CN111624206B - Metal surface defect detection method based on linear array camera stereoscopic vision - Google Patents
Metal surface defect detection method based on linear array camera stereoscopic vision Download PDFInfo
- Publication number
- CN111624206B CN111624206B CN202010632056.4A CN202010632056A CN111624206B CN 111624206 B CN111624206 B CN 111624206B CN 202010632056 A CN202010632056 A CN 202010632056A CN 111624206 B CN111624206 B CN 111624206B
- Authority
- CN
- China
- Prior art keywords
- metal surface
- linear array
- metal
- camera
- detected
- 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.)
- Active
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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
- G01N21/8903—Optical details; Scanning details using a multiple detector array
-
- 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
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
- G01N2021/8918—Metal
Abstract
The invention provides a metal surface defect detection method based on linear array camera stereoscopic vision, which comprises the following steps: acquiring to-be-measured metal surface images at different viewing angles by arranging a plurality of linear array cameras in a mode of irradiation of a shared light source or a coplanar light source; calculating the depth and the movement speed of the metal surface to be detected through stereo matching, and simultaneously determining the gray level corresponding relation of any point of the metal surface to be detected in the image acquired by the linear array camera; and calculating the normal angle of the metal surface to be detected according to the gray corresponding relation, and detecting the defects of the metal surface through the fusion of the normal angle and the depth three-dimensional information of the metal surface to be detected and the two-dimensional gray image. The method is suitable for reliably extracting the depth and normal three-dimensional information of the metal surface under the actual condition, is favorable for better distinguishing the defects and the pseudo-defects, and improves the accuracy and the reliability of the detection of the defects of the metal surface.
Description
Technical Field
The invention relates to the technical field of surface defect detection methods, in particular to a metal surface defect detection method based on linear array camera stereoscopic vision.
Background
The metal surface defects have an important influence on the quality of the metal plate strip. The method is influenced by factors such as raw materials, rolling process, system control and the like, and defects on the surface of the metal, such as cracks, scratches, roll marks, scabs, impurities and the like, not only have different degrees of influence on the wear resistance, fatigue resistance, corrosion resistance and electromagnetic property of the metal plate, but also can cause serious accidents such as strip breakage, parking and the like in production and cause unpredictable economic and credit losses to production enterprises. Therefore, all the manufacturing enterprises in all countries pay great attention to the detection of the metal surface quality, and the detection technology is improved and the detection level is improved without spending huge expenses.
The metal surface defect on-line detection technology based on machine vision is an important advanced means and technology for monitoring the surface quality of a metal plate production line. As for the metal surface defect detection method, the method mainly comprises manual visual inspection detection, magnetic flux leakage detection and on-line detection based on machine vision. The existing manual visual inspection has the problems of high time cost, low sampling coverage rate and the like. The magnetic leakage detection has different sensitivity degrees to different defects, has higher leakage detection rate, and can not be applied in many occasions limited by various conditions. The machine vision-based online detection can be used for detecting the quality of the metal surface in real time, full continuity and full coverage, is widely concerned by production enterprises and is widely applied.
The defect detection of the metal surface based on the machine vision always has the difficulty of high defect false detection rate. A large amount of false defect interferences such as iron scale, water mark and the like exist on the metal surface, and are very similar to real defects such as scratches, cracks, roll marks and the like in a two-dimensional image, so that the false detection rate is high. Research shows that most real defects have surface three-dimensional morphological characteristics, and a large number of false defects are planar and have no surface depth information. In order to reduce the false detection rate, patents with publication numbers CN 102830123B and CN 103913465B propose a three-dimensional detection method for metal surface defects based on photometric stereo: a single color three-CCD linear array camera and three strip-shaped light sources projected at different angles of red, green and blue are adopted, R (red), G (green) and B (blue) channel images are separated from a color image acquired by the camera, and surface inclination angles are calculated corresponding to the reflected light intensity distribution of the red, green and blue light sources respectively, so that the three-dimensional morphological characteristics of the surface are acquired. According to the technical scheme, the mode of irradiation by light sources with different colors is adopted, the metal surface is required to meet the precondition of ideal gray body when the inclination angle is calculated, and the larger the deviation is, the larger the inclination angle calculation error is. In fact, the metal surface cannot meet the condition of ideal gray body at all, so the technical scheme has the problem that the three-dimensional information of the metal surface is not accurately acquired.
