WO2023120243A1 - 表面検査装置、表面検査方法、欠陥自動修理システム及びプログラム - Google Patents
表面検査装置、表面検査方法、欠陥自動修理システム及びプログラム Download PDFInfo
- Publication number
- WO2023120243A1 WO2023120243A1 PCT/JP2022/045476 JP2022045476W WO2023120243A1 WO 2023120243 A1 WO2023120243 A1 WO 2023120243A1 JP 2022045476 W JP2022045476 W JP 2022045476W WO 2023120243 A1 WO2023120243 A1 WO 2023120243A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- images
- depth
- foreign matter
- estimating
- feature amount
- 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
Images
Classifications
-
- 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
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01N21/94—Investigating contamination, e.g. dust
-
- 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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
- G06T2207/10152—Varying illumination
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30156—Vehicle coating
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Definitions
- the present invention relates to a surface inspection apparatus, a surface inspection method, an automatic defect repair system, and a program capable of estimating the depth from the painted surface of foreign matter that has been mixed into the painted surface of products such as automobiles and caused surface defects. .
- the painted surface of an automobile is composed of four or more layers, but about 80% of automobile paint defects are caused by the contamination of foreign matter before or during painting.
- the depth of foreign matter from the painted surface also called the contamination depth
- the contamination depth can be estimated, and can be used for quality control, for example.
- the rate of occurrence of surface defects is monitored for each depth of contamination, and an alarm is issued when the rate of occurrence reaches an abnormal value. be able to.
- Patent Document 1 discloses a technique capable of accurately determining whether a defect is a genuine defect (defect requiring correction) or a fake defect (defect not corrected).
- Patent Document 2 discloses a technique for determining the depth of a defect by using two types of thresholds for binarization processing and using the area ratio of the defect in the binarized image for each of them.
- Patent Document 3 a complex time image is generated from a time-correlated image captured by illumination that gives a periodic temporal change in light intensity and a periodic spatial change, and the height or depth of a defect is estimated. Techniques are disclosed.
- Patent Document 1 does not describe estimating the contamination depth of foreign matter.
- Patent Document 2 describes determination of the depth of porous defects on the surface and Patent Document 3 describes determination of the depth of surface unevenness, the depth of contamination by foreign matter is described. It is not described to determine the tightness.
- the present invention has been made in view of such a technical background, and provides a surface inspection apparatus, a surface inspection method, and an automatic defect repair system capable of estimating the depth from the coated surface of foreign matter mixed in the coated surface of the work. and to provide programs.
- the above object is achieved by the following means. (1) Acquiring a plurality of images of the inspected portion photographed by an imaging device while the light-dark pattern of the illumination device that illuminates the inspected portion of the coated surface of the work is moved relative to the work. an image acquisition means for A calculation means for calculating a feature quantity representing surface defects for a plurality of images acquired by the image acquisition means; an estimating means for estimating the depth from the painted surface of the foreign matter that caused the surface defect by using the change in the feature quantity calculated by the computing means; surface inspection equipment.
- the surface inspection device according to the preceding item 1, wherein the depth of the foreign matter from the coated surface is estimated using (3)
- the feature amount is the minimum value of pixel values in the defective area.
- an imaging device that captures a plurality of images of the inspected portion in a state in which the light-dark pattern of the lighting device that illuminates the inspected portion of the coated surface of the work is moved relative to the work;
- the surface inspection apparatus according to any one of claims 1 to 5, which acquires the plurality of images and estimates the depth from the painted surface of the foreign matter that caused the surface defect; repair means for repairing surface defects based on the estimated result of the surface inspection device; defect auto-repair system.
- the value of the coefficient a when the frame number of the plurality of images is x, the feature amount is y, and a quadratic curve of y ax 2 +bx+c is fitted to changes in the feature amount.
- an image acquisition step for A computing step of calculating a feature quantity representing a surface defect for a plurality of images acquired by the image acquisition step; an estimating step of estimating the depth from the painted surface of the foreign matter that caused the surface defect using the change in the feature amount calculated in the computing step; A program that causes a computer to run (13) In the estimating step, the frame number of the plurality of images is x, the feature amount is y, and the value of the coefficient a when a quadratic curve of y ax 2 +bx+c is fitted to changes in the feature amount. 13.
- the program according to the preceding item 12 which causes the computer to execute a process of estimating the depth of the foreign matter from the coated surface using .
