JPH02213983A - Recognizing method of wire bonding device - Google Patents
Recognizing method of wire bonding deviceInfo
- Publication number
- JPH02213983A JPH02213983A JP1035401A JP3540189A JPH02213983A JP H02213983 A JPH02213983 A JP H02213983A JP 1035401 A JP1035401 A JP 1035401A JP 3540189 A JP3540189 A JP 3540189A JP H02213983 A JPH02213983 A JP H02213983A
- Authority
- JP
- Japan
- Prior art keywords
- correlation
- limit value
- degree
- value limit
- correlation value
- 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
Links
- 238000000034 method Methods 0.000 title claims description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 241001622618 Borbo Species 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L24/00—Arrangements for connecting or disconnecting semiconductor or solid-state bodies; Methods or apparatus related thereto
- H01L24/74—Apparatus for manufacturing arrangements for connecting or disconnecting semiconductor or solid-state bodies
- H01L24/78—Apparatus for connecting with wire connectors
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2224/00—Indexing scheme for arrangements for connecting or disconnecting semiconductor or solid-state bodies and methods related thereto as covered by H01L24/00
- H01L2224/74—Apparatus for manufacturing arrangements for connecting or disconnecting semiconductor or solid-state bodies and for methods related thereto
- H01L2224/78—Apparatus for connecting with wire connectors
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2924/00—Indexing scheme for arrangements or methods for connecting or disconnecting semiconductor or solid-state bodies as covered by H01L24/00
- H01L2924/0001—Technical content checked by a classifier
- H01L2924/00014—Technical content checked by a classifier the subject-matter covered by the group, the symbol of which is combined with the symbol of this group, being disclosed without further technical details
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2924/00—Indexing scheme for arrangements or methods for connecting or disconnecting semiconductor or solid-state bodies as covered by H01L24/00
- H01L2924/01—Chemical elements
- H01L2924/01005—Boron [B]
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Engineering (AREA)
- Image Processing (AREA)
- Wire Bonding (AREA)
- Image Analysis (AREA)
Abstract
Description
【発明の詳細な説明】
(産業上の利用分野〕
本発明はワイヤポンディング装置の認識方法に関するも
のである。DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a method for recognizing a wire bonding device.
第2図は、相関により入力画像の中から基準画像と類似
したパターンの座標を抽出する認識方法の従来例を説明
するための認識システムを示すブロック系統図である。FIG. 2 is a block diagram showing a recognition system for explaining a conventional recognition method for extracting coordinates of a pattern similar to a reference image from an input image by correlation.
同図において、1はリードフレームまたはICチップ等
の認識対象の認識点からカメラによって入力される入力
画像を取り込む入力画像取込手段、2は基準画像2a〜
2dで示すように認識点毎に設定・記憶される位置ずれ
量検出のだめの特徴あるパターンをもつ基準画像記憶手
段、3はスイフチ33〜3dにより認識点に対応する基
準画像を選択する基準画像選択手段、4は入力画像取込
手段lの入力画像aと選択された基準画像との相関演算
を行ない、結果として基準画像との類偵度(以下「相関
度」という)を出力する相関器、5は入力画像aの中の
相関演算対象画像が選択された基準画像と類似している
ことを相関度との比較により判定するための相関値限界
値入力手段、6は相関度が相関値限界値入力手段5より
出力される相関値限界値Cより大きいときにその画像が
類似していると判定し、その座標(以下「候補点」とい
う)を取り出すための比較器、7は候補点と相関度を記
憶する候補点記憶手段、8は候補点記憶手段7の候補点
71〜7nから相関度が最大である候補点を抽出する最
大相関度抽出手段である。In the figure, reference numeral 1 indicates input image capture means for capturing an input image inputted by a camera from a recognition point of a recognition target such as a lead frame or an IC chip, and 2 indicates reference images 2a to 2a.
As shown by 2d, a reference image storage means having a characteristic pattern for detecting the amount of positional deviation is set and stored for each recognition point, and 3 is a reference image selection unit for selecting a reference image corresponding to the recognition point by means of the swifts 33 to 3d. Means 4 is a correlator that performs a correlation calculation between the input image a of the input image capturing means l and the selected reference image, and outputs the degree of similarity (hereinafter referred to as "correlation degree") with the reference image as a result; Reference numeral 5 indicates a correlation value limit value input means for determining whether the correlation calculation target image in the input image a is similar to the selected reference image by comparing it with the correlation degree; A comparator 7 determines that the images are similar when the correlation value output from the value input means 5 is larger than the limit value C, and extracts the coordinates (hereinafter referred to as "candidate point"). Candidate point storage means for storing correlation degrees, and reference numeral 8 denote maximum correlation degree extraction means for extracting candidate points with the maximum correlation degree from candidate points 71 to 7n of candidate point storage means 7.
