JPH04142412A - Defect inspecting device - Google Patents
Defect inspecting deviceInfo
- Publication number
- JPH04142412A JPH04142412A JP26522590A JP26522590A JPH04142412A JP H04142412 A JPH04142412 A JP H04142412A JP 26522590 A JP26522590 A JP 26522590A JP 26522590 A JP26522590 A JP 26522590A JP H04142412 A JPH04142412 A JP H04142412A
- Authority
- JP
- Japan
- Prior art keywords
- defect
- type
- neural network
- output
- grade
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 claims abstract description 34
- 230000001537 neural effect Effects 0.000 claims abstract description 9
- 210000002569 neuron Anatomy 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 2
- 229910009445 Y1-Ym Inorganic materials 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 5
- 238000000034 method Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
【発明の詳細な説明】
〔発明の目的〕
(産業上の利用分野)
この発明は、鋼板やアルミニウム板などの帯状物の表面
を光電的に走査、撮像して表面の欠陥を調べる欠陥検査
装置に間し、特に、欠陥の種類や等級(程度)の判定の
情報処理をニューラルネットで行う技術に関する。[Detailed Description of the Invention] [Objective of the Invention] (Industrial Application Field) The present invention is a defect inspection device that photoelectrically scans and images the surface of a strip-shaped object such as a steel plate or an aluminum plate to check for defects on the surface. In particular, the present invention relates to technology that uses neural networks to process information for determining the type and grade (degree) of defects.
(従来の技術)
従来の一般的な欠陥検査装置では、欠陥の種類および程
度の判定は、抽出された欠陥の特徴量を統計的に処理し
たり、枝分れロジックを用いて行われている。この判定
の情報処理にニューラルネットを導入する場合、安易に
思いつくのは第4図に示すシステム構成である。(Prior art) In conventional general defect inspection equipment, the type and degree of defects are determined by statistically processing extracted feature quantities of defects or by using branching logic. . When introducing a neural network to information processing for this determination, the system configuration shown in FIG. 4 is easily thought of.
第4図において、検出器1は、矢印7方向に搬送される
帯状の検査対象5の表面を光電的に走査、撮像する。特
徴抽出回路2は、検出器1の画像信号から検査対象5の
表面欠陥6の特徴量を抽出する。In FIG. 4, the detector 1 photoelectrically scans and images the surface of a strip-shaped inspection object 5 that is conveyed in the direction of an arrow 7. The feature extraction circuit 2 extracts the feature amount of the surface defect 6 of the inspection object 5 from the image signal of the detector 1.
第1のニューラルネット3は、抽出された特徴量を入力
として欠陥の種類を判定し、種類別の出力KD、〜KD
、のいずれかを発する。第2のニューラルネット4は、
抽出された特徴量を入力として欠陥の程度(等級)を判
定し、等級別の出力GD、〜G D tのいずれかを出
力する。第1、第2のニューラルネット3.4の重みパ
ラメータは学習によって決まる。The first neural network 3 determines the type of defect using the extracted feature values as input, and outputs KD, ~KD for each type.
, emit one of the following. The second neural net 4 is
The degree (grade) of the defect is determined using the extracted feature quantity as input, and one of the outputs GD and -G D t for each grade is output. The weight parameters of the first and second neural networks 3.4 are determined by learning.
(発明が解決しようとする課題)
第4図のようなシステム構成の場合、学習に非常に時間
がかかるし、欠陥の程度の判定が適切に行えないという
問題がある。(Problems to be Solved by the Invention) In the case of the system configuration as shown in FIG. 4, there are problems in that learning takes a very long time and the degree of defects cannot be appropriately determined.
熟練した検査員が目視で検査する場合、欠陥の種類によ
って等級判定のしかたを微妙に変えているが、第4図の
システムにはこのように種類判定と等級判定とを結びつ
ける要素がなく、適切な等級判定が行えない。When a skilled inspector performs a visual inspection, the method of grading varies slightly depending on the type of defect, but the system shown in Figure 4 does not have an element that connects type and grading in this way, so it is not possible to properly It is not possible to make accurate grade judgments.
この発明は前述した従来の問題点に鑑みなされたもので
、その目的は、ニューラルネ・ントの学習の収束が速く
、かつ欠陥の種類ごと′に適切に等級判定を行えるよう
にした欠陥検査装置を携供することにある。This invention was made in view of the above-mentioned conventional problems, and its purpose is to provide a defect inspection device that allows neural net learning to converge quickly and that can appropriately grade each type of defect. The purpose is to carry.
