Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
JP2864510B2 - Shape discriminator - Google Patents
[go: Go Back, main page]

JP2864510B2 - Shape discriminator - Google Patents

Shape discriminator

Info

Publication number
JP2864510B2
JP2864510B2 JP63300296A JP30029688A JP2864510B2 JP 2864510 B2 JP2864510 B2 JP 2864510B2 JP 63300296 A JP63300296 A JP 63300296A JP 30029688 A JP30029688 A JP 30029688A JP 2864510 B2 JP2864510 B2 JP 2864510B2
Authority
JP
Japan
Prior art keywords
image
contour
work
shape
workpiece
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 - Lifetime
Application number
JP63300296A
Other languages
Japanese (ja)
Other versions
JPH02144774A (en
Inventor
弘道 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.)
Pentel Co Ltd
Original Assignee
Pentel Co 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 Pentel Co Ltd filed Critical Pentel Co Ltd
Priority to JP63300296A priority Critical patent/JP2864510B2/en
Publication of JPH02144774A publication Critical patent/JPH02144774A/en
Application granted granted Critical
Publication of JP2864510B2 publication Critical patent/JP2864510B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Landscapes

  • Length Measuring Devices By Optical Means (AREA)
  • Image Analysis (AREA)

Description

【発明の詳細な説明】 [産業上の利用分野] 本発明はワークの形状判別装置に関し、構成を簡略化
した画像処理を、重ね合せ合成により実現できるように
したものである。
DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention relates to a work shape discriminating apparatus, which is capable of realizing image processing with a simplified configuration by superposition synthesis.

[従来の技術] 従来、ワークの形状を判別するものとして、ワークの
特徴点に対しフォトリフレクターを近接させて判別する
か、複雑な形状のワークに対してはTVカメラ等の撮像装
置を用いて撮像した画像に対応した画像処理(例えば画
像の輪郭を抽出してパターンマッチングを行う。)を行
っていた。
[Prior art] Conventionally, the shape of a work is determined by approaching a photoreflector to a feature point of the work, or by using an imaging device such as a TV camera for a work having a complicated shape. Image processing (for example, extracting the contour of the image and performing pattern matching) corresponding to the captured image has been performed.

前者のフォトリフレクターを用いる場合は、ワーク形
状の特徴点を見出すのに熟練を要し、ワーク形状が複雑
になると素子の数が増加するという問題点があり、後者
の画像処理を行う場合は、一画面分の処理を行うのに装
置が複雑になり、画素数に応じて時間がかかるという問
題点があった。
In the case of using the former photoreflector, skill is required to find the feature points of the work shape, and there is a problem that the number of elements increases when the work shape becomes complicated.In the case of performing the latter image processing, There is a problem that the apparatus becomes complicated to perform processing for one screen, and it takes time according to the number of pixels.

[課題を解決するための手段] 本発明は如上の従来の問題点に鑑みなされたもので、
判別されるワークを映像化する撮像手段と、該撮像手段
からのワーク映像を輪郭抽出する手段と、該輪郭抽出さ
れた画像を複数に分割し、分割された画像を重ね合せ合
成する手段と、該合成手段で合成された画像と予め作成
されている標準パターンと比較する比較手段とからなる
形状判別装置を提案するものである。
[Means for Solving the Problems] The present invention has been made in view of the above conventional problems.
Imaging means for imaging the work to be determined, means for extracting a contour of the work video from the imaging means, means for dividing the contour-extracted image into a plurality of pieces, and superimposing and combining the divided images; The present invention proposes a shape discriminating apparatus including an image synthesized by the synthesizing means and a comparing means for comparing the image with a standard pattern created in advance.

[作用] 撮像されたワークの映像の輪郭を抽出し、この抽出さ
れた輪郭を複数に分割した画像毎に重ね合せ、この重ね
合わされた輪郭データと、標準パターンのデータと比較
照合して、判別されるワークの良否を決定する。
[Operation] An outline of a captured image of a workpiece is extracted, and the extracted outline is superimposed on each of a plurality of divided images. The quality of the work to be performed is determined.