Disclosure of Invention
According to the technical problem that the three-dimensional information of the metal surface is not accurately acquired, the method for detecting the defects of the metal surface based on the stereoscopic vision of the line camera is provided. The invention mainly utilizes a metal surface defect detection method based on linear array camera stereoscopic vision, which comprises the following steps:
step S1: acquiring to-be-measured metal surface images at different viewing angles by arranging a plurality of linear array cameras in a mode of irradiation of a shared light source or a coplanar light source;
step S2: calculating the depth and the movement speed of the metal surface to be detected through stereo matching, and simultaneously determining the gray level corresponding relation of any point of the metal surface to be detected in the image acquired by the linear array camera;
step S3: and calculating the normal angle of the metal surface to be detected according to the gray corresponding relation, and detecting the defects of the metal surface through the fusion of the normal angle and the depth three-dimensional information of the metal surface to be detected and the two-dimensional gray image.
Furthermore, the linear array cameras are arranged on the same side of the surface of the metal to be detected and are arranged front and back along the movement direction of the metal plate to be detected; the visual angles of the linear array cameras face towards each other, and the metal surfaces to be detected are not parallel to each other.
Furthermore, the included angle between the linear array camera visual angles is 20-150 degrees.
Further, the line camera is a common line camera or a time delay integral line camera.
Furthermore, the linear array camera projects the metal surface to be measured at the view field position of the metal surface to be measured by sharing the same light source or a plurality of coplanar light sources corresponding to the linear array camera.
Further, when the linear array cameras are at the same view field position on the metal surface, the shared light source projects to the metal surface to be measured along the direction perpendicular to the movement direction of the metal plate by sharing the same LED strip-shaped light source, linear light source or laser light source.
Further, when the linear array camera is different in view field position on the metal surface, a plurality of groups of coplanar light sources of the same type are used, and the coplanar light sources adopt LED strip-shaped light sources, linear light sources or laser light sources;
the multiple groups of coplanar light sources of the same type are matched with the linear array camera for use, and each group of coplanar light sources projects towards the surface of the metal to be measured along the imaging plane of the linear array camera matched with the coplanar light sources.
Furthermore, the method for calculating the depth of the surface of the metal to be measured comprises the following steps:
h＝(S-S0)/(tgα+tgβ)；
wherein h represents the surface height of the metal plate, S represents the pixel position difference of any point on the surface of the metal plate in the images acquired by the two linear array cameras after being subjected to stereo matching, and S represents the pixel position difference of any point on the surface of the metal plate in the images acquired by the two linear array cameras0And the difference of the corresponding positions of the reference heights is shown, and alpha and beta respectively show the included angle between the visual angle orientation of the two linear array cameras and the direction vertical to the movement direction of the plate.
Further, the calculation method of the normal solid angle of the metal surface to be measured comprises the following steps:
(1) when the two linear array cameras are basically the same in the metal surface view field position and share the same light source to vertically project the metal surface:
θ＝(β-α)/4+(α+β)(1/2-1/π·arc cos((|I2-I1|/k)1/n))sign(I2-I1)；
(2) when the two linear array cameras are different in view field position on the metal surface and the coplanar light source projection plane is superposed with the imaging plane of the corresponding linear array camera:
θ＝(β-α)/2+arc tg((I2-I1)/(I2+I1))；
wherein theta represents a calculated value of a normal angle of the metal surface, alpha and beta respectively represent an included angle between the direction of a linear array camera viewing angle and a direction perpendicular to the moving direction of the plate, and I1And I2Respectively representing the gray scale of any point of the metal surface in the image acquired by the linear array camera, and k and n represent the mirror reflection coefficient of the metal surface and are determined according to the roughness of the metal surface.