次に動作について説明する。リードフレームまたはIC
チップ等の認識対象物により認識点が決定すると、基準
画像選択手段3のスイッチ3a〜3dによりそれに対応
する基準画像2a〜2dのどれかが選択される。この選
択された基準画像と入力画像aの一部を相関器4に入力
して相関演算を行ない、相関度すを求める。相関度すと
相関限界値Cとを比較器6で比較し、相関度すが相関値
限界値Cより大きければ、このときの相関度と入力画像
a中の座標を候補点記憶手段7へ登録する。Next, the operation will be explained. Lead frame or IC
When a recognition point is determined by a recognition target such as a chip, one of the corresponding reference images 2a to 2d is selected by switches 3a to 3d of the reference image selection means 3. The selected reference image and a part of the input image a are input to the correlator 4, and a correlation calculation is performed to obtain the degree of correlation. The comparator 6 compares the correlation degree and the correlation limit value C, and if the correlation degree is greater than the correlation value limit C, the correlation degree at this time and the coordinates in the input image a are registered in the candidate point storage means 7. do.
相関度すが相関値限界値C1より小さければ登録は行な
わない。この動作を入力画像aの全部分に対して行ない
、全ての候補点を順次候補点記憶手段7へ登録していく
。上記動作が終了したら、最大相関度候補点抽出手段8
により全候補点の中で相関度が最大である候補点を抽出
する。図示はしていないが、このときの候補点における
座標と基準座標との差が認識対象物の位置ずれ量となる
。If the correlation degree is smaller than the correlation value limit value C1, no registration is performed. This operation is performed for all parts of the input image a, and all candidate points are sequentially registered in the candidate point storage means 7. When the above operation is completed, maximum correlation degree candidate point extraction means 8
The candidate point with the highest degree of correlation is extracted from all candidate points. Although not shown, the difference between the coordinates of the candidate point and the reference coordinates at this time becomes the amount of positional shift of the recognition target.
上記のような従来の認識方法では、認識点全てを一定の
固定された相関値限界値により認識しているので、認識
点毎の人力画像の状態(画素の濃度や輪郭形状)が異な
ったり、入力画像の状態が光の具合等で変化した場合に
相関度が異なり、候補点が多数抽出されたり、また候補
点が抽出されなかったりして、認識精度・認識率が悪い
という問題があった。In the conventional recognition method described above, all recognition points are recognized using a certain fixed correlation value limit value, so the state of the human image (pixel density and outline shape) for each recognition point may differ, When the state of the input image changes depending on the lighting, etc., the degree of correlation changes, resulting in a large number of candidate points being extracted or no candidate points being extracted, resulting in poor recognition accuracy and recognition rate. .
本発明はこのような点に鑑みてなされたものであり、そ
の目的とするところは、相関度が異なる画像であっても
認識精度および認識率の高いワイヤボンディング装置の
認識方法を得ることにある。The present invention has been made in view of these points, and its purpose is to provide a wire bonding device recognition method that has high recognition accuracy and recognition rate even for images with different degrees of correlation. .
このような課題を解決するために本発明は、基準画像に
応じてこの基準画像と人力画像との相関値限界値を設定
し、相関度が相関値限界値以上となる座標を抽出して、
抽出される座標の数により相関値限界(直を変化させる
よ・うにしたものである。In order to solve such problems, the present invention sets a correlation value limit value between this reference image and a human image according to the reference image, extracts coordinates where the degree of correlation is equal to or higher than the correlation value limit value,
The correlation value limit (direction) is changed depending on the number of extracted coordinates.
本発明によるワイヤボンディング装置の認識方法におい
ては、認識点毎の画像の濃度や画像の物体の輪郭形状に
よって異なる相関度に対し、また入力画像の状態の変化
によって変わる相関度に対し、適切な候補点を得る相関
値限界値が設定される。In the wire bonding device recognition method according to the present invention, appropriate candidates are selected for the degree of correlation that varies depending on the density of the image for each recognition point and the contour shape of the object in the image, and for the degree of correlation that changes depending on the state of the input image. A correlation value limit value for obtaining a point is set.