[実施例] 本発明の一実施例を添付図面を参照して説明する。第
1図は全体のブロック図、第2図はワークの撮像画像、
第3図の輪郭画像、第4図は重ね合せ画像を示すもので
ある。ワーク保持台11上には形状を判別されるワーク10
が載置され、このワーク10は撮像素子としてのTVカメラ
1で映像化される。TVカメラ1で映像化された信号は、
増幅器2で増幅され2値化回路3へ印加され、(第2図
参照)、この2値化回路3は簡単な図形の場合はコンパ
レータで構成され、複雑な図形の場合はAD変換の後ソフ
トウェアで2値化するもので、映像信号を明暗の2値に
変換し、画像メモリ4へ印加し記憶する。このとき、ワ
ーク10の背景を明るく照明し、ワーク10に照明が当らな
い構成にすることにより、ワーク10はシルエット状の画
像として捉えられ、比較的簡単に2値化することができ
る。画像メモリ4に記憶された2値化画像は、輪郭抽出
回路5により輪郭部分が抽出される(第3図参照)。輪
郭の抽出の手段としては、明暗の2値化画像の場合微分
法を用いることにより、比較的簡単に抽出することが可
能である。また、2値化画像の輪郭に局所的な凹凸が含
まれるような場合は、近傍法を用いて平滑化を行った
後、輪郭抽出を行うことにより、スムーズな輪郭線を得
ることができる。重ね合せ回路6は、抽出された輪郭を
分割数に応じた形で重ね合せ輪郭メモリ7に記憶する。
重ね合せ回路6は、第3図に示す分割画像としての領域
1〜4のそれぞれを順次読み出し、重ね合せ画像メモリ
7へ書き込む。書き込み手段としては、各領域画像1〜
4を論理和(OR)にて重ね合せ、また、輪郭画像が局所
的に集中するような場合には、排他的論理和(EXOR)を
利用して集中した重なりを排除しても良い。(第4図参
照) 制御回路8は、今迄述べた手順により予め準備されて
いる標準パターンを、標準パターンファイル9から読み
出し、比較回路10にて重ね合せ輪郭メモリ7のパターン
と、標準パターンとを比較することによりワーク10の良
否を判別する。ワーク保持台11とワーク10が同一であれ
ば、撮像画像(第2図)、輪郭画像(第3図)は単純な
重ね合せ(テンプレートマッチング)法で行うことがで
きる。また、ワーク形状に応じてより精度の高い相関法
をも採用できる。
Embodiment An embodiment of the present invention will be described with reference to the accompanying drawings. FIG. 1 is an overall block diagram, FIG. 2 is a captured image of a work,
FIG. 3 shows a contour image, and FIG. 4 shows a superimposed image. The work 10 whose shape is to be determined on the work holding table 11
The work 10 is imaged by the TV camera 1 as an image sensor. The signal imaged by the TV camera 1 is
The signal is amplified by an amplifier 2 and applied to a binarization circuit 3 (see FIG. 2). The binarization circuit 3 is composed of a comparator for a simple figure, and is converted to a software after an AD conversion for a complex figure. The video signal is converted into a binary value of light and dark, and is applied to the image memory 4 and stored. At this time, by illuminating the background of the workpiece 10 brightly and not illuminating the workpiece 10, the workpiece 10 can be captured as a silhouette image and can be binarized relatively easily. The outline portion is extracted from the binarized image stored in the image memory 4 by the outline extraction circuit 5 (see FIG. 3). As a means for extracting the contour, in the case of a light and dark binary image, it is possible to relatively easily extract the image by using a differentiation method. In the case where the contour of the binarized image includes local irregularities, a smooth contour line can be obtained by performing smoothing using the neighborhood method and then performing contour extraction. The superimposition circuit 6 stores the extracted contour in the superimposed contour memory 7 in a form corresponding to the number of divisions.
The superposition circuit 6 sequentially reads out each of the areas 1 to 4 as the divided images shown in FIG. As the writing means, each of the area images 1 to
4 are superimposed by a logical sum (OR), and when the contour images are locally concentrated, an exclusive logical sum (EXOR) may be used to eliminate the concentrated overlap. (Refer to FIG. 4.) The control circuit 8 reads out the standard pattern prepared in advance from the standard pattern file 9 according to the procedure described above, and the comparison circuit 10 compares the standard pattern with the pattern in the superimposed contour memory 7. Are compared, the quality of the work 10 is determined. If the work holding table 11 and the work 10 are the same, the captured image (FIG. 2) and the outline image (FIG. 3) can be performed by a simple superposition (template matching) method. Further, a more accurate correlation method can be adopted according to the work shape.

[発明の効果] 本発明は如上のような構成となしたので、比較すべき
画像のメモリの容量が小さくて済み、処理速度が向上す
るものである。更に標準パターンとして標準するものも
1/n(nは分割数)となることから、比較的安価に高精
度の形状記憶を実施できるものである。
[Effects of the Invention] Since the present invention is configured as described above, the memory capacity of the image to be compared can be small, and the processing speed can be improved. In addition, some standard patterns
Since it is 1 / n (n is the number of divisions), highly accurate shape storage can be performed relatively inexpensively.

