JP2002133422A - Automatic detecting device for inclination of image - Google Patents

Automatic detecting device for inclination of image

Info

Publication number
JP2002133422A
JP2002133422A JP2000330807A JP2000330807A JP2002133422A JP 2002133422 A JP2002133422 A JP 2002133422A JP 2000330807 A JP2000330807 A JP 2000330807A JP 2000330807 A JP2000330807 A JP 2000330807A JP 2002133422 A JP2002133422 A JP 2002133422A
Authority
JP
Japan
Prior art keywords
image
mask pattern
inclination
inspection
calculating
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
JP2000330807A
Other languages
Japanese (ja)
Inventor
Bokujiyu Imai
睦樹 今井
Kazuyoshi Takahashi
一義 高橋
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.)
TORAI TEC KK
Original Assignee
TORAI TEC KK
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 TORAI TEC KK filed Critical TORAI TEC KK
Priority to JP2000330807A priority Critical patent/JP2002133422A/en
Publication of JP2002133422A publication Critical patent/JP2002133422A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Analysis (AREA)

Abstract

PROBLEM TO BE SOLVED: To provide a device for automatically, accurately calculating and correcting the inclination of an image at high speed by installing a mask pattern having inclination and calculating the correlation between an image for inclination inspection and the mask pattern, to be efficiently used in an inspection device for various images, such as an inspection device for an OCR or a printing matter. SOLUTION: In order to solve problems that an image having no register frequently appears in an inspection object image to make automatic inspection impossible and a means for automatically judging inclination has not yet reached to a practical level from the standpoint of processing speed and accuracy, the mask pattern having inclination is installed and a means calculating a frequency at which the image is present on the mask pattern and judging that the inclination of the mask pattern in the smallest frequency is the same as the inclination of the image is installed.

Description

【発明の詳細な説明】DETAILED DESCRIPTION OF THE INVENTION

【0001】[0001]

【発明が属する技術分野】本発明はスキャナー等の画像
読取り装置を使った画像検査装置において自動的に画像
の傾き量を計算し補正する技術に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technique for automatically calculating and correcting the amount of tilt of an image in an image inspection apparatus using an image reading device such as a scanner.

【0002】[0002]

【従来の技術】従来、画像の傾きを算出する手段として
は、画像の4隅または3隅に位置検出用の基準画像(以
下、トンボ)を形成し、トンボの位置を見て画像の傾き
を算出していた。第5図にその例を示す。
2. Description of the Related Art Conventionally, as means for calculating the inclination of an image, a reference image (hereinafter referred to as a register mark) for position detection is formed at four or three corners of the image, and the inclination of the image is determined by observing the position of the register mark. Was calculated. Fig. 5 shows an example.

【0003】[0003]

【0004】[0004]

【発明が解決しようとする課題】しかし、検査したい画
像にはトンボを持たない画像がたびたび発生し、自動検
査が実現できなかった。または、自動的に傾きを判断す
る手段が存在したかもしれないが、処理速度と精度の問
題からから実用レベルには達していなかった。
However, an image to be inspected often has no registration mark, and automatic inspection cannot be realized. Alternatively, there may have been means for automatically judging the inclination, but it has not reached a practical level due to problems in processing speed and accuracy.

【課題を解決するための手段】[Means for Solving the Problems]

【0005】本発明では傾きを持つマスクパターンを設
け、マスクパターン上に画像が存在する頻度を計算して
頻度が最も小さい場合のマスクパターンの傾きと画像の
傾きが同じと判断する手段を設ける。
In the present invention, a mask pattern having an inclination is provided, and a means is provided for calculating the frequency at which an image is present on the mask pattern and determining that the inclination of the mask pattern is the same as the inclination of the image when the frequency is the lowest.

【発明の実施の形態】BEST MODE FOR CARRYING OUT THE INVENTION

【0006】本発明では、傾きを持つマスクパターンを
設けて傾き検査用の画像との相関を算出する事で、高速
で精度の高い画像の傾きを自動で算出及び補正する装置
を実現出来た。
According to the present invention, a device for automatically calculating and correcting a high-speed and high-precision image inclination can be realized by providing a mask pattern having an inclination and calculating a correlation with an image for inclination inspection.

