JPH0210204A - Object detection method - Google Patents
Object detection methodInfo
- Publication number
- JPH0210204A JPH0210204A JP63161635A JP16163588A JPH0210204A JP H0210204 A JPH0210204 A JP H0210204A JP 63161635 A JP63161635 A JP 63161635A JP 16163588 A JP16163588 A JP 16163588A JP H0210204 A JPH0210204 A JP H0210204A
- Authority
- JP
- Japan
- Prior art keywords
- inspected
- shadow
- inspection
- position detection
- determined
- 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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Geophysics And Detection Of Objects (AREA)
- Supply And Installment Of Electrical Components (AREA)
Abstract
(57)【要約】本公報は電子出願前の出願データであるた
め要約のデータは記録されません。(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.
Description
【発明の詳細な説明】
産業上の利用分野
本発明は製造工程中の検査工程において、検査対象物で
ある所定の寸法の部品等がある特定の位置に存在するこ
とを検査する物体検出方法に関するものである。DETAILED DESCRIPTION OF THE INVENTION Field of the Invention The present invention relates to an object detection method for inspecting the presence of a part of a predetermined size as an inspection object at a specific position in an inspection process during a manufacturing process. It is something.
従来の技術
所定の寸法の検査対象物がある特定の位置に存在する事
を検査する方法の一つとして、検査対象物の影を用いる
方法が提案されていた。これは、検査対象物の斜め上方
に設置した照明装置によシ検査対象物を照射したときに
得られる2値画像から、検査対象物の影部分の像を抽出
し、その形状から重心等の特徴量を計算し、予め登録さ
れている数値と比較することにより、検査対象物の位置
や有無を検出するものである。2. Description of the Related Art A method using the shadow of an object to be inspected has been proposed as one method for inspecting the presence of an object to be inspected with predetermined dimensions at a specific position. This method extracts the image of the shadow part of the inspection object from the binary image obtained when the inspection object is illuminated by a lighting device installed diagonally above the inspection object, and determines the center of gravity etc. from the shape. The position and presence or absence of the object to be inspected is detected by calculating the feature amount and comparing it with pre-registered numerical values.
発明が解決しようとする課題
しかしながら上記に示す従来の方法によると、まず影部
分の特定の形状の画像を得るために、検査対象物の影と
それ以外の部分とを区別できるようなしきい値と呼ばれ
るある一定の値の明るさを境に白と黒に2値化するだめ
の濃度値を、設定することが必要で、しきい値の設定に
あたっては、検査対象物の色や背景部分の色の条件等を
考慮して設定しても、常に所定の形状の影の画像が得ら
れるとは限らなかった。さらに、良品の検査対象物が存
在可能な許容範囲が大きくなる程、影を探索すべき探索
範囲も広くしなければならず、検査対象物の色、背景部
の色、照明の条件等により、得られる影の形状にバラツ
キを生じたシ、影身外の部分の余分な情報(ノイズ)を
検出する可能性が高くなり、位置検出精度が悪くなると
いう問題点があった。Problems to be Solved by the Invention However, according to the conventional method described above, in order to obtain an image of a specific shape of the shadow part, a threshold value that can distinguish the shadow from the other parts of the inspection object is first set. It is necessary to set the density value that is to be binarized into white and black at a certain brightness value called ``black''. Even if settings are made taking into account the conditions, etc., it is not always possible to obtain a shadow image with a predetermined shape. Furthermore, the larger the allowable range in which a good inspection object can exist, the wider the search range for shadows must be. There is a problem in that the shapes of the obtained shadows vary, the possibility of detecting extra information (noise) outside the shadow increases, and the position detection accuracy deteriorates.
