WO2005100962A1 - 分類装置及び分類方法 - Google Patents
分類装置及び分類方法 Download PDFInfo
- Publication number
- WO2005100962A1 WO2005100962A1 PCT/JP2005/007228 JP2005007228W WO2005100962A1 WO 2005100962 A1 WO2005100962 A1 WO 2005100962A1 JP 2005007228 W JP2005007228 W JP 2005007228W WO 2005100962 A1 WO2005100962 A1 WO 2005100962A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- classification
- category
- classification device
- area
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/47—Scattering, i.e. diffuse reflection
- G01N21/4788—Diffraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9501—Semiconductor wafers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
Definitions
- the present invention relates to a classification device and a classification method.
- an image of the entire wafer is taken at a low magnification of the level of the naked eye, and in the macro inspection defect classification for a wide range of defects such as poor resolution, film unevenness, scratches, and foreign matter, multiple images are included in the image.
- a defect may be present, and this corresponds to the above-mentioned "when there are a plurality of targets to be classified in the processed image".
- the macroscopic examination and analysis of the subject has advantages such as obtaining a weak result in local examination and analysis and processing the same range at a higher speed. It is an effective method in various fields.
- Japanese Patent Application Laid-Open No. 2003-168114 by the present inventor discloses a configuration related to a defect classification apparatus for macro inspection for a semiconductor wafer or the like.
- An inspection image 800 (FIG. 18A) obtained by imaging the entire surface of the subject generally includes defective resolution 801, unevenness 802, scratches 803, and the like.
- the difference image 860 (FIG. 18 (C)) is obtained by comparing such an inspection image 800 with the non-defective image 850 (FIG. 18 (B)).
- a defect region extraction image 870 in which defect regions 871 to 873 are extracted is obtained.
- a printed matter inspection device described in Japanese Patent Application Laid-Open No. 2001-225453 discloses a configuration of a device that determines the type of a defect based on an image and emits an alarm sound according to the type! When two or more defect types are detected, only a warning is issued that the defect is a compound defect, and no information on the defect type is output.
- the present invention has been made to solve the above-described problem, and an object of the present invention is to output a classification result representing a classification result of each object from an image in which a plurality of classification objects exist. It is an object of the present invention to provide a classification device and a classification method that can perform the classification.
- a first invention is a classification device, which is a region extraction means for extracting a plurality of regions from an image, and classifies each of the extracted regions into a predetermined category. Classification means, and a representative force in the entire image based on the classification result of each region in the image. Representative category determining means for determining a category.
- the representative category indicates a value indicating an existence ratio of each area in the image and reliability of a classification result of each area.
- the value is determined using at least one of the priority of each category.
- a third invention is the classification device according to the second invention, wherein the value indicating the existence ratio of each region includes a number of regions for each category in the image, a total area for each category, It is represented by at least one of the number of occupied sections for each category when the image is divided into sections of arbitrary size.
- the value indicating the reliability is calculated based on a distance in the feature amount space used for the classification.
- the plurality of classification target regions are defect regions when an image of the surface of the subject is imaged.
- the priority is set according to a criticality of the defective area.
- a seventh invention is the classification device according to any one of the first to sixth inventions, wherein the subject is a semiconductor wafer or a flat panel display substrate.
- the image is an interference image or a diffraction image of the surface of the subject.
- a display capable of switching and displaying a category of each detected area and a representative category in the entire image is provided. Means are further provided.
- an image to be processed is displayed together with the display of the force category on the display means.
- the extraction area or the outline of the extraction area is displayed in a color-coded manner for each category with respect to the image to be processed.
- a step of extracting a plurality of regions from an image, a step of classifying each of the extracted regions into a predetermined category, and a step of classifying each region in the image are performed. And determining a representative category in the entire image.
- FIG. 1 is a diagram showing a configuration of a defect classification device according to one embodiment of the present invention.
- FIG. 2 is a diagram for explaining a first method of extracting a defective area.
- FIG. 3 is a diagram for explaining a second method of defect area extraction.
- FIG. 4 is a diagram showing an example of a region connection process using a morphological process (closing process).