- the light-dark pattern of the illumination device that illuminates the inspected portion of the coated surface of the workpiece is imaged by the imaging device while being moved relative to the workpiece. , a plurality of images of the inspected portion are acquired, and a feature quantity representing a defect is calculated for the acquired plurality of images. Then, by using the calculated change in the feature amount, the depth from the painted surface where the foreign matter that caused the defect exists can be estimated. flow efficiency.
- defects on the painted surface can be automatically repaired based on the depth of the foreign matter from the painted surface estimated by the surface inspection device.
- the part to be inspected is imaged by the imaging device in a state in which the light-dark pattern of the lighting device that illuminates the part to be inspected on the coated surface of the work is moved relative to the work. a plurality of images are acquired, the feature value representing the defect is calculated for the acquired plurality of images, and the change in the calculated feature value is used to determine the depth from the coating surface of the foreign matter that caused the defect.
- a computer can be caused to perform the process of estimating the height.
- FIG. 1 is a configuration diagram of an automatic defect repair system using a surface inspection apparatus according to an embodiment of the present invention
- FIG. It is a perspective view which shows the structural example of the light-and-dark pattern by an illuminating device.
- FIG. 11 is a perspective view showing another configuration example of a light-dark pattern by the lighting device;
- (A) to (E) are images of the vicinity of the front tire house on the left side of the vehicle body taken by a camera while moving the workpiece.
- (A) is an original camera image when a foreign substance exists in a layer deep from the coating surface
- (B) is an image obtained by binarizing the original image with a certain threshold value.
- FIG. 2 is a scatter diagram plotting the deep layer shown in Table 1 and the shallow layer shown in Table 2, with the horizontal axis x representing the frame number and the vertical axis y representing the number of pixels (area) of the defect region, which is a feature quantity.
- . 2 is a scatter diagram plotting the deep layer shown in Table 1 and the shallow layer shown in Table 2, with the horizontal axis x representing the frame number, and the vertical axis y representing the minimum pixel value of the defect region, which is a feature quantity. .
- 3 is a cross-sectional view of a sample plate used in Examples.
- 10 is a graph showing the distribution of the coefficient a of the second-order term when a quadratic curve is fitted to changes in the feature amount, using the number of pixels in the defect area measured using the sample plate as the feature amount.
- FIG. 1 is a configuration diagram of an automatic defect repair system using a surface inspection apparatus 3 according to one embodiment of the present invention.
- the work 100 to be inspected is a car body having a surface coated, and the part to be inspected of the work 100 is the painted surface. A case of estimating the depth from the surface is shown.
- the surface of the car body is subjected to base treatment, metallic paint, clear paint, etc., and a multi-layered paint film layer is formed. Surface defects occur.
- the workpiece 100 is not limited to the vehicle body, and may be a workpiece other than the vehicle body as long as the surface is coated.
- the illumination device 1 In order to detect surface defects on the workpiece 100, the illumination device 1 needs to irradiate the inspected portion of the workpiece 100 with illumination light having a light-and-dark pattern having at least a pair of bright portions and dark portions.
- the type of lighting device 1 is not limited as long as it can irradiate a light-dark pattern having at least a pair of bright portions and dark portions.
- the illumination device 1 as shown in FIG. 2, a part of the planar light emitting portion is covered with a black mask in the moving direction of the workpiece 100, thereby forming a dark portion 12 covered with the black mask and a bright portion not covered with the black mask.
- An LED illumination device or the like that illuminates the inspected portion with a pair of stripe patterns of the portion 11 can be used.
- the bright and dark pattern is not limited to the one shown in FIG. 2, and may be a stripe pattern in which a plurality of pairs of bright portions 11 and dark portions 12 are present.
- the formation of the dark portion 12 does not need to be formed by masking a part of the light emitting surface of the lighting device 1.
- a light-dark pattern may be formed by forming a dark portion 12 around the illumination device 1 .
- the workpiece 100 is continuously moved and the relative positional relationship between the light-dark pattern and the workpiece 100 is shifted little by little.
- the camera 2 is moved together with the illumination device 1 .
- both the workpiece 100 and the illumination device 1 may be moved at different moving speeds so that one of them moves relatively to the other.
- the illumination device 1 is composed of a display panel such as an LED
- the illumination device 1 by scrolling the brightness pattern displayed on the display surface without physically moving the illumination device 1, the brightness pattern and the workpiece 100 can be displayed. may be moved relatively.