課題を解決するだめの手段
そこで本発明の物体検出方法では、検査対象物の斜め上
方に複数個の照明を設置し、各照明を順次照らして検査
対象物の影をつくり、まず良品である場合の許容範囲に
て、それらの影のうちの一つまたは数個の重心等の特徴
量を用いて検査対象物の大まかな存在位置を求め、その
情報をもとに、探索範囲を小さく限定した後にさらに、
物体の詳細な位置検出処理を行うという方法をとる。こ
こで位置検出処理とは、予め指定された範囲において、
微妙な明度差を判別し得るような非常に検出感度の鋭敏
な一連の演算処理群を意味する。Means to Solve the Problem Therefore, in the object detection method of the present invention, a plurality of lights are installed diagonally above the object to be inspected, and each light is sequentially illuminated to create a shadow of the object to be inspected. Within the allowable range, the approximate location of the object to be inspected is determined using features such as the center of gravity of one or several of those shadows, and based on that information, the search range is limited to a small size. Later further,
The method is to perform detailed position detection processing of the object. Here, position detection processing means, within a pre-specified range,
It refers to a series of arithmetic processing groups with extremely sensitive detection sensitivity that can distinguish subtle differences in brightness.
作 用
本発明は、上記方法により、許容範囲内にある物体の影
を利用して大まかな存在位置を求め、位置検出処理のだ
めの探索範囲を小さく限定することにより、余分なノイ
ズ情報を排除して位置検出処理における信頼性を向上さ
せることができ、物体の影そのものの形状から物体の位
置を直接検出する方法に比べて、影の形状のバラツキや
、余分なノイズ情報の影響を受けにくい安定した検出が
可能となる。Effect of the Invention The present invention uses the above method to determine the approximate location of an object by using the shadow of the object within the allowable range, and eliminates unnecessary noise information by limiting the search range for position detection processing to a small size. This improves the reliability of position detection processing, and compared to the method of directly detecting the position of an object from the shape of the object's shadow itself, it is more stable and less susceptible to variations in the shape of the shadow and the effects of extra noise information. detection becomes possible.
実施例 以下、本発明の一実施例を図を用いて説明する。Example An embodiment of the present invention will be described below with reference to the drawings.
第1図は本実施例の物体検出方法のフローチャート、第
2図は本実施例であるチップ部品装着検査装置(以下、
チップ検査装置と略す)の概略構成図である。本実施例
のチップ検査装置はプリント基板s上に装着されたチッ
プ部品9の位置を検査するもので、本発明の物体検出方
法を用いている。Fig. 1 is a flowchart of the object detection method of this embodiment, and Fig. 2 is a chip component mounting inspection device (hereinafter referred to as
1 is a schematic configuration diagram of a chip inspection device (abbreviated as a chip inspection device). The chip inspection apparatus of this embodiment inspects the position of a chip component 9 mounted on a printed circuit board s, and uses the object detection method of the present invention.
検査対象物であるチップ部品9と、照明装置1゜〜13
、画像を画像認識部16に入力するためのTVカメラ1
4との位置関係は第2図の通シであり、他の場所のチッ
プ部品を検査するために、照明装置とTVカメラはプリ
ント基板上をロボットによシ平行移動する。A chip component 9 that is an object to be inspected and lighting devices 1° to 13
, a TV camera 1 for inputting images to the image recognition unit 16
The positional relationship with 4 is as shown in FIG. 2, and in order to inspect chip components at other locations, the illumination device and TV camera are moved in parallel on the printed circuit board by a robot.