- FIG. 5 is a diagram showing an example of a membership function.
- FIG. 6 is a diagram for explaining the principle of defect type discrimination by a classification rule using a membership function.
- FIG. 7 is a diagram for explaining the principle of defect type discrimination by the k-nearest neighbor method.
- FIG. 8 is a diagram for explaining the principle of defect type discrimination based on a distance from a representative point of the teacher data distribution.
- FIG. 9 is a diagram showing a table of classification result data for each area.
- FIG. 10 is a view showing a table of classification result data of defect types.
- FIG. 11 is a diagram for explaining a difference between a judgment result of a person on an inspection image and a judgment result based on the number of areas or a judgment result based on an area area.
- FIG. 12 is a view showing the state of the occupied section due to the scratches 200 and unevenness 201 in FIG. 11 (A).
- FIG. 13 is a diagram showing a result of selecting a region having a high reliability index value in a table of classification result data by region.
- FIG. 14 is a table of defect type classification result data based on the region selected in FIG.
- FIG. 15 is a display screen displaying representative defect type information and an inspection image.
- FIG. 16 is a display screen displaying a detailed classification result of slot03 in FIG.
- FIG. 17 is a flowchart for explaining a processing flow of the defect classification device of the present embodiment.
- FIG. 18 is a diagram for explaining the principle of a conventional defect classification method.
- FIG. 19 is a diagram showing an example of feature amounts and classification rules calculated for each defect area. is there.
- the present invention is applied to a defect classification apparatus used for macro inspection of a semiconductor wafer or a flat panel display substrate.
- the present invention is not limited to this.
- a plurality of types of cells are classified.
- the present invention is also applicable to the use of displaying a representative result.
- FIG. 1 is a diagram showing a configuration of a defect classification device according to one embodiment of the present invention.
- the defect classifier includes an illuminator 101 for illuminating an object 112, a band-pass filter 102 for limiting the wavelength of illumination light from the illuminator 101, and a lens for imaging reflected light from the object 112.
- a CCD camera 104 for converting the formed subject image into an electric signal
- an image input board 105 for capturing a signal from the CCD camera 104 as an image, holding of image data
- a memory 106 for use in processing
- an area extracting means 107 for extracting a defect area to be classified from an image
- a classifying means 108 for classifying each extracted defect area into a predetermined defect type (or grade or the like).
- a representative category determining means 109 for determining a representative category in the entire image based on the classification result of each region, a display means 110 for displaying the classification result, and various settings required for each of the above-described means.
- To set Input means 111 and the force is also constructed.
- the memory 106 is a memory in the PC 120
- the area extracting means 107, the classifying means 108, and the representative category determining means 109 are the CPU in the PC 120
- the display means 110 is a monitor
- the input means 111 is a keyboard. And so on.
- the defect classifying apparatus irradiates the object 112 with the light of the illuminator 101 whose wavelength is limited by the band-pass filter 102.
- the diffracted light (or interference light) that also reflects the surface force of the test object 112 is imaged by the lens 103, and is converted into an electric signal by the CCD force camera 104.
- the reason why the diffracted light (or the interference light) is obtained is to sufficiently image defects such as poor resolution, film unevenness, scratches, and foreign matter, which are the targets of the macro inspection of the semiconductor wafer.
- image defects such as poor resolution, film unevenness, scratches, and foreign matter
- the film unevenness changes the thickness of a transparent resist material, so that it is easy to form an image by obtaining interference light having a light amount difference corresponding to the resist thickness.
- the electric signal from the CCD camera 104 is digitized through the image input board 105, and is taken into the operation memory 106. This is the test image 133 ((A) in FIG. 2) of the subject.
- the area extracting means 107 extracts a defective area from the acquired inspection image 133.
- a threshold is set for the luminance range of the non-defective level with respect to the inspection image 133, and a region of pixels having a luminance exceeding the threshold is extracted as the defect extraction image 140 (see FIG. B)).