【実施例】本発明の実施例の構成図を第1図に示す。1
は傾きを持つマスクパターンである。2は検査画像であ
る。マスクパターンは、第2図に示すように予想される
画像の傾き量を網羅できるように用意する。ある傾きの
マスクパターンで2の検査画像上にマスクパターンを矢
印の方向に1画素ずつ滑らせていく。各位置において、
マスクパターン上の画像が存在する場合は、頻度データ
に+1をする。ない場合は加算しない。この様にして画
像の先端から画像の後端までマスクパターンを滑らせて
頻度の合計を算出する。これに依りある画像に対してあ
る傾き(マスクパターン)における頻度(一致率)が求
まった事になる。ここで検査画像の特性について説明す
る。本発明で、検査の対象とする画像は横書きの文書画
像及び文章に画像が含まれている場合である。こういう
画像の特徴は水平方向に画像が並んでいるという事であ
る。本発明では、検査画像のこの特徴を利用して、傾き
を持つマスクパターンを提案し、マスクパターンと検査
画像との関係を調べて傾き量を計算している。第3図に
本発明の適用例を示す。横軸はマスクパターンの傾き量
を表す。縦軸は上記説明のように各マスクパターンに対
して、画像が存在する頻度をしめす。マスクパターンの
傾きと検査画像の傾きが一致しているほど頻度は小さく
なる。いろいろな画像で検討した結果、第3図において
頻度が3回続けて上がり続けるか同じ値を持つ場合に、
傾きが一致したと判断すればいい事が判った。ここでは
3回と言ったが回数はマスクパターンの作り方や検査対
象画像の特徴によることは言うまでもない。第4図に縦
書きの画像の場合を示す。これは第1図に対してマスク
パターンが90度傾いている事が判る。こうすれば縦書
き画像でも同様に入力画像の傾きが自動に判断する事が
出来る事は容易に推測できる。傾き量が判ったらそれを
補正する方法は複数提案されている。本発明の主眼は傾
き量の自動算出にあり補正についての説明は本明細書で
は割愛する。
FIG. 1 is a block diagram showing an embodiment of the present invention. 1
Is a mask pattern having an inclination. 2 is an inspection image. The mask pattern is prepared so as to cover the expected amount of tilt of the image as shown in FIG. The mask pattern is slid one pixel at a time in the direction of the arrow on the two inspection images with the mask pattern having a certain inclination. At each position,
If there is an image on the mask pattern, +1 is added to the frequency data. If not, do not add. In this way, the mask pattern is slid from the leading edge of the image to the trailing edge of the image to calculate the total frequency. This means that the frequency (coincidence rate) of a certain image at a certain inclination (mask pattern) has been obtained. Here, the characteristics of the inspection image will be described. In the present invention, an image to be inspected is a horizontally written document image and a case where an image is included in a sentence. The feature of such an image is that the images are arranged in the horizontal direction. In the present invention, a mask pattern having an inclination is proposed using this characteristic of the inspection image, and the amount of inclination is calculated by examining the relationship between the mask pattern and the inspection image. FIG. 3 shows an application example of the present invention. The horizontal axis represents the amount of tilt of the mask pattern. The vertical axis indicates the frequency at which an image exists for each mask pattern as described above. The frequency decreases as the inclination of the mask pattern matches the inclination of the inspection image. As a result of examining various images, if the frequency continues to increase three times or has the same value in Fig. 3,
It turns out that it is only necessary to judge that the inclinations match. Here, the number of times is three, but it goes without saying that the number of times depends on the method of forming the mask pattern and the characteristics of the inspection target image. FIG. 4 shows a case of a vertically written image. This indicates that the mask pattern is inclined by 90 degrees with respect to FIG. In this way, it can be easily guessed that the inclination of the input image can be automatically determined in the vertical writing image. If the amount of inclination is known, a plurality of methods for correcting it are proposed. The focus of the present invention is on the automatic calculation of the tilt amount, and the description of the correction is omitted in this specification.