さて実施例のチップ検査装置の動作を第1図に基づき説
明する。前処理としてチップ検査装置としての画像処理
等の処理全体を司どる画像認識部15に各チップ部品の
位置、外形寸法、種類等のデータを入力し、影の重心か
らの相対位置や許容範囲を設定しておく。まず、検査の
ステップ1で照明1oを発光し、チップ部品9の影16
を生じさせる。引き続きステップ2にて、ステップ1で
得られた影の形状より影の重心位置P1 を計算する
。同様に照明11〜13を順次発光し各々の照明に対応
する影17〜19を生じさせ、それらの形状より重心位
置P2〜P4を計算する。次にステップ3において、予
めP1〜P4各々からの相対位置によって定められてい
る位置Pを求め、ステップ4にて予め教えられている検
査対象物の大きさを考慮して所定の許容範囲との位置関
係をチエツクする。部品の欠品等で検査対象物が許容範
囲内に存在しない場合には、影16〜18に相当する所
定の形状が得られないので、P1〜P4から求まるPの
位置は正規の場合に比べると太きくずれ、検査対象物の
大きさを考慮すると許容範囲外となる場合が多く、部品
欠品のNGの多くはこのステップにて判別されることに
なる。ステップ4にて許容範囲内にあると判断された場
合には、先に求められた位置Pをもとにして、予め登録
された検査対象物の大きさに応じた位置検出処理のだめ
の探索範囲を設定する(ステップ6)。ここで設定され
る位置検出処理のだめの探索範囲の大きさは、良品物体
の存在し得る許容範囲よりも小さい範囲とする。ステッ
プ6にて設定された探索範囲内において位置検出処理を
行う。ここで位置検出処理とは、指定された範囲内にお
いて微妙な明度の差を判別し、その変化点を検出するよ
うな非常に検出感度の鋭敏な一連の演算処理群で、本実
施例においては、前記の位置検出処理を検査対象部品の
外形部に適用することにより、検査対象物の外形形状を
検出し、その各頂点の位置座標を計算するものとする(
ステップ6)。ステップeにおいて求められた各頂点の
位置座標をもとに、検出対象物に対する詳細な位置や寸
法を求め、予め登録しである条件と比較し、最終的な良
否の判定を行う(ステップ7)。Now, the operation of the chip inspection apparatus according to the embodiment will be explained based on FIG. As preprocessing, data such as the position, external dimensions, and type of each chip component are input to the image recognition unit 15, which controls the entire processing such as image processing as a chip inspection device, and the relative position from the center of gravity of the shadow and the allowable range are determined. Set it. First, in step 1 of inspection, the illumination 1o is emitted, and the shadow 16 of the chip component 9 is
cause Subsequently, in step 2, the position of the center of gravity P1 of the shadow is calculated from the shape of the shadow obtained in step 1. Similarly, the lights 11 to 13 are sequentially emitted to produce shadows 17 to 19 corresponding to each light, and the center of gravity positions P2 to P4 are calculated from their shapes. Next, in step 3, the position P determined in advance by the relative position from each of P1 to P4 is determined, and in consideration of the size of the inspection object taught in advance in step 4, the position P is determined in accordance with the predetermined tolerance range. Check the positional relationship. If the object to be inspected does not exist within the allowable range due to missing parts, etc., the predetermined shape corresponding to shadows 16 to 18 cannot be obtained, so the position of P found from P1 to P4 is compared to the normal case. This is often outside the allowable range considering the size of the object to be inspected, and many NGs due to missing parts are determined in this step. If it is determined in step 4 that it is within the allowable range, based on the previously determined position P, the search range for position detection processing according to the size of the inspection object registered in advance is determined. (Step 6). The size of the search range set here for the position detection processing is set to be smaller than the allowable range in which a non-defective object may exist. Position detection processing is performed within the search range set in step 6. Here, the position detection process is a series of arithmetic processes with extremely sensitive detection sensitivity that distinguishes subtle differences in brightness within a specified range and detects the point of change. , by applying the above-mentioned position detection process to the outer shape of the part to be inspected, the outer shape of the object to be inspected is detected, and the position coordinates of each vertex thereof are calculated (
Step 6). Based on the positional coordinates of each vertex determined in step e, the detailed position and dimensions of the object to be detected are determined, compared with pre-registered conditions, and a final judgment of quality is made (step 7). .