- the threshold indicating the luminance range of the non-defective level may be set in advance in the PC 120 or may be determined adaptively based on the luminance histogram in the image (The University of Tokyo Press: Image Analysis node book: Mikio Takagi, Hirohisa Shimoda, supervision: 502P, binarization).
- a non-defective wafer image 850 as shown in FIG. 18B (or an image 150 of a certain section which becomes a non-defective product as shown in the upper part of FIG. 3A) is held.
- this image is aligned with the inspection image 133 (or the corresponding section in the inspection image) as shown in FIG. 3A, and the luminance difference between the overlapping pixels is calculated to obtain the difference image 160 (( B)) is created, and a defect area is extracted using the difference image 160 by the same threshold processing as in the first method.
- the classifying means 108 classifies each defective area. The classification procedure will be described below.
- Procedure 1 Calculate the feature amount for each extracted defect area.
- the same defect may be divided and extracted when extracting a region due to the influence of a base pattern, a dicing line, or the like. Therefore, if necessary, morphological processing ((reference): Corona: Morphology: written by Hidefumi Obata) is performed to connect the areas, and then the feature values are calculated.
- morphological processing (reference): Corona: Morphology: written by Hidefumi Obata) is performed to connect the areas, and then the feature values are calculated.
- FIGS. 4A and 4B show one example of a region connection process using a morphological process (closing process). An example is shown.
- the continuous resolution failure 170 and unevenness 171 shown in FIG. 4A are converted into connection defect areas 170-1 and 171-1 as shown in FIG. 4B by the area connection processing.
- the feature amount includes a size, a shape, a position, a luminance, and a texture of an area alone, and an arrangement structure of a plurality of areas.
- the feature amount in the macro inspection is disclosed in Japanese Patent Application Laid-Open No. 2003-168114 by the present inventor. It should be noted that the above-described method of extracting a region and the method of calculating a feature amount are changed according to the classification target, and do not limit the content of the present invention.
- Step 2 A predetermined classification rule is applied to the calculated feature amount to determine the category of each region.
- an example using the IF-THEN rule in fuzzy inference as a classification rule is shown. in this case,
- the relationship between the feature value and the defect type is expressed in IF-THEN format based on human knowledge, as in.
- the relationship between the labels such as “large” and “small” and the actual values for the degree of each feature used in the above rule is set by a membership function as shown in FIG. 5, and these are set.
- the type of defect in each area is determined.
- the horizontal axis is the area
- the vertical axis is the fitness.
- Relevance is a value that indicates how much a given feature value matches the target label.
- FIG. 6 is a diagram for explaining the principle of defect type discrimination based on a classification rule using a membership function.
- Rule (1) is a rule indicating the feature value for unevenness.
- certainty is defined as a value indicating the reliability of such a discrimination result by a numerical value of 0 to 1, and between the degree of conformity to the IF clause and the certainty is determined according to the content of the THEN clause.
- the certainty factor of poor resolution 0.6 from the rule (2)
- the certainty factor of the defect 0.7 from the rules (3) and (4). Note that using the minimum value of the fitness for each feature value as the fitness of the entire IF clause, or using the maximum value for the confidence of the overlapping rule for each defect type is only an example. Is also conceivable.
- the region X is finally determined to be flawed (certainty factor: 0.7).
- Step 2 ′ The type of defect in each region is determined based on the relationship between the calculated feature amount and the teacher data in the feature amount space.
- the teacher data is a set of features and information on correct defect types, and is prepared in advance.
- FIG. 7 is a diagram for explaining the principle of defect type determination by the k-nearest neighbor method, which is one of the methods for performing classification using teacher data.
- ⁇ , ⁇ , and mouth indicate the positions in the feature amount space of the teacher data of unevenness, scratches, and poor resolution, respectively.
- P is the position in the feature space of the region to be classified.
- v lm is the (l, m) element of the inverse matrix V ⁇ 1 of the variance-covariance matrix V of the entire teacher data.
- This distance is a distance in a space in which the influence of the variance of the entire distribution of the teacher data is normalized.
- w 1 is the weighting factor for feature 1 (pre-set).
