CN112150441A - Smooth paint surface defect detection method based on machine vision - Google Patents
Smooth paint surface defect detection method based on machine vision Download PDFInfo
- Publication number
- CN112150441A CN112150441A CN202011017844.9A CN202011017844A CN112150441A CN 112150441 A CN112150441 A CN 112150441A CN 202011017844 A CN202011017844 A CN 202011017844A CN 112150441 A CN112150441 A CN 112150441A
- Authority
- CN
- China
- Prior art keywords
- defect
- defects
- stripe
- image
- paint surface
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G01N21/84—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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; CALCULATING OR 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
Abstract
The invention discloses a method for detecting surface defects of a smooth paint surface based on machine vision, and relates to the technical field of digital image processing. The defects such as pits, bulges, scratches and the like are highlighted by reflecting stripe light on the surface of the paint surface, and a CCD camera is used for collecting images; step two: and judging the distortion condition of the stripes through an algorithm, and extracting defects. By adopting a stripe reflection polishing mode, the influence of a mirror reflection effect is eliminated, the appearing force of the paint surface defects can be enhanced, and high-quality paint surface defect images are obtained. Through the self-adaptive binarization image processing result, the stripe information of the surface of the paint surface is completely retained, and the effect is ideal. The curve in the image without the defect is continuous and has uniform curvature, the curve in the image with the defect can be broken and distorted, and the curvature change is large. And finally, traversing the extracted edge, calculating the curvature of the edge and extracting the defect.
Description
Technical Field
The invention relates to the technical field of digital image processing, in particular to a smooth paint surface defect detection method based on machine vision.
Background
With the rapid development of economy in China, the quantity of automobile reserves in China is increased from 1947 thousands in 2008 to 1.8 hundred million in 2018. The painting technique of automobiles needs to be continuously improved, and the complexity and tightness of the painting process make painting become a high-precision work, but the painting flaw is still manually detected at present. When particles and foreign matters exist in the paint and the surface of a product has defects, the surface of the paint has concave-convex flaws after the paint is sprayed. The conventional method is that after the automobile shell is painted, a plurality of workers detect the defects by means of oilstones, illumination and the like and by combining observation, touch and the like from different angles. The mode is difficult to avoid the defects of high manual omission factor, low speed, high cost and the like.
The automobile skin is an indispensable part of the whole automobile, the surface of a finished product is a smooth paint surface, the specular reflection is serious, the defects such as bumps are small (the diameter is in millimeter magnitude), and when manual visual inspection is caused, workers are easy to fatigue in long-term single repetitive work, so that unqualified products flow into an application market. And different workers can make different judgments on the qualification of the limit pieces. In order to improve the detection efficiency, the machine vision detection technology is distinguished from a plurality of detection technologies by the advantages of non-contact property, good flexibility, higher precision, rapid acquisition of information of a detected object and the like.
The traditional visual defect detection method proposed by Newman et al comprises complex steps of image preprocessing, feature extraction, classifier training and the like, and may have the problems of low operation speed, large influence of illumination and the like. However, the invention provides a method for detecting the surface defects of the smooth paint surface based on machine vision based on the traditional manual detection mode and the traditional visual detection mode.
The difficulty in solving the above problems lies in: for the whole automobile skin, the characteristics of various shapes exist, the colors of the surface spray paint are inconsistent, and the adaptability of various shapes and colors is required for detection equipment. A principle of utilizing fringe reflection is proposed, a regular reference fringe is provided, and defects are indirectly reflected by observing distortion conditions at the positions of the defects. Due to the existence of the reference stripes, the automobile skin color-changing device is suitable for automobile skins with various shapes and colors.
For paint surface detection, the detection area is large, the number of processed images is large, higher requirements are put forward on calculation power, and the calculation power and the time consumption are increased. The image processing result of self-adaptive binarization is provided, so that the stripe information of the surface of the visible paint surface is completely reserved, the effect is ideal, and the requirement on calculation power is reduced to 50% of that of the traditional mode.
The curve in the image without the defect is continuous and has uniform curvature, the curve in the image with the defect can be broken and distorted, and the curvature change is large. And finally, traversing the extracted edge, calculating the curvature of the edge and extracting the defect.