(課題を解決するための手段)
そこでこの発明では、特徴抽出回路で抽出した特徴量を
第1のニューラルネットに入力して欠陥の種類を判定す
るように構成するとともに、前記の特徴量と第1のニュ
ーラルネ・ットの判定出力とを第2のニューラルネット
に入力して欠陥の等級を判定するように構成した。(Means for Solving the Problem) Therefore, in the present invention, the feature quantity extracted by the feature extraction circuit is input to the first neural network to determine the type of defect, and the feature quantity and the The second neural network is configured to input the determination output of the first neural network and the second neural network to determine the grade of the defect.
(作用)
第2のニューラルネットによる欠陥の等級判定には、欠
陥の特徴量だけでなく、第1のニューラルネットによる
欠陥の種類の判定結果が反映する。つまり、欠陥の種類
ごとに異なる基準で等級判定を行うことができる。(Operation) In the defect grade determination by the second neural network, not only the feature amount of the defect but also the determination result of the defect type by the first neural network is reflected. In other words, the grade can be determined based on different criteria for each type of defect.
(実施例) 第1図は本発明の基本的な実施例のmtを示している。(Example) FIG. 1 shows mt of a basic embodiment of the invention.
矢印7方向に搬送される検査対象5の表面を検出器1で
撮像し、その画像信号から特徴抽出回N2にて欠陥6の
特徴量を抽出するという横或は従来と同じである。The detector 1 images the surface of the inspection object 5 being conveyed in the direction of the arrow 7, and the feature amount of the defect 6 is extracted from the image signal in the feature extraction step N2, which is the same as in the horizontal or conventional method.
第1のニューラルネット3は、特徴抽出回路2で抽出さ
れた特徴量(XI〜X、)を入力とし、欠陥の種類を判
定して出力(y+〜Y、)を発する。The first neural network 3 inputs the feature amounts (XI to X,) extracted by the feature extraction circuit 2, determines the type of defect, and outputs (y+ to Y,).
第2のニューラルネット4は、特徴抽出回路2で抽出さ
れた特徴量(X +〜X、)と、第1のニューラルネッ
ト3からの欠陥種類の判定出力(Y1〜Y、)とを入力
とし、欠陥種類ごとに欠陥の等級を判定して出力(zl
〜Zt )を発する。The second neural network 4 receives as input the feature amount (X + ~ X,) extracted by the feature extraction circuit 2 and the defect type determination output (Y1 ~ Y,) from the first neural network 3 , determines the defect grade for each defect type and outputs it (zl
~Zt).
第1および第2のニューラルネット3.4は複数個のニ
ューロンからなるネットワークで、各入力に対する重み
パラメータは学習により決定される。第2のニューラル
ネット4としてフィードバック機構を持たない最も単純
なニューラルネ・yトを採用した実施例を第2図に示し
ている。第2図において、第1ニューロン4−1から第
1ニユーロン4−eまでの各々は第1のニューラルネ・
ント3からの欠陥種類の判定出力によってそれぞれ発火
するものである。The first and second neural networks 3.4 are networks consisting of a plurality of neurons, and weight parameters for each input are determined by learning. FIG. 2 shows an embodiment in which the second neural network 4 is the simplest neural network without a feedback mechanism. In FIG. 2, each of the first neuron 4-1 to the first neuron 4-e is a first neural neuron 4-e.
Each of these fires depending on the defect type determination output from the component 3.
第3図は第2のニューラルネット4についての他の実施
例を示している。ここには各欠陥種類ごとに等級判定を
行うためのm個のニューラルネ・ント40−1〜40−
mか含まれている。各ニューラルネット40−1〜40
−mは特徴量(X 、〜X、)を入力として等級判定を
行い、グレード1からグレードlまでの出力を択一的に
発する。FIG. 3 shows another embodiment of the second neural network 4. In FIG. Here, m neural nets 40-1 to 40- are used to judge the grade for each defect type.
Contains m. Each neural net 40-1 to 40
-m performs grade determination using the feature quantity (X, ~X,) as input, and selectively outputs outputs from grade 1 to grade l.