【発明の効果】以上説明したように、本発明の画像傾き
検出装置は、高速で高い信頼性を持ち入力画像の傾きを
算出できる事が可能になった。本発明は各種の画像の検
査装置において高い効果を発生する。OCRや印刷物の
検査装置等で有効である。
As described above, the image inclination detecting apparatus of the present invention can calculate the inclination of an input image at high speed and with high reliability. The present invention produces high effects in various image inspection apparatuses. It is effective in an OCR or a printed matter inspection device.

【00007】[0000]

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

【図1】本発明の中心であり、マスクパターンと検査画
像の関係を示す。
FIG. 1 is the center of the present invention and shows the relationship between a mask pattern and an inspection image.

【図2】マスクパターンの説明図FIG. 2 is an explanatory diagram of a mask pattern.

【図3】本発明の適用例FIG. 3 is an application example of the present invention.

【図4】縦書きの画像に対するマスクパターンと検査画
像の関係。
FIG. 4 shows a relationship between a mask pattern and an inspection image for a vertically written image.

【図5】傾きの補正手段の例FIG. 5 shows an example of a tilt correcting unit.

【00008】[0108]

【符号の説明】 1 マスクパターン 2 検査画像[Description of Signs] 1 Mask pattern 2 Inspection image

【00009】[0000]

─────────────────────────────────────────────────────
────────────────────────────────────────────────── ───

【手続補正書】[Procedure amendment]

【提出日】平成13年2月5日(2001.2.5)[Submission date] February 5, 2001 (2001.2.5)

【手続補正2】[Procedure amendment 2]

【補正対象書類名】明細書[Document name to be amended] Statement

【補正対象項目名】図面の簡単な説明[Correction target item name] Brief description of drawings

【補正方法】変更[Correction method] Change

【補正内容】[Correction contents]

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

【図1】本発明の中心であり、マスクパターンと検査画
像の関係を示す。
FIG. 1 is the center of the present invention and shows the relationship between a mask pattern and an inspection image.

【図2】マスクパターンの説明図FIG. 2 is an explanatory diagram of a mask pattern.

【図3】本発明の適用例FIG. 3 is an application example of the present invention.

【図4】縦書きの画像に対するマスクパターンと検査画
像の関係。
FIG. 4 shows a relationship between a mask pattern and an inspection image for a vertically written image.

【図5】傾きの補正手段の例FIG. 5 shows an example of a tilt correcting unit.

【符号の説明】 1 マスクパターン 2 検査画像[Description of Signs] 1 Mask pattern 2 Inspection image

Claims (4)

【特許請求の範囲】[Claims] 【請求項1】画像を入力して所定の検査を行なう画像検
査装置において、該入力画像に対して自動的にその傾き
量を算出する機能を有し、該傾き量算出手段として、マ
スクパターンを設け、該マスクパターンの傾きを変化さ
せて、該入力画像との間の一致率を算出し、該一致率を
もって該入力画像の傾き量を算出する事を特徴とする画
像検査装置。
An image inspection apparatus for inputting an image and performing a predetermined inspection has a function of automatically calculating a tilt amount of the input image, and a mask pattern is used as the tilt amount calculating means. An image inspection apparatus, comprising: changing a tilt of the mask pattern, calculating a coincidence rate with the input image, and calculating a tilt amount of the input image using the coincidence rate.
【請求項2】前記1において、該マスクパターンは傾き
をもつ1ラインの線分とし、該マスクパターンを該入力
画像に沿って移動させ、各位置において該マスクパター
ン上に画像が存在する場合を1として、存在しない場合
を0として、該検査画像全体における該マスクパターン
上に画像が存在するライン数の総計を算出し、該総計値
が最も小さな値であるマスクパターンをもって傾き量と
する事を特徴とする画像検査装置。
2. The method according to claim 1, wherein the mask pattern is a line segment having one inclination, the mask pattern is moved along the input image, and an image is present on the mask pattern at each position. Assuming that the number of lines where an image exists on the mask pattern in the entire inspection image is calculated as 1 and the total number of lines where the image exists on the mask pattern in the entire inspection image is set as 0, and that the mask pattern having the smallest total value is used as the inclination amount Characteristic image inspection device.
【請求項3】前記1及び2において、該総計値が最も小
さな値のマスクパターンを選択する方法として所定回数
連続して該総計値が増えた場合は、該マスクパターンの
傾き量の変化方向と該入力画像の傾きが逆であると判断
し、所定回数連続して該総計値が減少した場合は、該マ
スクパターンの傾き量の変化方向と該入力画像の傾きが
同じであると判断する事を特徴とする画像検査装置。
3. The method according to 1 or 2, wherein the total value increases continuously for a predetermined number of times as a method of selecting a mask pattern having the smallest total value. If the inclination of the input image is determined to be opposite and the total value decreases continuously for a predetermined number of times, it is determined that the direction of change in the amount of inclination of the mask pattern and the inclination of the input image are the same. An image inspection apparatus characterized by the above-mentioned.
【請求項4】前記1において、横書きまたは縦書きの該
入力画像に対して、該マスクパターンの傾きを90度切
り換える事を特徴とする画像検査装置。
4. The image inspection apparatus according to claim 1, wherein the inclination of the mask pattern is switched by 90 degrees with respect to the input image written horizontally or vertically.
JP2000330807A 2000-10-30 2000-10-30 Automatic detecting device for inclination of image Pending JP2002133422A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2000330807A JP2002133422A (en) 2000-10-30 2000-10-30 Automatic detecting device for inclination of image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2000330807A JP2002133422A (en) 2000-10-30 2000-10-30 Automatic detecting device for inclination of image