- the camera 2 is a CCD camera or a CMOS camera, and may be a camera that generates monochrome images or a camera that generates color images. In this embodiment, while at least one of the light-dark pattern of the illumination device 1 and the work 100 is moved, the camera 2 sequentially images a preset inspection range of the work 100 at predetermined time intervals.
- the imaging operation of the camera 2, the moving operation of the workpiece 100 or the illumination device 1, the control of the light/dark pattern of the illumination device 1, and the like are performed by a control device (not shown). Alternatively, it may be controlled by the surface inspection device 3 .
- the surface inspection device 3 is composed of a personal computer (PC) or the like, and an arithmetic processing unit such as a CPU executes an operation program stored in a storage unit, thereby estimating the contamination depth of foreign matter.
- PC personal computer
- arithmetic processing unit such as a CPU executes an operation program stored in a storage unit, thereby estimating the contamination depth of foreign matter.
- the surface inspection device 3 functionally has an image acquisition unit 31 , a calculation unit 32 and an estimation unit 33 .
- the image acquisition unit 31 acquires the image of the workpiece 100 captured by the camera 2. Images may be acquired directly from the camera 2 through wired communication or wireless communication, or images captured by the camera 2 may be temporarily stored in an external storage device, and the stored images may be transferred from the storage device. You can get it.
- the calculation unit 32 calculates feature amounts representing surface defects (so-called spots) for a plurality of acquired images, and the estimation unit 33 uses changes in feature amounts for each image calculated by the calculation unit , to estimate the contamination depth of the foreign matter that caused the defect.
- the process of estimating the feature amount representing the surface defect and the mixture depth will be described later.
- the repair device 4 uses a robot to polish and repair surface defects caused by foreign matter when the depth of foreign matter contamination estimated by the surface inspection device 3 is a depth that can be repaired by surface polishing. be.
- FIG. 5(A) shows a plurality of camera original images when a foreign substance exists in a layer deep from the coating surface
- FIG. 5(B) shows an image obtained by binarizing the original image with a certain threshold value.
- a dark portion (white in the image) appearing in a light band 101 (black in the image) in FIG. Expansion processing or contraction processing may be performed on the defect area 102 .
- the numerical value displayed in each image is the frame number of the image.
- FIG. 6A shows a plurality of camera original images when a foreign substance exists in a layer shallow from the coating surface, and FIG. , respectively.
- a dark portion which is a defect region 102, appears in the light band 101 in FIG. 6B. Note that there is no relationship between the frame number of the image in FIG. 5 and the frame number of the image in FIG.
- the luminance change of the defect region 102 in the original image is small, and when the foreign matter exists in a deep layer, the luminance Big change.
- the change in area of the defect region 102 is small when the foreign matter exists in a shallow layer, and the area change is large when the foreign matter exists in a deep layer.
- Table 1 shows the results of calculating the area of the defect region 102 (the number of pixels in the defect region) and the minimum pixel value (brightness) of each pixel in the defect region 102 when the foreign matter exists in a deep layer. Calculation results are shown. Table 2 shows similar calculation results when the foreign matter is present in a shallow layer. These calculations are performed by the calculation unit 32 of the surface inspection device 3 .
- the defect area 102 is a closed white circle area in the binarized image shown in FIGS. 5B and 6B.
- FIG. 7 plots each of the deep layers shown in Table 1 and the shallow layers shown in Table 2, with the horizontal axis x representing the frame number and the vertical axis y representing the number of pixels (area) of the defect region 102, which is a characteristic quantity.
- FIG. 8 is a scatter diagram similarly plotted using the minimum pixel value of the defect area 102 as a feature quantity.
- the number of pixels (area) of the defect area 102 or the minimum value of the pixel values of the defect area 102 is used as a feature amount, and the change in the feature amount in each image is fitted by a quadratic equation. It can be seen that the penetration depth of the foreign matter from the surface can be estimated by using the coefficient a of the second-order term in the case as an index.
- the deep layer shown in FIG. 7 has a larger numerical value than the shallow layer shown in FIG. It can be seen that the depth from the surface of the foreign matter can be estimated.
- the feature amount may be set to 1. Furthermore, the feature amount may be normalized by dividing by the maximum value or minimum value of the feature amount.
- silica beads 300 with diameters of 100 ⁇ m, 150 ⁇ m, and 200 ⁇ m were placed as foreign matter on the surface of the electrodeposition (ED) layer 201, on the surface of the primer (primer: intermediate coating) layer 202 with a thickness of 45 ⁇ m, and on the surface of the primer layer 202 with a thickness of 30 ⁇ m.