- a method other than the k-nearest neighbor method as shown in FIG. 8, there is a method of classifying based on the distance from a representative point (for example, the center) of the teacher data distribution for each defect type.
- the value of the feature 1 (L) (1 ⁇ 1 (L) ⁇ N) at the representative point is calculated by the following formula, the above distance calculation is performed, and the defect type having the closest distance is classified.
- the computational load increases as the number of features (the number of dimensions) increases. It is also possible to determine a method for calculating a feature amount, perform a feature amount reduction process based on the determined feature amount, and then calculate the distance.
- FIG. 9 is a table of the area-based classification result data.
- the number of occupied sections in the table is the number of sections where defective areas overlap when the image is divided into sections of an arbitrary size. The effect of using the number of occupied partitions will be described later.
- the reliability index value is a value of the certainty factor at the time of discrimination.
- the average distance of teacher data plural
- the distance to the representative point having the shortest distance is calculated. I do.
- the confidence is used, the larger the reliability, the higher the reliability of the result.
- the distance in the feature space is used, the smaller, the more reliable.
- Figure 10 is a table of this classification result data.
- the priority in the table indicates the priority level of the defect type as viewed from the user of the classification device, and is set in advance. Usually, the higher the defect type, the higher the priority. (In Fig. 10, the higher the numerical value, the higher the priority.)
- FIG. 11A consider an image in which a large number of scratches 200 are scattered in the image and unevenness 201 is present in the area.
- the human perceives the flaw 200 as a representative defect type in the image.
- the scratch 200 is determined to be the representative defect type, a correct determination result is obtained.
- FIG. 11B when processing an image as shown in FIG. 11B, a person can judge that the unevenness 201 is the representative defect type, but in the “determination of the number of regions”, the unevenness 201 occupies most of the image. Nevertheless, the representative defect type is determined to be scratch 200.
- the unevenness 201 is a representative defect type in the image of FIG.
- the unevenness 201 is determined to be the representative defect type, and the result is also different from the human judgment.
- FIGS. 12A and 12B are diagrams showing the state of the occupied section due to the scratches 200 and unevenness 201 shown in FIG. 11A.
- the section size is the exposure section size of the semiconductor wafer
- the section size is 1/4 exposure section size. This can be arbitrarily set in advance. is there.
- FIG. 13 shows a region in which the reliability of the result is high in the table of the classification result data by region in FIG. 9 and is shaded.
- FIG. 14 is a table of defect type classification result data based on the region selected in FIG.
- the above-described reliability index value is also set using the input unit 111.
- FIG. 15 shows an example of a display screen of the representative defect types.
- information (flaw, unevenness, poor resolution, etc.) of the representative defect type for each slot 01 to slot 25 is displayed. Further, in order to make it easy to confirm the correspondence between the classification result and the inspection image, the inspection image display section 301 displays a reduced inspection image of each slot.
- FIG. 16 shows an example in which slot03 is specified on the display screen of FIG. 15 and the detailed classification result in slot03 is displayed.
- FIG. 17 is a flowchart for explaining the flow of the processing of the present embodiment described above.
- an inspection image is obtained by imaging the subject with a CCD camera (step Sl).
- a defect area to be classified is extracted from the inspection image (step S2).
- the feature amount of each extracted defect region is extracted (step S3), and each defect region is classified into a predetermined category based on the extracted feature amount (step S4).
- an area with high reliability of the classification result is selected (step S5).
- the existence ratio of each category in the image is calculated based on the information (category, area, number of occupied sections) of each area (step S6).
- a category representing the image is determined based on the priority of each power category and the existence ratio of each category (step S7).
- the category and the inspection image representing the image, the category of each area, and the outline of the defect area are displayed (step S8).