第1図は本発明によるワイヤボンディング装置の認識方
法の一実施例を説明するための認識システムを示すブロ
ック系統図である。同図において第2図と同一部分又は
相当部分には同一符号が付してあり、5 a y 5
dは基準画像毎に設定された相関値限界値、9は基準画
像に対応する相関値限界値を選択するための相関値限界
値選択手段、10は候補点の登録結果により相関値限界
値を変更するための相関値限界値変更量人力手段である
。FIG. 1 is a block diagram showing a recognition system for explaining an embodiment of the wire bonding apparatus recognition method according to the present invention. In this figure, the same parts or equivalent parts as in Fig. 2 are given the same reference numerals, and 5 a y 5
d is a correlation value limit value set for each reference image, 9 is a correlation value limit value selection means for selecting a correlation value limit value corresponding to the reference image, and 10 is a correlation value limit value selection means for selecting a correlation value limit value based on the registration result of candidate points. The correlation value limit value change amount for changing is a manual means.
リードフレームまたはICチップ等の認識対象物により
認識点を決定すると、基準画像選択手段3のスイッチ3
3〜3 dによりそれに対応する基準画像2a〜2dの
どれかが選択されると同時に相関値限界値選択手段9の
スイッチ9a〜9dにより上記選択された基準画像に対
応する相関(a限界値5a〜5dのどれかが選択される
。従来技術と同様に、上記選択された基準画像と入力画
像aの一部を相関器3に入力して相関演算を行ない相関
度すを求める。相関度すと相関値限界値Cとを比較器6
で比較し、相関度すか相関値限界値Cより大きければ、
このときの相関度すと人力画像a中の座標を候補点記憶
手段7へ登録する。この動作を入力画像aの全部分に対
して行ない、全ての候補点を順次候補点記憶手段7へ登
録していく。When a recognition point is determined based on a recognition target such as a lead frame or an IC chip, the switch 3 of the reference image selection means 3 is activated.
3 to 3d, one of the corresponding reference images 2a to 2d is selected, and at the same time, the switches 9a to 9d of the correlation value limit value selection means 9 select the correlation (a limit value 5a) corresponding to the selected reference image. 5d is selected.Similar to the prior art, the selected reference image and a part of the input image a are input to the correlator 3 and a correlation calculation is performed to obtain the correlation degree. and the correlation value limit value C by the comparator 6.
If the correlation degree is greater than the correlation value limit value C,
The correlation degree at this time and the coordinates in the manual image a are registered in the candidate point storage means 7. This operation is performed for all parts of the input image a, and all candidate points are sequentially registered in the candidate point storage means 7.
このとき相関値限界値Cは選択された基準画像に応じて
適切な値に設定されており、適度の数の候補点が抽出さ
れる。もし、入力画像aの状態が変化して、設定してあ
った相関値限界値では適度の数の候補点が得られなかっ
た場合は、次のように相関値限界値変更量人力手段10
により相関値限界値を変更する。At this time, the correlation value limit value C is set to an appropriate value according to the selected reference image, and an appropriate number of candidate points are extracted. If the state of the input image a changes and an appropriate number of candidate points cannot be obtained with the set correlation value limit value, the correlation value limit value change amount manual means 10 is determined as follows.
Change the correlation value limit value.
候補点が多数抽出されるのは相関値限界値が低いためで
、正の変更量を加えて相関イ直限界値を高くする。また
、候補点が無いのは相関値限界値が高いためで、負の変
更量を加えて相関値限界値を低くする。The reason why a large number of candidate points are extracted is because the correlation value limit value is low, and a positive change amount is added to increase the correlation value limit value. Furthermore, the reason why there are no candidate points is because the correlation value limit value is high, and a negative change amount is added to lower the correlation value limit value.
この再設定された相関値限界値により再度上記の動作を
適度の数の候補点が得られるまで行なう。Using this reset correlation value limit value, the above operation is performed again until an appropriate number of candidate points are obtained.
上記動作が終了したら、最大相関度候補点抽出手段8に
より全候補の中で相関度が最大である候補点を抽出する
。従来技術の説明におけると同様に図示はしていないが
、上記相関度が最大である候補点における座標と基準座
標との差が認識対象物の位置ずれ量となる。When the above operation is completed, the maximum correlation degree candidate point extracting means 8 extracts the candidate point having the maximum correlation degree among all the candidates. Although not shown in the drawings as in the description of the prior art, the difference between the coordinates at the candidate point having the maximum correlation and the reference coordinates is the amount of positional shift of the recognition target object.
