１１−１である。つぎに制御部１０は、サ
ンプル走査線データメモリ１２より、指示された配列順
序のサンプル走査線番号に対応するサンプル走査線デー
タを順次画信号バッファ１３に転送し９画信号６を作成
する。Next, the operation of Fang 2 will be explained. However, in the following explanation, it is assumed that I'2J of the image signal 6 illustrated in FIG. 1 is created. First, the control unit 10 reads out the sample scanning line number and the arrangement order of the sample scanning lines necessary for creating a one-picture signal from the one-picture signal production information data memory 11. The arrangement order of the sample scanning lines is 1-1 in the case of image signal 6 "2".
-2-2-5-5-5-5-5-2-2-4-4-4-
4-4-2-11-1. Next, the control unit 10 sequentially transfers the sample scanning line data corresponding to the sample scanning line numbers in the specified arrangement order from the sample scanning line data memory 12 to the image signal buffer 13 to create a nine-image signal 6.
ツキに、制御部１０は１画信号バッファ１３に作成した
画信号６を、認識処理装置９へ転送する。Finally, the control unit 10 transfers the image signal 6 created in the one-image signal buffer 13 to the recognition processing device 9.
認識処理装置９は１画信号バッファ１３より転送された
画信号６を認識処理し、認識結果を画信号バッファ１３
に返送する。つぎに制御部１０は。The recognition processing device 9 recognizes and processes the image signal 6 transferred from the one-image signal buffer 13, and transfers the recognition result to the image signal buffer 13.
send it back to Next, the control section 10.
認識処理装置９より返送され１画信号バッファ１３に格
納された認識結果を正解データメモリ１４に記憶してい
る正解データ（この場合の正解データは「２」である）
と照合することにより、認識処理装置９の認識処理機能
の正常性を判別する。Correct data stored in the correct data memory 14 is the recognition result returned from the recognition processing device 9 and stored in the one-stroke signal buffer 13 (the correct data in this case is "2")
The normality of the recognition processing function of the recognition processing device 9 is determined by comparing with the recognition processing function.
なお２本説明ではサンプル走査線データメモリ１２には
、サンプル走査線を原画信号で記憶するものとしたが、
サンプル走査線データメモリ１２に記憶する各サンプル
走査線データを走査線ごとに冗長度抑圧符号化して記憶
しておき９画信号作成時に復号してもよい。このように
すれば、前述の実施例に比べ、サンプル走査線データメ
モリ１２のメモリ容量を削減することができる。また、
認識処理装置９が冗長度抑圧符号化画信号で動作する場
合には、冗長度抑圧符号化したサンプル走査線データで
作成した画信号をそのまま使用すればよい。In the two explanations, it is assumed that the sample scanning line data memory 12 stores the sample scanning line as an original image signal.
Each sample scanning line data stored in the sample scanning line data memory 12 may be redundancy suppressed encoded and stored for each scanning line, and then decoded when creating a 9-pixel signal. In this way, the memory capacity of the sample scanning line data memory 12 can be reduced compared to the previous embodiment. Also,
When the recognition processing device 9 operates with a redundancy suppressed encoded image signal, it is sufficient to use the image signal created from redundancy suppressed coded sample scanning line data as is.
また、認識処理装置９の認識処理機能が変更された場合
、従来のように試験用画信号を磁気テープ装置等の外部
記憶装置に記憶しでおく方式では。Furthermore, when the recognition processing function of the recognition processing device 9 is changed, the conventional method of storing test image signals in an external storage device such as a magnetic tape device is not possible.
膨大な試験用画信号を変更しなければならないが。However, I have to change a huge amount of test image signals.
本試験方式では、サンプル走査線データ、および画信号
作成情報データの変更ですみ、その変更量も少なく容易
である。In this test method, only the sample scanning line data and the image signal creation information data need to be changed, and the amount of change is small and easy.
（５）効果の説明 以上説明したように９本発明の試験方式は。(5) Explanation of effects As explained above, the test method of the present invention is as follows.
膨大な試験用画信号を少量のサンプル走査線データと画
信号作成情報データにより作成するため。To create a huge amount of test image signals using a small amount of sample scanning line data and image signal creation information data.
制御装置に外部記憶装置や画信号入力装置等を接続する
必要がなく、少ない試験データで認識処理装置の認識処
理機能を試験できる利点がある。There is no need to connect an external storage device, an image signal input device, etc. to the control device, and there is an advantage that the recognition processing function of the recognition processing device can be tested with a small amount of test data.
また、認識処理装置の認識処理機能の変更においても、
少量の試験データの変更で容易に対処可能な利点がある
。Also, when changing the recognition processing function of the recognition processing device,
This has the advantage of being easily handled by changing a small amount of test data.