Landscapes
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
- Image Analysis (AREA)
- Liquid Crystal (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2005800109520A CN1942757B (zh) | 2004-04-14 | 2005-04-14 | 分类装置和分类方法 |
| US11/546,479 US20070025611A1 (en) | 2004-04-14 | 2005-04-14 | Device and method for classification |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2004-119291 | 2004-04-14 | ||
| JP2004119291A JP4176041B2 (ja) | 2004-04-14 | 2004-04-14 | 分類装置及び分類方法 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US11546479 Continuation | 2006-10-11 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2005100962A1 true WO2005100962A1 (ja) | 2005-10-27 |
Family
ID=35150112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2005/007228 Ceased WO2005100962A1 (ja) | 2004-04-14 | 2005-04-14 | 分類装置及び分類方法 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20070025611A1 (ja) |
| JP (1) | JP4176041B2 (ja) |
| CN (1) | CN1942757B (ja) |
| WO (1) | WO2005100962A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104076039A (zh) * | 2014-03-28 | 2014-10-01 | 合波光电通信科技有限公司 | 滤光片外观缺陷自动检测方法 |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007248198A (ja) * | 2006-03-15 | 2007-09-27 | Sharp Corp | 特性分布の特徴量抽出方法および特性分布の分類方法 |
| JP5237596B2 (ja) * | 2007-08-10 | 2013-07-17 | オリンパス株式会社 | 判別装置 |
| JP2010085225A (ja) * | 2008-09-30 | 2010-04-15 | Epson Toyocom Corp | 圧電振動片ウェハのエッチング欠陥検査方法、及び検査システム |
| JP5075111B2 (ja) * | 2008-12-29 | 2012-11-14 | 株式会社日立ハイテクノロジーズ | 画像分類基準更新方法、プログラムおよび画像分類装置 |
| GB0909461D0 (en) | 2009-06-02 | 2009-07-15 | Ge Healthcare Uk Ltd | Image analysis |
| JP2011023638A (ja) * | 2009-07-17 | 2011-02-03 | Toshiba Corp | 検査領域設定方法 |
| KR101830679B1 (ko) * | 2010-07-29 | 2018-02-22 | 삼성디스플레이 주식회사 | 표시 패널 검사 장치 및 그 방법 |
| WO2012122467A1 (en) * | 2011-03-09 | 2012-09-13 | Rolls-Royce Corporation | Intelligent airfoil component surface imaging inspection |
| JP5715873B2 (ja) * | 2011-04-20 | 2015-05-13 | 株式会社日立ハイテクノロジーズ | 欠陥分類方法及び欠陥分類システム |
| JP5581343B2 (ja) * | 2012-01-13 | 2014-08-27 | 株式会社日立ハイテクノロジーズ | 欠陥検査方法およびその装置 |
| CN102590221A (zh) * | 2012-02-24 | 2012-07-18 | 深圳大学 | 一种偏光片的外观缺陷检测系统及检测方法 |
| KR102071735B1 (ko) * | 2012-03-19 | 2020-01-30 | 케이엘에이 코포레이션 | 반도체 소자의 자동화 검사용 레시피 생성을 위한 방법, 컴퓨터 시스템 및 장치 |
| CN103383774B (zh) * | 2012-05-04 | 2018-07-06 | 苏州比特速浪电子科技有限公司 | 图像处理方法及其设备 |
| US9513215B2 (en) * | 2013-05-30 | 2016-12-06 | Seagate Technology Llc | Surface features by azimuthal angle |
| JP5704520B2 (ja) * | 2013-10-17 | 2015-04-22 | セイコーエプソン株式会社 | 圧電振動片ウェハのエッチング欠陥検査方法、及び検査システム |
| US10062155B2 (en) * | 2013-11-19 | 2018-08-28 | Lg Display Co., Ltd. | Apparatus and method for detecting defect of image having periodic pattern |
| DE102014017478A1 (de) * | 2014-11-26 | 2016-06-02 | Herbert Kannegiesser Gmbh | Verfahren zum Sortieren von Wäschestücken, insbesondere Schmutzwäschestücken |