なお、第1図に示した認識システムはハードウェアで構
成した例であるが、このシステムの動作をソフトウェア
で行なわせても同様の効果がある。Note that although the recognition system shown in FIG. 1 is an example constructed using hardware, the same effect can be obtained even if the operation of this system is performed using software.
以上説明したように本発明によるワイヤボンディング装
置の認識方法は、基準画像に応じて相関値限界値を設定
し、候補点数に応じて相関値限界値を変更するようにし
たことにより、相関度が異なる画像であっても、また相
関度が変化する画像であっても、その画像に適切な相関
値限界値を設定できるので、認識精度および認識率が高
くなるという効果がある。As explained above, in the wire bonding device recognition method according to the present invention, the correlation value limit value is set according to the reference image and the correlation value limit value is changed according to the number of candidate points, so that the degree of correlation can be improved. Even if the images are different or the degree of correlation changes, an appropriate correlation value limit value can be set for the image, resulting in an effect of increasing recognition accuracy and recognition rate.
第1図は本発明によるワイヤボンディング装置の認識方
法の一実施例を説明するための認識システムを示すブロ
ック系統図、第2図は従来方法を説明するための認識シ
ステムを示すブロック系統図である。FIG. 1 is a block system diagram showing a recognition system for explaining an embodiment of the wire bonding apparatus recognition method according to the present invention, and FIG. 2 is a block system diagram showing a recognition system for explaining a conventional method. .
Claims (1)
パターンを探索し、物体の位置ずれ量を認識してボンデ
ィング位置を補正するワイヤボンディング装置の認識方
法において、基準画像に応じてこの基準画像と入力画像
との相関値限界値を設定し、相関度が相関値限界値以上
となる座標を抽出して、抽出される座標の数により相関
値限界値を変化させることを特徴とするワイヤボンディ
ング装置の認識方法。In a wire bonding device recognition method that searches for a pattern similar to the reference image using the correlation between the reference image and the input image, and corrects the bonding position by recognizing the amount of positional deviation of the object, this reference image is Wire bonding characterized by setting a correlation value limit value between the input image and the input image, extracting coordinates where the degree of correlation is equal to or higher than the correlation value limit value, and changing the correlation value limit value depending on the number of extracted coordinates. How to recognize the device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP1035401A JPH02213983A (en) | 1989-02-15 | 1989-02-15 | Recognizing method of wire bonding device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP1035401A JPH02213983A (en) | 1989-02-15 | 1989-02-15 | Recognizing method of wire bonding device |
Publications (1)
Publication Number | Publication Date |
---|---|
JPH02213983A true JPH02213983A (en) | 1990-08-27 |
Family
ID=12440892
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP1035401A Pending JPH02213983A (en) | 1989-02-15 | 1989-02-15 | Recognizing method of wire bonding device |
Country Status (1)
Country | Link |
---|---|
JP (1) | JPH02213983A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6928611B2 (en) | 2000-09-25 | 2005-08-09 | Adobe Systems Incorporated | Setting text composition spacing amount |
US6993709B1 (en) | 2000-02-12 | 2006-01-31 | Adobe Systems Incorporated | Smart corner move snapping |
US7039862B2 (en) | 2002-05-10 | 2006-05-02 | Adobe Systems Incorporated | Text spacing adjustment |
US7071941B2 (en) | 2000-02-12 | 2006-07-04 | Adobe Systems Incorporated | Method for calculating CJK emboxes in fonts |
US7123261B2 (en) | 2002-12-26 | 2006-10-17 | Adobe Systems Incorporated | Coordinating grid tracking and mojikumi spacing of Japanese text |
US7167274B2 (en) | 2001-09-28 | 2007-01-23 | Adobe Systems Incorporated | Line leading from an arbitrary point |
US7168037B2 (en) | 2000-09-25 | 2007-01-23 | Adobe Systems Incorporated | Text composition spacing amount setting device with icon indicators |
US7296227B2 (en) | 2001-02-12 | 2007-11-13 | Adobe Systems Incorporated | Determining line leading in accordance with traditional Japanese practices |
US7305617B2 (en) | 2000-02-12 | 2007-12-04 | Adobe Systems Incorporated | Method for aligning text to baseline grids and to CJK character grids |
US7320104B2 (en) | 2000-02-12 | 2008-01-15 | Adobe Systems Incorporated | Text grid creation tools |