The significance of solving the problems is that: in consideration of the traditional manual detection mode and the traditional visual detection mode, the detection method provided by the text can adapt to the paint surfaces of the automobile skins with different surface forms and different colors, the calculation force requirement is reduced, the detection efficiency is improved, and the size of the defect is calculated according to the curvature change degree in the image of the defect.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiment of the invention provides a method for detecting the surface defects of a smooth paint surface based on machine vision. The technical scheme is as follows:
the method for detecting the surface defects of the smooth paint surface based on the machine vision comprises the following steps:
the method comprises the following steps: the defects such as pits, bulges, scratches and the like are highlighted by reflecting stripe light on the surface of the paint surface, and a CCD camera is used for collecting images;
step two: and judging the distortion condition of the stripes through an algorithm, and extracting defects.
In one embodiment, the light reflected by the stripes on the surface of the paint surface is in a manner of stripe reflection.
In one embodiment, the light source of the stripe reflection lighting mode adopts customized stripe board light, the camera lens module and the light source form a certain angle, the painted surface is shot in an inclined mode, and an image is acquired.
In one embodiment, in the second step, when the surface is free of defects, the stripe image has clear texture and the stripes do not interfere with each other;
when the defects exist, the stripe images are bent or deflected, so that the defect information can be represented;
the reflectance rho of the defect position under the influence of light scattering in the vicinity of the defectsRefractive index p relative to defect-free positionbAnd the image at the defect becomes blurred.
In one embodiment, the distortion of the stripes is determined by preprocessing the image to provide good input information for subsequent processing.
In one embodiment, the image preprocessing adopts a local adaptive threshold method to perform image binarization, and the specific calculation method is as follows:
setting P (n) as the gray value of the nth point, fs(n) is the sum of the gray values of s pixels before the nth pixel position;
the variables s and t are introduced to determine the binarization result T (n) of P (n) as:
wherein s and t are empirical values, and s is image.
In one embodiment, fs(n) by gs(n) substitution:
in one embodiment, the algorithm is modified to correlate pixels in the vertical direction during the scan by averaging g (n) with the previous g _ rev (n) to make the final value h (n) more convincing,
in one embodiment, the edges of the stripes in the image are extracted before the stripe information of the paint surface is extracted.
In one embodiment, after the stripe information of the paint surface is extracted, the extracted edge is traversed, the curvature of the edge is calculated, and the defect is extracted.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
firstly, a strip reflection polishing mode is adopted, the influence of a mirror reflection effect is eliminated, the appearing force of the paint surface defects can be enhanced, and high-quality paint surface defect images are obtained. The detection effect is adapted to 100% aiming at the defects of the automobile skin paint surfaces with different shapes and colors, and the stripe reflection polishing mode is suitable for the detection of the automobile skin paint surfaces.
Secondly, through the self-adaptive binarization image processing result, the stripe information of the surface of the visible paint surface is completely reserved, and the effect is ideal. Compared with the traditional computing power and computing time, the method saves 50 percent.
And thirdly, the curve in the image without the defect is continuous and uniform in curvature, the curve in the image without the defect is fractured and distorted, and the curvature change is large. And finally, traversing the extracted edge, calculating the curvature of the edge, extracting the defect, and calculating the size of the defect. The field production line can carry out conditional screening according to the calculation result, the detection efficiency is improved, and the operation cost of enterprises is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a flowchart of a method for detecting defects of a paint surface of an automobile skin based on machine vision according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a sample automobile skin according to the invention provided in the embodiment of the present invention;
a, a smooth painted automobile skin reflection effect graph; b. the reflection effect diagram of the automobile skin with the common paint surface.
FIG. 3 illustrates a general defect in the invention provided in an embodiment of the invention relating to the surface of an automobile skin finish.
Fig. 4 is a schematic diagram of an environment related to lighting in the invention provided in the embodiment of the present invention.
Fig. 5 is a light diagram of the invention provided in the embodiment of the present invention, which relates to a stripe structure.
Fig. 6 is a fringe reflection diagram according to the invention provided in the embodiment of the present invention.
Wherein, a, when the surface is not defective, the stripe image displays a state diagram; b. when the surface has a defect, the stripe image shows a state diagram.
Fig. 7 is a diagram relating to an image binarization result in the invention provided in the embodiment of the present invention.
Fig. 8 is a graph of the results of extraction of the fringe edges involved in the invention provided in the embodiment of the present invention.