発明の効果
以上のように本発明によれば、検査対象物の影を利用し
て大まかな存在位置を求めることによシ、通常検出対象
物の許容範囲全域に対して位置検出処理を施すと、余分
なノイズ情報を検出してしまって検出精度が低くなるよ
うな場合にでも、位置検出処理のだめの探索範囲を小さ
く限定することができるので、従来の方法に比べて、影
の形状のバラツキや余分な/゛イズ情報影響を受けにく
い安定した検出が可能となる。さらに、検査対象物の周
囲に基板上のシルク印刷や穴などの存在により、影とそ
れ以外の部分との判別が困難な箇所においては、予めそ
の箇所の検査対象物の位置の算出に用いる影のいくつか
を選択しておくことで、検査対象物の多様化に対応でき
、かつよシー層の検査信頼性の向上が可能となる。Effects of the Invention As described above, according to the present invention, by determining the approximate location of the object by using the shadow of the object to be inspected, it is possible to perform position detection processing over the entire allowable range of the object to be detected. Even in cases where detection accuracy decreases due to excessive noise information being detected, the search range for position detection processing can be limited to a smaller size, which reduces the variation in shadow shape compared to conventional methods. This enables stable detection that is less susceptible to the effects of noise and redundant image information. Furthermore, in areas where it is difficult to distinguish between shadows and other parts due to the presence of silk printing or holes on the board around the object to be inspected, we will use the shadows in advance to calculate the position of the object to be inspected. By selecting some of them, it is possible to cope with the diversification of the objects to be inspected, and to improve the inspection reliability of the sea layer.
第1図a
bは本発明の一実施例における物体
図すは平面図である。
9・・・・・検査対象物、10〜13・・・・・・照明
装置、14・・・・・・TVカメラ、15・・・・・・
画像認識部。
代理人の氏名 弁理士 中 尾 敏 男 ほか1名第1
図
第1図FIGS. 1a and 1b are plan views of an object according to an embodiment of the present invention. 9...Inspection object, 10-13...Lighting device, 14...TV camera, 15...
Image recognition section. Name of agent: Patent attorney Toshio Nakao and 1 other person No. 1
Figure 1
Claims (1)
を順次発光して検査対象物の影を生じさせる第1工程と
、これらの影のうちの一つまたは数個の重心等の特徴量
を用いて、検査対象物の存在する大まかな位置を求める
第2工程と、この第2工程での情報をもとに探索範囲を
小さく限定する第3工程と、この第3工程後、検査対象
物の位置検出処理を行うことを特徴とする物体検出方法
。The first step is to place a plurality of lights diagonally above the object to be inspected and emit light from each of the lights in sequence to create a shadow on the object to be inspected. A second step of determining the approximate location of the object to be inspected using the feature quantity, a third step of narrowing down the search range based on the information in this second step, and after this third step, An object detection method characterized by performing position detection processing of an object to be inspected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP63161635A JP2692147B2 (en) | 1988-06-29 | 1988-06-29 | Object detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP63161635A JP2692147B2 (en) | 1988-06-29 | 1988-06-29 | Object detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH0210204A true JPH0210204A (en) | 1990-01-16 |
| JP2692147B2 JP2692147B2 (en) | 1997-12-17 |
Family
ID=15738935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP63161635A Expired - Fee Related JP2692147B2 (en) | 1988-06-29 | 1988-06-29 | Object detection method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2692147B2 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5347363A (en) * | 1991-07-25 | 1994-09-13 | Kabushiki Kaisha Toshiba | External lead shape measurement apparatus for measuring lead shape of semiconductor package by using stereoscopic vision |
| JP2014072681A (en) * | 2012-09-28 | 2014-04-21 | Saxa Inc | Monitoring device and monitoring system |
| CN107565375A (en) * | 2017-09-30 | 2018-01-09 | 昂纳信息技术(深圳)有限公司 | A kind of pasting method of chip of laser |
| WO2018105051A1 (en) * | 2016-12-07 | 2018-06-14 | ヤマハ発動機株式会社 | Surface mounting machine, component recognition device, and component recognition method |
| WO2026028965A1 (en) * | 2024-07-29 | 2026-02-05 | 清水技研株式会社 | Component-placing device and component-placing method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6024403A (en) * | 1983-07-20 | 1985-02-07 | Tokico Ltd | Position detecting device |
| JPS62266403A (en) * | 1986-05-15 | 1987-11-19 | Toshiba Corp | Position recognizing instrument for three-dimensional object |