第１図は本発明による画信号作成方法の一例を示す図、
第２図は本発明の一実施例システムの構成図である。
図中、１乃至５はサンプル走査線、６．７は画信号、８
は制御装置、９は認識処理装置、１０は制御部、１１は
画信号作成情報データメモリ。
１２はサンプル走査線データメモリ、１３は画信号バッ
ファ、１４は正解データメモリを示す。
特許出願人 日本電信電話公社
代理人弁理士 森 １） 寛
才 １ 図
才 ２ 図FIG. 1 is a diagram showing an example of the image signal creation method according to the present invention;
FIG. 2 is a configuration diagram of a system according to an embodiment of the present invention. In the figure, 1 to 5 are sample scanning lines, 6.7 is an image signal, and 8
9 is a control device, 9 is a recognition processing device, 10 is a control unit, and 11 is an image signal creation information data memory. 12 is a sample scanning line data memory, 13 is an image signal buffer, and 14 is a correct data memory. Patent applicant Nippon Telegraph and Telephone Public Corporation Patent attorney Mori 1) Hirozai 1 Zuzai 2 Diagram
Claims (2)
りマークあるいは数字等の情報を抽出して認識処理を行
ない、認識結果を前記制御装置に返送する機能を有する
認識処理装置の機能試験において。 前記制御装置にｎ本のサンプル走査線と画信号作成情報
と認識結果の正解データとをあらかじめ記憶し、前記制
御装置は前記画信号作成情報にもとづいて前記ｎ本のサ
ンプル走査線を組み合せることにより画信号を作成し、
前記画信号を前記認識処理装置に送出し、前記認識処理
装置よりその認識結果を受取り、前記認識結果を前記正
解デブ゛りと照合することにより前記認識処理装置の正
常性を判別することを特徴とする認識処理装置の試験方
式。(1) In a functional test of a recognition processing device that has a function of receiving an image signal from a control device, extracting information such as marks or numbers from the image signal, performing recognition processing, and sending the recognition result back to the control device. n sample scanning lines, image signal generation information, and correct data of recognition results are stored in advance in the control device, and the control device combines the n sample scanning lines based on the image signal generation information. Create an image signal by
The image signal is sent to the recognition processing device, the recognition result is received from the recognition processing device, and the normality of the recognition processing device is determined by comparing the recognition result with the correct answer data. A test method for recognition processing devices.
化されでいることを特徴とする特許請求の範囲オ（１）
項記載の認識処理装置の試験方式。(2) Claim (1) characterized in that the n sample scanning lines are redundancy suppressed encoded.
Test method for the recognition processing device described in Section 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57195679A JPS5985581A (en) | 1982-11-08 | 1982-11-08 | Test system of recognition processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57195679A JPS5985581A (en) | 1982-11-08 | 1982-11-08 | Test system of recognition processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS5985581A true JPS5985581A (en) | 1984-05-17 |
| JPH0142022B2 JPH0142022B2 (en) | 1989-09-08 |
Family
ID=16345193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP57195679A Granted JPS5985581A (en) | 1982-11-08 | 1982-11-08 | Test system of recognition processor |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS5985581A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63123169A (en) * | 1986-11-12 | 1988-05-26 | Fujitsu Ltd | Image inputting and coupling unit |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5439702A (en) * | 1977-07-08 | 1979-03-27 | Westinghouse Electric Corp | Device for controlling pump and turbine which supply water to boiler |
| JPS5585976A (en) * | 1978-12-22 | 1980-06-28 | Omron Tateisi Electronics Co | Pattern recognizing system |
-
1982
- 1982-11-08 JP JP57195679A patent/JPS5985581A/en active Granted
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5439702A (en) * | 1977-07-08 | 1979-03-27 | Westinghouse Electric Corp | Device for controlling pump and turbine which supply water to boiler |
| JPS5585976A (en) * | 1978-12-22 | 1980-06-28 | Omron Tateisi Electronics Co | Pattern recognizing system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63123169A (en) * | 1986-11-12 | 1988-05-26 | Fujitsu Ltd | Image inputting and coupling unit |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH0142022B2 (en) | 1989-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US4566039A (en) | Facsimile system | |
| JPS5985581A (en) | Test system of recognition processor | |
| JPH04293106A (en) | Remote diagnostic device of numerical controller | |
| JPH0693245B2 (en) | Form information compression method | |
| JP2570815B2 (en) | Optical character recognition device | |
| JPS59158482A (en) | Character recognizing device | |
| JPS622744A (en) | Transmission control circuit | |
| JPS6313567A (en) | Graphic display device for electronic conference system | |
| JPS58111562A (en) | Facsimile transmission system | |
| JP2917367B2 (en) | Character recognition device | |
| JP2790276B2 (en) | Character reader | |
| JPS62177686A (en) | Optical character reader | |
| JPH05197837A (en) | Business card reader | |
| JPS62160590A (en) | Format generating system for character reader | |
| JPS5857854A (en) | Multilex processor for remote input character recognition | |
| JPS6363954B2 (en) | ||
| JPH03230287A (en) | Information transmission and reception system | |
| JPS61133776A (en) | Image data compression device | |
| JPH043099A (en) | Voice recognition processor | |
| JPS61172481A (en) | Form information compressing method | |
| JPS6337735A (en) | Data conversion system in communication processor | |
| JPS61128678A (en) | Image information processing system | |
| JPH04334169A (en) | 2-dimension coder | |
| JPH02272689A (en) | Optical character reader | |
| JPH0962531A (en) | Test result matching method |