| JP6031151B2 (ja) * | 2015-04-30 | 2016-11-24 | 株式会社日立ハイテクノロジーズ | 欠陥検査方法及びその装置 |
| JP6623545B2 (ja) * | 2015-04-30 | 2019-12-25 | 大日本印刷株式会社 | 検査システム、検査方法、プログラムおよび記憶媒体 |
| JP6689539B2 (ja) * | 2016-08-12 | 2020-04-28 | 株式会社ディスコ | 判定装置 |
| KR102058427B1 (ko) * | 2017-12-21 | 2019-12-23 | 동우 화인켐 주식회사 | 검사 장치 및 방법 |
| WO2019230356A1 (ja) * | 2018-05-31 | 2019-12-05 | パナソニックIpマネジメント株式会社 | 学習装置、検査装置、学習方法および検査方法 |
| CN112513926A (zh) * | 2018-07-31 | 2021-03-16 | 奥林巴斯株式会社 | 图像解析装置及图像解析方法 |
| CN110957231B (zh) * | 2018-09-26 | 2022-03-11 | 长鑫存储技术有限公司 | 电性失效图形判别装置及判别方法 |
| CN109975321A (zh) * | 2019-03-29 | 2019-07-05 | 深圳市派科斯科技有限公司 | 一种用于fpc的缺陷检测方法和装置 |
| JP7843022B2 (ja) * | 2021-11-22 | 2026-04-09 | 株式会社Magnolia Blue | 検査方法、検査装置及びプログラム |
| JP7491427B1 (ja) | 2023-03-15 | 2024-05-28 | 日本電気株式会社 | 印刷物検査装置、印刷物検査方法、プログラム |
| CN117420863B (zh) * | 2023-10-30 | 2024-04-19 | 上海频准激光科技有限公司 | 一种增益介质材料隶属函数类型确定方法、设备及介质 |
| TWI874236B (zh) * | 2024-06-04 | 2025-02-21 | 力晶積成電子製造股份有限公司 | 圖片中缺陷的分類方法 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001305073A (ja) * | 2000-04-25 | 2001-10-31 | Hitachi Ltd | 検査データ処理方法およびその装置 |
| JP2003168114A (ja) * | 2001-12-04 | 2003-06-13 | Olympus Optical Co Ltd | 欠陥分類装置 |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05264240A (ja) * | 1992-03-19 | 1993-10-12 | Fujitsu Ltd | 外観検査装置 |
| CA2163965A1 (en) * | 1993-05-28 | 1994-12-08 | Marie Rosalie Dalziel | An automatic inspection apparatus |
| JP3974946B2 (ja) * | 1994-04-08 | 2007-09-12 | オリンパス株式会社 | 画像分類装置 |
| JP3088063B2 (ja) * | 1994-10-25 | 2000-09-18 | 富士通株式会社 | カラー画像処理方法及びカラー画像処理装置 |
| JPH0918798A (ja) * | 1995-07-03 | 1997-01-17 | Sanyo Electric Co Ltd | 文字処理機能付き映像表示装置 |
| JPH11328422A (ja) * | 1998-03-13 | 1999-11-30 | Matsushita Electric Ind Co Ltd | 画像識別装置 |
| JP3522570B2 (ja) * | 1999-03-03 | 2004-04-26 | 日本電信電話株式会社 | 画像検索・画像分類連携システム |
| JP4017285B2 (ja) * | 1999-06-02 | 2007-12-05 | 松下電器産業株式会社 | パターン欠陥検出方法 |
| US6693664B2 (en) * | 1999-06-30 | 2004-02-17 | Negevtech | Method and system for fast on-line electro-optical detection of wafer defects |
| JP2001160057A (ja) * | 1999-12-03 | 2001-06-12 | Nippon Telegr & Teleph Corp <Ntt> | 画像の階層的分類方法、および画像の分類・検索装置、およびこの方法を実行するプログラムを記録した記録媒体 |
| DE10011200A1 (de) * | 2000-03-08 | 2001-09-13 | Leica Microsystems | Verfahren zur Bewertung von Strukturfehlern auf einer Waferoberfläche |
| JP3468755B2 (ja) * | 2001-03-05 | 2003-11-17 | 石川島播磨重工業株式会社 | 液晶駆動基板の検査装置 |
| US7602962B2 (en) * | 2003-02-25 | 2009-10-13 | Hitachi High-Technologies Corporation | Method of classifying defects using multiple inspection machines |
-
2004
- 2004-04-14 JP JP2004119291A patent/JP4176041B2/ja not_active Expired - Fee Related
-
2005