各ニューラルネット40−1〜40−mのグレード1の
各出力のうちの1つのみが出力スイッチS1で選択され
て出力G D 1 となる、グレード2の各出力のうち
の1つが出力スイッチS2で選択されて出力GD2とな
る。以下同様にして、グレードEの各出力のうちの1つ
が出力スイ・ツチS。Only one of the grade 1 outputs of each neural net 40-1 to 40-m is selected by the output switch S1 to become the output GD1, and one of the grade 2 outputs is selected by the output switch S2. is selected and becomes the output GD2. Similarly, one of the grade E outputs is output switch S.
で選択されて出力G D iとなる。is selected and becomes the output GDi.
そして、出力スイッチSl〜S1は第1のニューラルネ
ット3からの種類判定出力(Y、〜Y、、)を受けて、
その種類に対応してニューラルネット40−1〜40−
mのうちの該当のものの出力を選択するように切換えら
れる。つまり、種類判定出力Y + (i = 1
□” m )が入力された場合、ニューラルネット40
−1の出力が等級判定出力(GD1〜GD、)となる。Then, the output switches Sl to S1 receive the type determination output (Y, ~Y,,) from the first neural network 3, and
Neural networks 40-1 to 40- corresponding to the type
It is possible to switch to select the output of the corresponding one among m. In other words, type determination output Y + (i = 1
□”m) is input, the neural network 40
The output of −1 becomes the grade determination output (GD1 to GD,).
以上詳細に説明したように、この発明の欠陥検査装置で
は、熟練者が目視で検査するのと同様に、欠陥の種類に
合わせた適切な基準でもって欠陥の等級を適切に判定す
ることができる。また、ニューラルネットの学習の収束
も速い。As explained in detail above, the defect inspection device of the present invention can appropriately determine the grade of a defect using appropriate criteria according to the type of defect, just as a skilled person would visually inspect. . Also, the convergence of neural network learning is fast.
第1図は本発明の第1実施例の構成図、第2図は第2実
施例の構成図、第3図は第3実施例の要部構成図、第4
図は従来例の構成図である。
3・・・第1のニューラルネット
4・・・第2のニューラルネット
4−1〜4−!!・・・ニューロンFig. 1 is a block diagram of the first embodiment of the present invention, Fig. 2 is a block diagram of the second embodiment, Fig. 3 is a block diagram of main parts of the third embodiment, and Fig. 4 is a block diagram of the main part of the third embodiment.
The figure is a configuration diagram of a conventional example. 3...First neural network 4...Second neural network 4-1 to 4-! ! ...neuron
Claims (3)
出器と、この検出器の画像信号から欠陥の特徴量を抽出
する特徴抽出回路と、抽出された特徴量を入力として欠
陥の種類を判定出力する第1のニューラルネットと、前
記特徴量と第1のニューラルネットの出力とを入力とし
て欠陥の等級を判定出力する第2のニューラルネットと
を備えた欠陥検査装置。(1) A detector that photoelectrically scans and images the surface of the object to be inspected, a feature extraction circuit that extracts the feature amount of the defect from the image signal of this detector, and a feature extraction circuit that uses the extracted feature amount as input to identify the defect. A defect inspection device comprising: a first neural network that determines and outputs the type; and a second neural network that receives the feature amount and the output of the first neural network as input and determines and outputs the grade of the defect.
ニューラルネットの第1層の各ニューロンに第1のニュ
ーラルネット出力を分配するように構成したことを特徴
とする欠陥検査装置。(2) The defect inspection apparatus according to claim 1, wherein the defect inspection apparatus is configured to distribute the output of the first neural network to each neuron of the first layer of the second neural network.