| JPS6344104A (en) * | 1986-08-12 | 1988-02-25 | Nissan Motor Co Ltd | Method for confirming position and posture of work |
-
1988
- 1988-06-29 JP JP63161635A patent/JP2692147B2/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6024403A (en) * | 1983-07-20 | 1985-02-07 | Tokico Ltd | Position detecting device |
| JPS62266403A (en) * | 1986-05-15 | 1987-11-19 | Toshiba Corp | Position recognizing instrument for three-dimensional object |
| JPS6344104A (en) * | 1986-08-12 | 1988-02-25 | Nissan Motor Co Ltd | Method for confirming position and posture of work |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5347363A (en) * | 1991-07-25 | 1994-09-13 | Kabushiki Kaisha Toshiba | External lead shape measurement apparatus for measuring lead shape of semiconductor package by using stereoscopic vision |
| JP2014072681A (en) * | 2012-09-28 | 2014-04-21 | Saxa Inc | Monitoring device and monitoring system |
| WO2018105051A1 (en) * | 2016-12-07 | 2018-06-14 | ヤマハ発動機株式会社 | Surface mounting machine, component recognition device, and component recognition method |
| KR20190057120A (en) * | 2016-12-07 | 2019-05-27 | 야마하하쓰도키 가부시키가이샤 | Surface machining, part recognition, parts recognition |
| JPWO2018105051A1 (en) * | 2016-12-07 | 2019-06-24 | ヤマハ発動機株式会社 | Surface mounter, part recognition apparatus, part recognition method |
| US11291151B2 (en) | 2016-12-07 | 2022-03-29 | Yamaha Hatsudoki Kabushiki Kaisha | Surface mounter, component recognition device and component recognition method |
| DE112016007500B4 (en) * | 2016-12-07 | 2025-08-21 | Yamaha Hatsudoki Kabushiki Kaisha | Surface mount device, component detection device and component detection method |
| CN107565375A (en) * | 2017-09-30 | 2018-01-09 | 昂纳信息技术(深圳)有限公司 | A kind of pasting method of chip of laser |
| WO2026028965A1 (en) * | 2024-07-29 | 2026-02-05 | 清水技研株式会社 | Component-placing device and component-placing method |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2692147B2 (en) | 1997-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112614086B (en) | Learning device, inspection device, learning method, and inspection method | |
| Sanz et al. | Machine-vision techniques for inspection of printed wiring boards and thick-film circuits | |
| CN119151939B (en) | A PCB circuit board defect detection method based on computer vision | |
| JP5045591B2 (en) | Method for creating area setting data for inspection area and board appearance inspection apparatus | |
| JPH0210204A (en) | Object detection method | |
| JPH0669700A (en) | Printed board unit visual inspection system | |
| JP2906454B2 (en) | Object position detection method | |
| JP3233205B2 (en) | Circuit inspection method and device | |
| Zhang | Computer-aided visual inspection for integrated quality control | |
| JPH05180780A (en) | Inspection method and apparatus with electronic component | |
| TWI902049B (en) | Inspection apparatus, inspection method, and computer-readable program | |
| TWI918585B (en) | Inspection apparatus, inspection method, and computer-readable program | |
| JP4474006B2 (en) | Inspection device | |
| JP4087973B2 (en) | Inter-component inspection method and apparatus for mounted components | |
| JP3278555B2 (en) | Bonding wire recognition method | |
| JP2531694B2 (en) | Method for detecting holes in the soldering part | |
| KR19990070849A (en) | Solder Inspection System and Method of Printed Circuit Board | |
| JPH0399250A (en) | Mounting state recognizing apparatus | |
| Johnson | EE368: Reverse engineering of printed circuit boards | |
| JPS62169040A (en) | Printed circuit board pattern inspection equipment | |
| CN118446956A (en) | Inspection device and inspection method | |
| TW202605346A (en) | Inspection apparatus, inspection method, and computer-readable program | |
| JP2002372502A (en) | Printed circuit board inspection method | |
| Lu et al. | Machine vision systems using machine learning for industrial product inspection | |
| JPH0630413A (en) | Image binarization circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| LAPS | Cancellation because of no payment of annual fees |