Fig. 9 is a diagram of the detection results involved in the invention provided in the embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as broadly as the present invention is capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. As used herein, the terms "vertical," "horizontal," "left," "right," and the like are for purposes of illustration only and are not intended to represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The embodiment of the invention provides a method for detecting defects of a paint surface of an automobile skin based on machine vision, which is used for solving the technical problems of low accuracy and low precision of the detection of the defects of the paint surface of the automobile skin in the prior art. The invention aims to fully utilize an industrial light source and an industrial camera, realize the rapid and accurate detection of the surface defects of the automobile skin paint surface by adopting a machine vision detection method, and process data in real time. The embodiment provides a method for detecting defects of an automobile skin paint surface based on machine vision, please refer to fig. 1, and the method comprises the following steps:
step S101: the defects such as pits, bulges, scratches and the like are highlighted by reflecting stripe light on the surface of the paint surface, and a CCD camera is used for collecting images.
Step S102: and judging the distortion condition of the stripes through an algorithm, and extracting defects.
In the above method, the defect is highlighted only when the size of the defect is larger than the stripe width of the stripe light. The principle of the streak light energy highlighting defects is laser triangulation.
The method for detecting the defects of the automobile skin paint surface based on the machine vision provided by the application is described in detail below with reference to fig. 1:
step S101 is performed first, by reflecting stripe light on the surface of the painted surface, defects such as pits, bumps, scratches, etc. are highlighted, and an image is captured using a CCD camera.
As can be seen from FIG. 2, the surface of the automobile skin is a smooth paint surface, and when ordinary ambient light irradiates the paint surface, the mirror reflection effect is severe, the illumination is uneven, and the defect detection difficulty is increased. Secondly, as can be seen from fig. 3, the common bump defects of the paint surface are very small, and the diameter is usually about 0.5mm, so that the detection difficulty is further increased. The painted surface of the automobile skin is smooth and is similar to a mirror surface, and a strong mirror reflection effect is easily generated, so that the brightness of the acquired image is unevenly distributed, the brightness distribution of a local area is supersaturated, and further, the loss of detail information is caused. Secondly, the strong specular reflection effect can cause surrounding impurities to be easily mapped to the surfaces of the vehicle body parts, and errors of processing results are caused.
In order to solve the problem caused by the mirror reflection effect, the invention adopts a stripe reflection polishing mode, eliminates the influence of the mirror reflection effect, and simultaneously can enhance the appearance force of the paint surface defects, so that the defects are more prominent, and the paint surface defect image with high quality is obtained.
The polishing manner of the stripe reflection is specifically shown in fig. 4. The light source used a custom striped plate light with the stripe pattern shown in fig. 5. The light source irradiates the paint surface in an inclined mode, the camera lens module and the light source form a certain angle, the paint surface is shot in an inclined mode, and the collected image is shown in fig. 6.
Then, step S102 is executed: and judging the distortion condition of the stripes through an algorithm, and extracting defects.
When the surface is free from defects, the stripe image has clear texture and the stripes do not interfere with each other as can be seen from the observation of fig. 6. When the defect exists, the stripe image is bent or deflected, so that the defect information can be represented. The reflectance rho of the defect position under the influence of light scattering in the vicinity of the defectsRefractive index p relative to defect-free positionbAnd the image at the defect becomes blurred.
To determine the distortion of the fringes, the image needs to be preprocessed first to provide good input information for subsequent processing. In order to effectively extract the stripe pattern on the surface of the painted surface, because the contrast between the stripe position and the non-stripe position in the image is obvious, the invention adopts a method of binaryzation of the image to extract the stripe information. Because the stripe gray values in the image are not consistent, the invention adopts a local self-adaptive threshold method to carry out image binarization. The specific calculation method is as follows:
setting P (n) as the gray value of the nth point, fs(n) is the sum of the gray values of s pixels before the nth pixel position.
The variables s and t are introduced to determine the binarization result T (n) of P (n) as:
wherein s and t are empirical values, and s is image. Therefore, the binarization result of the point p (n) to be solved depends on the average value of the gray values of the previous s points 0.85, and if the gray value of the point is less than the value, the result is 1, i.e. black; if the value is larger than this, the result is 0, i.e., white. In the above algorithm, the average value of the gray values of the first n pixels is used when the value t (n) is determined, that is, the weights of the pixels are the same, and it is actually obvious that the pixels at different positions have different influences on the current point, and the influence of the closer pixels on the current point is larger, and vice versa. For this purpose, the invention introduces a more efficient gs(n) in place of fs(n):
G can be calculated by recursions(n) different weights for gray values of pixels at different positions, as well asIn order to associate the pixels in the vertical direction during the scanning process, the algorithm is further improved, and g (n) and the previous g _ rev (n) are averaged to make the final value h (n) more convincing.