US7594171B2 (en) | 2004-10-01 | 2009-09-22 | Adobe Systems Incorporated | Rule-based text layout |
JPWO2018235186A1 (en) * | 2017-06-21 | 2020-02-27 | 株式会社Fuji | Board work equipment |
-
1989
- 1989-02-15 JP JP1035401A patent/JPH02213983A/en active Pending
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7320104B2 (en) | 2000-02-12 | 2008-01-15 | Adobe Systems Incorporated | Text grid creation tools |
US6993709B1 (en) | 2000-02-12 | 2006-01-31 | Adobe Systems Incorporated | Smart corner move snapping |
US7305617B2 (en) | 2000-02-12 | 2007-12-04 | Adobe Systems Incorporated | Method for aligning text to baseline grids and to CJK character grids |
US7071941B2 (en) | 2000-02-12 | 2006-07-04 | Adobe Systems Incorporated | Method for calculating CJK emboxes in fonts |
US7168037B2 (en) | 2000-09-25 | 2007-01-23 | Adobe Systems Incorporated | Text composition spacing amount setting device with icon indicators |
US6928611B2 (en) | 2000-09-25 | 2005-08-09 | Adobe Systems Incorporated | Setting text composition spacing amount |
US7296227B2 (en) | 2001-02-12 | 2007-11-13 | Adobe Systems Incorporated | Determining line leading in accordance with traditional Japanese practices |
US7167274B2 (en) | 2001-09-28 | 2007-01-23 | Adobe Systems Incorporated | Line leading from an arbitrary point |
US7039862B2 (en) | 2002-05-10 | 2006-05-02 | Adobe Systems Incorporated | Text spacing adjustment |
US7123261B2 (en) | 2002-12-26 | 2006-10-17 | Adobe Systems Incorporated | Coordinating grid tracking and mojikumi spacing of Japanese text |
US7594171B2 (en) | 2004-10-01 | 2009-09-22 | Adobe Systems Incorporated | Rule-based text layout |
US7783969B1 (en) | 2004-10-01 | 2010-08-24 | Adobe Systems Incorporated | Rule-based text layout |
JPWO2018235186A1 (en) * | 2017-06-21 | 2020-02-27 | 株式会社Fuji | Board work equipment |
US11210764B2 (en) | 2017-06-21 | 2021-12-28 | Fuji Corporation | Apparatus for performing work on substrate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9224034B2 (en) | Face searching and detection in a digital image acquisition device | |
US4805224A (en) | Pattern matching method and apparatus | |
US8472721B2 (en) | Pattern identification unit generation method, information processing apparatus, computer program, and storage medium | |
US5184216A (en) | Image sensing apparatus having camera-shake detection function | |
JPH02213983A (en) | Recognizing method of wire bonding device | |
US8098903B2 (en) | Apparatus for adjusting focus and exposure based on a face image and method of controlling same | |
JPS5839357B2 (en) | Pattern position detection method | |
JP2001307096A (en) | Image recognition device and method | |
KR20000076486A (en) | Face-image processing apparatus | |
CN100492088C (en) | Automatic focusing method | |
JP2007067559A (en) | Image processing method, image processing apparatus, and control method of imaging apparatus | |
JP4939292B2 (en) | APPARATUS HAVING AUTHENTICATION PROCESS FUNCTION, ITS CONTROL METHOD, PROGRAM, AND RECORDING MEDIUM | |
JPH08237535A (en) | Tracking area setting device, motion vector detecting circuit and object tracking device using the same | |
JP2000123186A (en) | Object recognizing device | |
JPH05174149A (en) | Picture recognition device | |
JPH05303643A (en) | Pattern matching method | |
CN107579028B (en) | Method and device for determining edge of incomplete wafer and scribing device | |
JP5375401B2 (en) | Image processing apparatus and method | |
CN110766671B (en) | Image processing method based on machine vision software | |
JPH03120732A (en) | Misregistration amount recognition device and manufacture of semiconductor device using same | |
JPH03272149A (en) | Recognition of wire bonder and wire bonder using method of this recognition | |
Xu et al. | Environment adapted active multi-focal vision system for object detection | |
JPH03272150A (en) | Recognition of wire bonder | |
KR20230052774A (en) | Method and system for controlling robot arm using obtaining re-size image by frame grabber | |
JP2903823B2 (en) | Pattern recognition device |