尚、実施例として4分割の例を示したが、ワークの複
雑さに応じて分割数を変えることもでき、実施例として
一方向のみの判別で示したが、ワーク形状によっては複
数の方向からのパターンを準備し、最適な方向を選択し
て方向を順次変えて比較を行うことにより、ワーク保持
の自由度を増すこともできるものである。
Although an example of four divisions has been described as an example, the number of divisions can be changed according to the complexity of a work, and in the example, determination is made in only one direction. By preparing the pattern described above, selecting the optimum direction, and sequentially changing the direction to perform comparison, the degree of freedom in holding the work can be increased.

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

図面は、本発明の実施例であり、第1図は全体のブロッ
ク図、第2図は撮像画像、第3図は輪郭画像、第4図は
重ね合せ画像である。 1……TVカメラ,2……増幅器、3……2値化回路,4……
画像メモリ,5……輪郭抽出回路,6……重ね合わ回路,7…
…重ね合せ輪郭メモリ,8……制御回路,9……標準パター
ンファイル,10……比較回路
1 is an overall block diagram, FIG. 2 is a captured image, FIG. 3 is a contour image, and FIG. 4 is a superimposed image. 1 TV camera 2 Amplifier 3 Binarization circuit 4 4
Image memory, 5 ... Contour extraction circuit, 6 ... Superposition circuit, 7 ...
... superimposed contour memory, 8 ... control circuit, 9 ... standard pattern file, 10 ... comparison circuit

Claims (1)

(57)【特許請求の範囲】(57) [Claims] 【請求項1】判別されるワークを映像化する撮像手段
と、該撮像手段からのワーク映像を輪郭抽出する手段
と、該輪郭抽出された画像を所定の数に分割し、分割さ
れた画像を所定の方向に重ね合わせ合成する手段と、該
合成手段で合成された画像と予め作成されている標準パ
ターンと比較する比較手段とを有することを特徴とする
形状判別装置。
1. An imaging means for visualizing a workpiece to be determined, a means for extracting a contour of a workpiece video from the imaging means, dividing the contour-extracted image into a predetermined number, and dividing the divided image. A shape discriminating apparatus comprising: means for superimposing and synthesizing in a predetermined direction; and comparing means for comparing an image synthesized by the synthesizing means with a standard pattern created in advance.
JP63300296A 1988-11-28 1988-11-28 Shape discriminator Expired - Lifetime JP2864510B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP63300296A JP2864510B2 (en) 1988-11-28 1988-11-28 Shape discriminator

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP63300296A JP2864510B2 (en) 1988-11-28 1988-11-28 Shape discriminator

Publications (2)

Publication Number Publication Date
JPH02144774A JPH02144774A (en) 1990-06-04
JP2864510B2 true JP2864510B2 (en) 1999-03-03

Family

ID=17883078

Family Applications (1)

Application Number Title Priority Date Filing Date
JP63300296A Expired - Lifetime JP2864510B2 (en) 1988-11-28 1988-11-28 Shape discriminator

Country Status (1)

Country Link
JP (1) JP2864510B2 (en)

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS58161082A (en) * 1982-03-19 1983-09-24 Fujitsu Ltd Collating system of seal impression

Also Published As

Publication number Publication date
JPH02144774A (en) 1990-06-04

Similar Documents

Publication Publication Date Title
KR102680424B1 (en) High-resolution image synthesis method for semiconductor defect inspection
JPH0791927A (en) Three dimensional measuring device
JP2864510B2 (en) Shape discriminator
JPH0664614B2 (en) Hierarchical structured template matching method
JPH07107379A (en) Still image capturing device
CN114742882A (en) Alignment algorithm for single-pixel closed-loop framework alignment
JPH10213420A (en) Reference image creation method used for pattern matching
JP2678940B2 (en) Shape discriminator
JPH05307608A (en) Image processing method and image processing apparatus
JPH10332333A (en) Method for detecting angle of rotation and position of object
JP3611225B2 (en) Core and main position detector
JPH03158709A (en) Recognizing device for solid body shape
JP3271889B2 (en) Edge detection method for recognition target
JPH06325156A (en) Method and device for character shape inspection
JPH0566636B2 (en)
JPH11238136A (en) Texture acquisition method and texture acquisition system
JP2564736Y2 (en) Shading image processing device
JP2864815B2 (en) Image feature information integration device
JPH02257006A (en) Shape discriminating device
JPH05297950A (en) Object positioning device
JP2001250107A (en) Method and device for recognizing processed area of plate material and computer-readable recording medium with recorded program for performing processed area recognition of plate material
JPH08279034A (en) Image synthesis processing method and scanner
JPS60167071A (en) Stamp shape reader
JPH0290374A (en) Positioning device and image processing LSI circuit
JPH07124121A (en) Image processing device