Fig. 7 shows the result of the image processing by the local adaptive binarization, which shows that the stripe information of the paint surface is completely retained, and the effect is ideal.
To extract the stripe information of the painted surface, the edges of the stripes in the image must be extracted. Fig. 8 shows the result of morphological edge extraction of a paint surface image containing defects. It can be seen that the curve in the defect-free image is continuous and has uniform curvature, the curve in the defect-free image is broken and distorted, and the curvature change is large.
Finally, the extracted edge is traversed, the curvature of the edge is calculated, and the defect is extracted, as shown in fig. 9.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.
Claims (10)
1. A method for detecting surface defects of a smooth finish based on machine vision is characterized by comprising the following steps:
the method comprises the following steps: the surface of the paint surface reflects stripe light, so that the defects of pits, bulges and scratches are highlighted, and a CCD camera is used for collecting images;
step two: and judging the distortion condition of the stripes through an algorithm, and extracting defect data.
2. The method for detecting the surface defects of the smooth paint surface based on the machine vision as claimed in claim 1, wherein the stripe light reflected by the paint surface adopts a stripe reflection polishing mode.
3. The method for detecting the surface defects of the smooth paint surface based on the machine vision as claimed in claim 2, wherein a light source of a stripe reflection lighting mode adopts a customized stripe board light, a camera lens module and the light source form a certain angle, the paint surface is shot obliquely, and an image is acquired.
4. The method for detecting the surface defects of the smooth paint surface based on the machine vision as claimed in the claim 1, wherein in the second step, when the surface is free from defects, the stripe image has clear texture and the stripes do not interfere with each other;
when the defects exist, the stripe images are bent or deflected, so that the defect information can be represented;
the reflectance rho of the defect position under the influence of light scattering in the vicinity of the defectsRefractive index p relative to defect-free positionbAnd the image at the defect becomes blurred.
5. The method for detecting the surface defects of the smooth paint surface based on the machine vision as claimed in claim 1, wherein the image is preprocessed to provide good input information for processing when judging the distortion condition of the stripes.
6. The method for detecting the surface defects of the smooth paint surface based on the machine vision as claimed in claim 5, wherein the image preprocessing adopts a local adaptive threshold method to carry out image binarization, and the specific calculation method is as follows:
setting P (n) as the gray value of the nth point, fs(n) is the sum of the gray values of s pixels before the nth pixel position;
the variables s and t are introduced to determine the binarization result T (n) of P (n) as:
wherein s and t are empirical values, and s is image.
7. The machine-vision-based method for detecting surface defects of glossy paint surfaces according to claim 6, wherein fs(n) by gs(n) substitution:
8. the method of claim 7 wherein the algorithm is modified by associating vertical pixels during the scanning process, and averaging g (n) with its previous g _ rev (n) to make the final value h (n) more convincing,
9. the method of claim 3, wherein the edges of the stripes in the image are extracted before extracting the stripe information of the paint.