- a sample plate 200 was prepared by coating a plurality of base layers (Base Coat) 203 on the surface of each, and further coating a clear layer (Clear Coat) 204 having a thickness of 45 ⁇ m on the surface. The surface of the sample plate 200 was photographed by the camera 2 and a plurality of images were obtained by moving the sample plate 200 while illuminating it with illumination light having a light and dark pattern.
- the coefficient a of the second-order term forms a group of values with significant differences for each mixing depth. Therefore, it can be seen that the existence position (mixing depth) of the silica beads 300 can be estimated to some extent using the coefficient a of the second-order term.
- the repair device 4 for polishing and repairing by a robot is incorporated into the system, and only defects that can be repaired by polishing are selected according to the depth of foreign matter contamination of the surface defect site estimated by the surface inspection device 1. can be automatically repaired by the repair device 4, and the efficiency of the repair process can be improved.
- the present invention is not limited to the above embodiment.
- the surface coating of the workpiece 100 is multi-layer coating
- it may be single-layer coating.
- the present invention can be used, for example, in a surface inspection device capable of estimating the depth from the painted surface of foreign matter that has entered the painted surface of products such as automobiles and caused surface defects.
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
(1)ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得手段と、
前記画像取得手段により取得された複数の画像について表面欠陥を表す特徴量を計算する演算手段と、
前記演算手段で計算された特徴量の変化を利用して、表面欠陥の原因となった異物の塗装表面からの深さを推定する推定手段と、
を備えた表面検査装置。
(2)前記推定手段は、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する前項1に記載の表面検査装置。
(3)前記推定手段は、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する前項1に記載の表面検査装置。
(4)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする前項1~3のいずれかに記載の表面検査装置。
(5)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする前項1~3のいずれかに記載の表面検査装置。
(6)ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で、前記被検査部位についての複数の画像を撮影する撮像装置と、
前記複数の画像を取得し、表面欠陥の原因となった異物の塗装表面からの深さを推定する請求項1~5のいずれかに記載の表面検査装置と、
前記表面検査装置による推定結果に基づいて表面欠陥を修理する修理手段と、
を備えた欠陥自動修理システム。
(7)ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得ステップと、
前記画像取得ステップにより取得された複数の画像について表面欠陥を表す特徴量を計算する演算ステップと、
前記演算ステップで計算された特徴量の変化を利用して、表面欠陥の原因となった異物の存在する塗装表面からの深さを推定する推定ステップと、
を備えた表面検査方法。
(8)前記推定ステップでは、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する前項7に記載の表面検査方法。
(9)前記推定ステップでは、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する前項7に記載の表面検査方法。
(10)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする前項7~9のいずれかに記載の表面検査方法。
(11)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする前項7~9のいずれかに記載の表面検査方法。
(12)ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得ステップと、
前記画像取得ステップにより取得された複数の画像について表面欠陥を表す特徴量を計算する演算ステップと、
前記演算ステップで計算された特徴量の変化を利用して、表面欠陥の原因となった異物の塗装表面からの深さを推定する推定ステップと、
をコンピュータに実行させるためのプログラム。
(13)前記推定ステップでは、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する処理を前記コンピュータに実行させる前項12に記載のプログラム。
(14)前記推定ステップでは、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する処理を前記コンピュータに実行させる前項12に記載のプログラム。
(15)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする前項12~14のいずれかに記載のプログラム。
(16)前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする請求項12~15のいずれかに記載のプログラム。
2 撮像装置(カメラ)
3 表面検査装置
4 修理装置
11 明部