Publications (1)

Publication Number Publication Date
JP2002133422A true JP2002133422A (en) 2002-05-10

Family

ID=18807259

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2000330807A Pending JP2002133422A (en) 2000-10-30 2000-10-30 Automatic detecting device for inclination of image

Country Status (1)

Country Link
JP (1) JP2002133422A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006222878A (en) * 2005-02-14 2006-08-24 Konica Minolta Business Technologies Inc Image processor, image processing method and image processing program

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006222878A (en) * 2005-02-14 2006-08-24 Konica Minolta Business Technologies Inc Image processor, image processing method and image processing program
JP4552681B2 (en) * 2005-02-14 2010-09-29 コニカミノルタビジネステクノロジーズ株式会社 Image processing apparatus, image processing method, and image processing program
US7925115B2 (en) 2005-02-14 2011-04-12 Konica Minolta Business Technologies, Inc. Image processing device capable of detecting and correcting inclination of image

Similar Documents

Publication Publication Date Title
US8848244B2 (en) Image inspection method, apparatus, control program overlapping inspection images to obtain positional shift
US9536297B2 (en) Apparatus, system, and method of inspecting image, and recording medium storing image inspection control program
JP3998334B2 (en) Defect inspection method
US7024041B2 (en) Pattern inspection apparatus and method
JPH0789063A (en) Printed matter inspecting system
JP6323190B2 (en) Inspection apparatus, image forming apparatus, and image inspection method
JP7350637B2 (en) High-speed image distortion correction for image inspection
JP2011076204A (en) Method and apparatus for inspecting printed matter
JP2002005846A (en) Defect inspecting apparatus
CN111007086A (en) Defect detection method and device and storage medium
JP5852641B2 (en) Automatic inspection device and alignment method in automatic inspection device
US10325353B2 (en) Image processing apparatus
JP2002133422A (en) Automatic detecting device for inclination of image
JP3187107B2 (en) Pattern inspection equipment
US10911636B2 (en) Image inclination angle detection apparatus that detects inclination angle of image with respect to document, image forming apparatus, and computer-readable non-transitory recording medium storing image inclination angle detection program
JP2005091331A (en) Inspection device and method of printed matter
JP4285253B2 (en) Image inspection device with tilt detection function
JPH09133514A (en) Image measuring system
JPS61277248A (en) Method and device for discriminating picture quality of picture reader
JP2015156166A (en) Map correction method and map correction device
JP2002236925A (en) Image inspection device
JP2006054516A (en) Image processing apparatus and image correction method
JP2009069951A (en) Character recognition device and character recognition method in character recognition device
CN108846863B (en) Position detection method and device for positioning mark, computer and storage medium
JP3916596B2 (en) Image position correcting apparatus and method

Legal Events

Date Code Title Description
A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20050909

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20050928

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20060228