- 2005-04-14 WO PCT/JP2005/007228 patent/WO2005100962A1/ja not_active Ceased
- 2005-04-14 US US11/546,479 patent/US20070025611A1/en not_active Abandoned
- 2005-04-14 CN CN2005800109520A patent/CN1942757B/zh not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001305073A (ja) * | 2000-04-25 | 2001-10-31 | Hitachi Ltd | 検査データ処理方法およびその装置 |
| JP2003168114A (ja) * | 2001-12-04 | 2003-06-13 | Olympus Optical Co Ltd | 欠陥分類装置 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104076039A (zh) * | 2014-03-28 | 2014-10-01 | 合波光电通信科技有限公司 | 滤光片外观缺陷自动检测方法 |
| CN104076039B (zh) * | 2014-03-28 | 2017-05-31 | 合波光电通信科技有限公司 | 滤光片外观缺陷自动检测方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1942757B (zh) | 2010-11-17 |
| US20070025611A1 (en) | 2007-02-01 |
| JP4176041B2 (ja) | 2008-11-05 |
| JP2005301823A (ja) | 2005-10-27 |
| CN1942757A (zh) | 2007-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2005100962A1 (ja) | 分類装置及び分類方法 | |
| JP7325952B2 (ja) | 表示装置の欠陥検出システム及び方法 | |
| US8437534B2 (en) | Defect classification method and apparatus, and defect inspection apparatus | |
| TWI236840B (en) | Method and apparatus for optical inspection of a display | |
| US20070165939A1 (en) | Reduction of false alarms in pcb inspection | |
| JP5371916B2 (ja) | 検査システムにおける対話型閾値調整方法及びシステム | |
| JPH1145919A (ja) | 半導体基板の製造方法 | |
| JP2005293264A (ja) | 学習型分類装置及び学習型分類方法 | |
| JP2001156135A (ja) | 欠陥画像の分類方法及びその装置並びにそれを用いた半導体デバイスの製造方法 | |
| CN106934794A (zh) | 信息处理装置,信息处理方法和检查系统 | |
| JP2000137804A (ja) | デジタル画像の異常検出方法およびシステム、ならびにそのための記憶媒体 | |
| JP7492240B2 (ja) | 分析装置及び分析方法 | |
| CN116091505B (zh) | 一种蓝宝石衬底自动缺陷检测分类的方法和系统 | |
| CN109919908A (zh) | 发光二极管芯片缺陷检测的方法和装置 | |
| CN115222705A (zh) | 基于改进yolov5的化纤丝饼外观缺陷检测方法 | |
| JP2003168114A (ja) | 欠陥分類装置 | |
| CN116823755A (zh) | 一种基于骨架生成和融合构型的柔性电路板缺陷检测方法 | |
| JP2840347B2 (ja) | 基板実装検査装置 | |
| Chang et al. | Application of two Hopfield neural networks for automatic four-element LED inspection | |
| CN119048518B (zh) | 基于图像识别的消防面具缺陷检测方法 | |
| CN118302790A (zh) | 示教数据作成辅助装置、示教数据作成辅助方法 | |
| CN118674703B (zh) | 一种fcob线路载板缺陷检测方法及系统 | |
| JP2006047102A (ja) | 検査対象物の所定の表面状態の原因を自動的に求める装置 | |
| JP4599980B2 (ja) | 多層配線構造の不良解析方法および不良解析装置 | |
| CN119850539B (zh) | 一种基于大模型的电子行业aoi视觉检测优化方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
| AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
| WWE | Wipo information: entry into national phase |
Ref document number: 200580010952.0 Country of ref document: CN Ref document number: 11546479 Country of ref document: US |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWW | Wipo information: withdrawn in national office |
Country of ref document: DE |
|
| WWP | Wipo information: published in national office |
Ref document number: 11546479 Country of ref document: US |
|
| 122 | Ep: pct application non-entry in european phase |