10. The method of claim 9, wherein after extracting the stripe information of the painted surface, traversing the extracted edge, calculating the curvature of the edge, and extracting the defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011017844.9A CN112150441A (en) | 2020-09-24 | 2020-09-24 | Smooth paint surface defect detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011017844.9A CN112150441A (en) | 2020-09-24 | 2020-09-24 | Smooth paint surface defect detection method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112150441A true CN112150441A (en) | 2020-12-29 |
Family
ID=73897974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011017844.9A Pending CN112150441A (en) | 2020-09-24 | 2020-09-24 | Smooth paint surface defect detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112150441A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112858332A (en) * | 2021-02-22 | 2021-05-28 | 菲特(珠海横琴)智能科技有限公司 | Synchronizer gear hub surface defect detection method, system and terminal based on machine vision |
| CN112986260A (en) * | 2021-02-08 | 2021-06-18 | 菲特(珠海横琴)智能科技有限公司 | Camera matrix-based detection system, control system, terminal, medium and application |
| CN113109346A (en) * | 2021-03-08 | 2021-07-13 | 中国第一汽车股份有限公司 | Automatic surface quality detection system and method for automobile panel plate |
| CN113155839A (en) * | 2021-01-06 | 2021-07-23 | 天津大学 | Steel plate outer surface defect online detection method based on machine vision |
| CN113324994A (en) * | 2021-05-26 | 2021-08-31 | 江苏骠马智能工业设计研究有限公司 | Layered detection device and detection method for defects of finish paint of vehicle body |
| CN113763346A (en) * | 2021-08-31 | 2021-12-07 | 哈尔滨工业大学（威海） | Binocular vision-based method for detecting facade operation effect and surface defect |
| CN113899755A (en) * | 2021-11-17 | 2022-01-07 | 武汉华星光电半导体显示技术有限公司 | Screen crease degree detection method and visual detection equipment |
| CN114046923A (en) * | 2021-09-28 | 2022-02-15 | 中交四航局第四工程有限公司 | Nondestructive testing method for post-tensioned prestressed corrugated pipe |
| CN114113145A (en) * | 2021-11-15 | 2022-03-01 | 天津大学 | Detection method, detection device and application of micron-level defects of small-caliber inner wall |
| CN114494129A (en) * | 2021-12-14 | 2022-05-13 | 苏州大学 | Contrast enhancement method for surface slight deformation defect |
| CN115032202A (en) * | 2022-08-10 | 2022-09-09 | 山东唐乐生物科技股份有限公司 | Method for removing residual impurities of stevioside product |
| CN115165920A (en) * | 2022-09-06 | 2022-10-11 | 南昌昂坤半导体设备有限公司 | Three-dimensional defect detection method and detection equipment |
| CN115791806A (en) * | 2022-12-27 | 2023-03-14 | 浙江大学 | Detection imaging method, electronic equipment and medium for automobile paint surface defects |
| CN116106330A (en) * | 2023-04-17 | 2023-05-12 | 武汉名杰模塑有限公司 | Automobile bumper paint defect detection device and detection method thereof |
| CN116402789A (en) * | 2023-03-30 | 2023-07-07 | 开思时代科技(深圳)有限公司 | Vehicle paint spraying demand data analysis method and system |
| CN116630329A (en) * | 2023-07-26 | 2023-08-22 | 山东山森数控技术有限公司 | Online visual detection method for multi-axis multi-channel numerical control system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781739A (en) * | 2019-03-04 | 2019-05-21 | 杭州晶耐科光电技术有限公司 | Automobile finish surface appearance defects automatic detection system and method |
-
2020
- 2020-09-24 CN CN202011017844.9A patent/CN112150441A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781739A (en) * | 2019-03-04 | 2019-05-21 | 杭州晶耐科光电技术有限公司 | Automobile finish surface appearance defects automatic detection system and method |
Non-Patent Citations (2)
| Title |
|---|
| PIERRE D. WELLNER: "Adaptive Thresholding for the DigitalDesk", 《RANK XEROX RESEARCH CENTRE》 * |
| 张恺: "陶瓷球表面缺陷视觉检测关键技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113155839A (en) * | 2021-01-06 | 2021-07-23 | 天津大学 | Steel plate outer surface defect online detection method based on machine vision |
| CN112986260A (en) * | 2021-02-08 | 2021-06-18 | 菲特(珠海横琴)智能科技有限公司 | Camera matrix-based detection system, control system, terminal, medium and application |
| CN112858332A (en) * | 2021-02-22 | 2021-05-28 | 菲特(珠海横琴)智能科技有限公司 | Synchronizer gear hub surface defect detection method, system and terminal based on machine vision |
| CN113109346A (en) * | 2021-03-08 | 2021-07-13 | 中国第一汽车股份有限公司 | Automatic surface quality detection system and method for automobile panel plate |
| CN113324994A (en) * | 2021-05-26 | 2021-08-31 | 江苏骠马智能工业设计研究有限公司 | Layered detection device and detection method for defects of finish paint of vehicle body |
| CN113324994B (en) * | 2021-05-26 | 2022-11-29 | 江苏骠马智能工业设计研究有限公司 | Layered detection device and detection method for vehicle body finish paint defects |