12 暗部
100 ワーク
101 光帯
102 欠陥領域
200 サンプル板
201 電着層
202 プライマー層
203 ベース層
204 クリア層
300 シリカビーズ(異物)
Claims (16)
- ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得手段と、
前記画像取得手段により取得された複数の画像について表面欠陥を表す特徴量を計算する演算手段と、
前記演算手段で計算された特徴量の変化を利用して、表面欠陥の原因となった異物の塗装表面からの深さを推定する推定手段と、
を備えた表面検査装置。 - 前記推定手段は、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する請求項1に記載の表面検査装置。
- 前記推定手段は、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する請求項1に記載の表面検査装置。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする請求項1~3のいずれかに記載の表面検査装置。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする請求項1~3のいずれかに記載の表面検査装置。
- ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で、前記被検査部位についての複数の画像を撮影する撮像装置と、
前記複数の画像を取得し、表面欠陥の原因となった異物の塗装表面からの深さを推定する請求項1~5のいずれかに記載の表面検査装置と、
前記表面検査装置による推定結果に基づいて表面欠陥を修理する修理手段と、
を備えた欠陥自動修理システム。 - ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得ステップと、
前記画像取得ステップにより取得された複数の画像について表面欠陥を表す特徴量を計算する演算ステップと、
前記演算ステップで計算された特徴量の変化を利用して、表面欠陥の原因となった異物の存在する塗装表面からの深さを推定する推定ステップと、
を備えた表面検査方法。 - 前記推定ステップでは、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する請求項7に記載の表面検査方法。
- 前記推定ステップでは、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する請求項7に記載の表面検査方法。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする請求項7~9のいずれかに記載の表面検査方法。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする請求項7~9のいずれかに記載の表面検査方法。
- ワークの塗装表面の被検査部位を照明する照明装置の明暗パターンをワークに対して相対的に移動させた状態で撮像装置により撮影された、前記被検査部位についての複数の画像を取得する画像取得ステップと、
前記画像取得ステップにより取得された複数の画像について表面欠陥を表す特徴量を計算する演算ステップと、
前記演算ステップで計算された特徴量の変化を利用して、表面欠陥の原因となった異物の塗装表面からの深さを推定する推定ステップと、
をコンピュータに実行させるためのプログラム。 - 前記推定ステップでは、前記複数の画像のフレーム番号をx、前記特徴量をyとし、特徴量の変化に対しy=ax2+bx+cの2次曲線をフィッティングさせた時の係数aの値を用いて、前記異物の塗装表面からの深さを推定する処理を前記コンピュータに実行させる請求項12に記載のプログラム。
- 前記推定ステップでは、前記特徴量の最大値-最小値を用いて、前記異物の塗装表面からの深さを推定する処理を前記コンピュータに実行させる請求項12に記載のプログラム。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域の画素数とする請求項12~14のいずれかに記載のプログラム。
- 前記複数の画像を2値化した画像において、欠陥部を構成する画素の集合を欠陥領域としたとき、前記特徴量を前記欠陥領域における画素値の最小値とする請求項12~14のいずれかに記載のプログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP22910953.3A EP4455646A4 (en) | 2021-12-21 | 2022-12-09 | Surface scanning device, surface scanning method, automatic defect repair system and program therefor |
| US18/719,976 US20250045898A1 (en) | 2021-12-21 | 2022-12-09 | Surface inspection device, surface inspection method, automatic defect repair system, and program |
| JP2023569310A JPWO2023120243A1 (ja) | 2021-12-21 | 2022-12-09 | |
| CN202280083390.6A CN118414540A (zh) | 2021-12-21 | 2022-12-09 | 表面检查装置、表面检查方法、缺陷自动修理系统以及程序 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021-207503 | 2021-12-21 | ||
| JP2021207503 | 2021-12-21 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023120243A1 true WO2023120243A1 (ja) | 2023-06-29 |
Family
ID=86902387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2022/045476 Ceased WO2023120243A1 (ja) | 2021-12-21 | 2022-12-09 | 表面検査装置、表面検査方法、欠陥自動修理システム及びプログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20250045898A1 (ja) |
| EP (1) | EP4455646A4 (ja) |
| JP (1) | JPWO2023120243A1 (ja) |
| CN (1) | CN118414540A (ja) |
| WO (1) | WO2023120243A1 (ja) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06317417A (ja) * | 1992-01-23 | 1994-11-15 | Mazda Motor Corp | 表面異常検出装置 |
| JPH09318338A (ja) | 1996-05-31 | 1997-12-12 | Nissan Motor Co Ltd | 表面欠陥検査装置 |
| JP2010151802A (ja) * | 2008-11-20 | 2010-07-08 | Asahi Glass Co Ltd | 透明体検査装置および透明体検査方法 |
| WO2016006039A1 (ja) | 2014-07-08 | 2016-01-14 | 日産自動車株式会社 | 欠陥検査装置及び生産システム |