ニューラルネットとして欠陥の種類ごとに等級を判定す
る複数個のニューラルネットを設け、第1のニューラル
ネットの出力により前記複数個のニューラルネットを選
択的に動作させるように構成したことを特徴とする欠陥
検査装置。(3) In the defect inspection apparatus according to claim 1, a plurality of neural networks are provided as the second neural net for determining the grade for each type of defect, and the plurality of neural networks are determined by the output of the first neural network. A defect inspection device characterized in that it is configured to selectively operate a net.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP26522590A JP2758260B2 (en) | 1990-10-04 | 1990-10-04 | Defect inspection equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP26522590A JP2758260B2 (en) | 1990-10-04 | 1990-10-04 | Defect inspection equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
JPH04142412A true JPH04142412A (en) | 1992-05-15 |
JP2758260B2 JP2758260B2 (en) | 1998-05-28 |
Family
ID=17414265
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP26522590A Expired - Fee Related JP2758260B2 (en) | 1990-10-04 | 1990-10-04 | Defect inspection equipment |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2758260B2 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06308049A (en) * | 1993-04-23 | 1994-11-04 | Nippon Steel Corp | Surface flaw discriminating device |
JPH08501386A (en) * | 1992-09-07 | 1996-02-13 | アグロビジョン・エービー | Method and apparatus for automatic evaluation of cereal grains and other granular products |
JPH10302049A (en) * | 1997-04-28 | 1998-11-13 | Kumamoto Techno Porisu Zaidan | Image identification device, its method, image detection/ identification device provided with the image identification device and medium recording image identification program |
JP2014002497A (en) * | 2012-06-18 | 2014-01-09 | Shindengen Electric Mfg Co Ltd | Sealed symbol inspection device and method for electronic apparatus |
WO2022185474A1 (en) * | 2021-03-04 | 2022-09-09 | 日本電気株式会社 | Training device, training method, inspection device, inspection method, and recording medium |
WO2022185481A1 (en) * | 2021-03-04 | 2022-09-09 | 日本電気株式会社 | Inspection apparatus, inspection method, and recording medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10929774B2 (en) * | 2015-02-12 | 2021-02-23 | Koninklijke Philips N.V. | Robust classifier |
-
1990
- 1990-10-04 JP JP26522590A patent/JP2758260B2/en not_active Expired - Fee Related
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08501386A (en) * | 1992-09-07 | 1996-02-13 | アグロビジョン・エービー | Method and apparatus for automatic evaluation of cereal grains and other granular products |
JPH06308049A (en) * | 1993-04-23 | 1994-11-04 | Nippon Steel Corp | Surface flaw discriminating device |
JPH10302049A (en) * | 1997-04-28 | 1998-11-13 | Kumamoto Techno Porisu Zaidan | Image identification device, its method, image detection/ identification device provided with the image identification device and medium recording image identification program |
JP2014002497A (en) * | 2012-06-18 | 2014-01-09 | Shindengen Electric Mfg Co Ltd | Sealed symbol inspection device and method for electronic apparatus |
WO2022185474A1 (en) * | 2021-03-04 | 2022-09-09 | 日本電気株式会社 | Training device, training method, inspection device, inspection method, and recording medium |
WO2022185481A1 (en) * | 2021-03-04 | 2022-09-09 | 日本電気株式会社 | Inspection apparatus, inspection method, and recording medium |
Also Published As
Publication number | Publication date |
---|---|
JP2758260B2 (en) | 1998-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0382466A2 (en) | Methods and apparatus for optically determining the acceptability of products | |
US5208870A (en) | Image inspection methods and apparatus | |
JPH04142412A (en) | Defect inspecting device | |
CN110634124A (en) | Method and equipment for area detection | |
JPH08145907A (en) | Inspection equipment of defect | |
JPH04364449A (en) | Fruit defect detecting apparatus | |
JPH04169807A (en) | Inspecting apparatus of surface flaw | |
KR19980086523A (en) | Optical nonuniformity inspection device and optical nonuniformity inspection method | |
JPH08145904A (en) | Inspection equipment of bright defect/dark defect | |
CN112240888A (en) | Visual detection method and visual detection system | |
JPH09218957A (en) | Image processing method | |
Tetteh et al. | Evaluation of a job‐aiding tool in inspection systems | |
Tobias et al. | Automatic visual inspection using the co-occurrence approach | |
JPH04147002A (en) | Inspecting apparatus of surface of fruit and vegetable | |
JPH03160309A (en) | Image quality testing apparatus | |
Beard et al. | Using vision modeling to define occupational vision standards | |
JPS63100354A (en) | Screening method for coke | |
JPH04152251A (en) | Surface state inspection device | |
Abeysundara et al. | A Multiobjective Evolutionary Optimized Recurrent Neural Network for Defects Detection on Flat Panel Displays | |
JPH03280166A (en) | Product inspection device | |
JPH04104048A (en) | Image processing apparatus | |
JPH02173877A (en) | Picture pattern change detecting device | |
JPS63175976A (en) | Flaw detecting and inspecting device | |
JPH06329351A (en) | Number-of-persons measuring device of elevator | |
JP2021125074A (en) | Image processing device, image processing method, and image processing program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
LAPS | Cancellation because of no payment of annual fees |