| CN113763346A (en) * | 2021-08-31 | 2021-12-07 | 哈尔滨工业大学（威海） | Binocular vision-based method for detecting facade operation effect and surface defect |
| CN113763346B (en) * | 2021-08-31 | 2023-12-01 | 哈尔滨工业大学（威海） | Binocular vision-based facade operation effect and surface defect detection method |
| CN114046923B (en) * | 2021-09-28 | 2024-04-19 | 中交四航局第四工程有限公司 | Nondestructive testing method for post-tensioned prestressing corrugated pipe |
| CN114046923A (en) * | 2021-09-28 | 2022-02-15 | 中交四航局第四工程有限公司 | Nondestructive testing method for post-tensioned prestressed corrugated pipe |
| CN114113145A (en) * | 2021-11-15 | 2022-03-01 | 天津大学 | Detection method, detection device and application of micron-level defects of small-caliber inner wall |
| CN113899755A (en) * | 2021-11-17 | 2022-01-07 | 武汉华星光电半导体显示技术有限公司 | Screen crease degree detection method and visual detection equipment |
| CN114494129A (en) * | 2021-12-14 | 2022-05-13 | 苏州大学 | Contrast enhancement method for surface slight deformation defect |
| CN115032202A (en) * | 2022-08-10 | 2022-09-09 | 山东唐乐生物科技股份有限公司 | Method for removing residual impurities of stevioside product |
| CN115032202B (en) * | 2022-08-10 | 2022-11-08 | 山东唐乐生物科技股份有限公司 | Method for removing residual impurities of stevioside product |
| CN115165920A (en) * | 2022-09-06 | 2022-10-11 | 南昌昂坤半导体设备有限公司 | Three-dimensional defect detection method and detection equipment |
| CN115791806A (en) * | 2022-12-27 | 2023-03-14 | 浙江大学 | Detection imaging method, electronic equipment and medium for automobile paint surface defects |
| CN115791806B (en) * | 2022-12-27 | 2024-04-05 | 浙江大学 | Detection imaging method, electronic equipment and medium for automobile paint defects |
| CN116402789A (en) * | 2023-03-30 | 2023-07-07 | 开思时代科技(深圳)有限公司 | Vehicle paint spraying demand data analysis method and system |
| CN116402789B (en) * | 2023-03-30 | 2023-11-28 | 开思时代科技(深圳)有限公司 | Vehicle paint spraying demand data analysis method and system |
| CN116106330A (en) * | 2023-04-17 | 2023-05-12 | 武汉名杰模塑有限公司 | Automobile bumper paint defect detection device and detection method thereof |
| CN116630329A (en) * | 2023-07-26 | 2023-08-22 | 山东山森数控技术有限公司 | Online visual detection method for multi-axis multi-channel numerical control system |
| CN116630329B (en) * | 2023-07-26 | 2023-09-29 | 山东山森数控技术有限公司 | Online visual detection method for multi-axis multi-channel numerical control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112150441A (en) | Smooth paint surface defect detection method based on machine vision | |
| US11024020B2 (en) | Method and system for automatic quality inspection of materials and virtual material surfaces | |
| US11270110B2 (en) | Systems and methods for surface modeling using polarization cues | |
| CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
| Martínez et al. | Quality inspection of machined metal parts using an image fusion technique | |
| CN111693549B (en) | Method for detecting and classifying defects of mobile phone cover plate glass | |
| CN110146507B (en) | System and method for detecting appearance defects of automobile paint surface | |
| CN112326671A (en) | Metal plate surface defect detection method based on machine vision | |
| Liu et al. | Automatic detection technology of surface defects on plastic products based on machine vision | |
| CN104101611A (en) | Mirror-like object surface optical imaging device and imaging method thereof | |
| CN111968100B (en) | Machine vision detection method and system | |
| CN110634128A (en) | Ball pin size detection method and device, computer equipment and storage medium | |
| CN110514665A (en) | A kind of detection method of electronic product plastic shell scratch defects | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CA3109406C (en) | Systems and methods for surface modeling using polarization cues | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN211426295U (en) | Automobile paint surface appearance defect detection system | |
| CN111833350A (en) | Machine vision detection method and system | |
| Agrawal | Glass defect detection techniques using digital image processing–a review | |
| Coulthard | Image processing for automatic surface defect detection | |
| Meng et al. | Rubber hose surface defect detection system based on machine vision | |
| CN111179248A (en) | Transparent smooth curved surface defect identification method and detection device | |
| Cheah et al. | Optimum Illumination for Real-time Wiper Arm Defect Detection | |
| Agrawal | Automated inspection of defects in glass by proper color space selection and segmentation technique of digital image processing | |
| He et al. | An effective MID-based visual defect detection method for specular car body surface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201229 |