| JP2019174232A (ja) | 2018-03-28 | 2019-10-10 | リコーエレメックス株式会社 | 検査システムおよび検査方法 |
| JP2021014988A (ja) * | 2017-10-25 | 2021-02-12 | パナソニックIpマネジメント株式会社 | 計測装置 |
| JP2021139817A (ja) * | 2020-03-06 | 2021-09-16 | コニカミノルタ株式会社 | ワークの表面検査装置、表面検査システム、表面検査方法及びプログラム |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6714831B2 (en) * | 2002-01-24 | 2004-03-30 | Ford Motor Company | Paint defect automated seek and repair assembly and method |
-
2022
- 2022-12-09 CN CN202280083390.6A patent/CN118414540A/zh active Pending
- 2022-12-09 US US18/719,976 patent/US20250045898A1/en active Pending
- 2022-12-09 WO PCT/JP2022/045476 patent/WO2023120243A1/ja not_active Ceased
- 2022-12-09 EP EP22910953.3A patent/EP4455646A4/en active Pending
- 2022-12-09 JP JP2023569310A patent/JPWO2023120243A1/ja active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06317417A (ja) * | 1992-01-23 | 1994-11-15 | Mazda Motor Corp | 表面異常検出装置 |
| JPH09318338A (ja) | 1996-05-31 | 1997-12-12 | Nissan Motor Co Ltd | 表面欠陥検査装置 |
| JP2010151802A (ja) * | 2008-11-20 | 2010-07-08 | Asahi Glass Co Ltd | 透明体検査装置および透明体検査方法 |
| WO2016006039A1 (ja) | 2014-07-08 | 2016-01-14 | 日産自動車株式会社 | 欠陥検査装置及び生産システム |
| JP2021014988A (ja) * | 2017-10-25 | 2021-02-12 | パナソニックIpマネジメント株式会社 | 計測装置 |
| JP2019174232A (ja) | 2018-03-28 | 2019-10-10 | リコーエレメックス株式会社 | 検査システムおよび検査方法 |
| JP2021139817A (ja) * | 2020-03-06 | 2021-09-16 | コニカミノルタ株式会社 | ワークの表面検査装置、表面検査システム、表面検査方法及びプログラム |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4455646A4 |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4455646A1 (en) | 2024-10-30 |
| CN118414540A (zh) | 2024-07-30 |
| US20250045898A1 (en) | 2025-02-06 |
| JPWO2023120243A1 (ja) | 2023-06-29 |
| EP4455646A4 (en) | 2025-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2968843C (en) | Defect inspection method and apparatus therefor | |
| EP3060902B1 (en) | Defect inspection system and method | |
| US10267747B2 (en) | Surface defect inspecting device and method for steel sheets | |
| JP2014066657A (ja) | 自動車車体の表面検査装置および表面検査方法 | |
| JP2023151945A (ja) | 検査システムおよび検査方法 | |
| JP2018146442A (ja) | 検査装置、検査システム及び物品の製造方法 | |
| Zhang et al. | Defect inspection of coated automobile roofs using a single camera | |
| JP2009204388A (ja) | 欠陥検査方法 | |
| JP2021139817A (ja) | ワークの表面検査装置、表面検査システム、表面検査方法及びプログラム | |
| JP2019207114A (ja) | ダル仕上げ材表面の良否判定方法及び良否判定装置 | |
| WO2023120243A1 (ja) | 表面検査装置、表面検査方法、欠陥自動修理システム及びプログラム | |
| JP5605010B2 (ja) | 表面検査方法 | |
| JP4760029B2 (ja) | 欠陥検査方法および欠陥検査装置 | |
| JP4322230B2 (ja) | 表面欠陥検査装置及び表面欠陥検査方法 | |
| US10410336B2 (en) | Inspection device, storage medium, and program | |
| JP6373743B2 (ja) | 面の評価方法および面の評価装置 | |
| WO2021049326A1 (ja) | 表面欠陥判別装置、外観検査装置及びプログラム | |
| JP2009139209A (ja) | 欠陥検査方法 | |
| JP2000136917A (ja) | 成形品の表面観察方法及びこれに用いる照明装置 | |
| JP4269423B2 (ja) | 表面検査装置及び表面検査方法 | |
| US7321679B2 (en) | Machine for inspecting glass bottles | |
| JP3661466B2 (ja) | 塗装ムラ検査装置および方法 | |
| JP2016109532A5 (ja) | ||
| KR102117697B1 (ko) | 표면검사 장치 및 방법 | |
| JP7242418B2 (ja) | 表面検査方法とその装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22910953 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2023569310 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18719976 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202280083390.6 Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2022910953 Country of ref document: EP Effective date: 20240722 |