Furthermore, according to the pixel position difference of any point on the surface of the metal plate after the three-dimensional matching in the images acquired by the two linear array cameras, the method for calculating the motion speed of the metal plate comprises the following steps:
V＝Pf/S；
wherein V represents the movement speed of the metal sheet to be detected, P represents the visual field distance of the linear array camera on the surface of the metal sheet, f represents the sampling line frequency of the linear array camera, and S represents the pixel position difference in the image acquired by the linear array camera after any point on the surface of the metal sheet to be detected is subjected to stereo matching.
Compared with the prior art, the invention has the following advantages:
the method is suitable for reliably extracting the depth and normal three-dimensional information of the metal surface under the actual condition, is favorable for better distinguishing the defects and the pseudo-defects, and improves the accuracy and the reliability of the detection of the defects of the metal surface.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic view of the arrangement of the cameras of the present invention. Wherein, (a) the linear array cameras are opposite in visual angle and are aligned to the same position of the metal surface; (b) aiming at different positions of the metal surface for the opposite visual angles of the linear array camera; (c) the linear array camera is opposite in visual angle and is aligned to different positions of the metal surface.
FIG. 2 is a schematic view of a light source and a camera according to the present invention. Wherein, (a) the camera is aligned to the same position of the metal surface, and a shared light source is adopted; (b) aiming at different positions of the metal surface by a camera, adopting a coplanar light source, and enabling the coplanar light source to be superposed with an imaging plane of the camera; (c) and aiming the camera at different positions of the metal surface, adopting a coplanar light source, wherein the coplanar light source is superposed with an imaging plane of the camera.
FIG. 3 is a schematic diagram of the surface depth calculation of the present invention. When the surface is concave, the camera 2 firstly enters the visual field of the camera 1, and then the surface is concave; (b) when the surface is convex, the camera 1 firstly enters the visual field of the camera 2, and then the camera is in the visual field of the camera.
FIG. 4 is a schematic view of the calculation of the surface normal solid angle according to the present invention. Wherein, (a) the camera is aligned to the same position of the metal surface and shares the light source; (b) the light sources c are coplanar for the cameras to be aimed at different positions of the metal surface.
FIG. 5 is a schematic flow chart of a defect identification and localization algorithm according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1-5, the invention provides a method for acquiring normal three-dimensional information of a metal surface based on the three-dimensional vision of a linear array camera, which has the basic principle that two-dimensional scanning images of the metal surface are acquired by two linear array cameras arranged at different visual angles by utilizing the movement of a metal plate, the two-dimensional scanning images of the metal surface are matched, the depth of the metal surface and the movement speed of the metal surface are calculated, simultaneously, the gray level corresponding relation of any point of the metal surface at the two different visual angles is acquired, and the normal three-dimensional angle of the metal surface is calculated according to the gray level corresponding relation.
In fig. 1, the arrangement of the two line cameras may be opposite or reverse, and the view field positions of the two line cameras on the metal surface may be the same or different. The two linear array cameras are arranged in a front-back mode along the movement direction of the metal sheet, the visual angles of the two linear array cameras are not parallel, and the included angle between the visual angles of the two linear array cameras is 20-150 degrees. The linear array cameras are arranged on the same side of the surface of the metal to be detected and are arranged in the front and back direction along the movement direction of the metal plate to be detected; the visual angles of the linear array cameras face to the metal surface, and the visual angles of the linear array cameras are not parallel.
As a preferred embodiment, in the present application, the method for calculating the depth of the metal surface to be measured includes:
h＝(S-S0)/(tgα+tgβ)；
wherein h represents the surface height of the metal plate, S represents the pixel position difference of any point on the surface of the metal plate in the images acquired by the two linear array cameras after being subjected to stereo matching, and S represents the pixel position difference of any point on the surface of the metal plate in the images acquired by the two linear array cameras0And the difference of the corresponding positions of the reference heights is shown, and alpha and beta respectively show the included angle between the visual angle orientation of the two linear array cameras and the direction vertical to the movement direction of the plate.
Meanwhile, the calculation method of the normal solid angle of the metal surface to be measured comprises the following steps:
(1) when the two linear array cameras are basically the same in the metal surface view field position and share the same light source to vertically project the metal surface:
θ＝(β-α)/4+(α+β)(1/2-1/π·arc cos((|I2-I1|/k)1/n))sign(I2-I1)；
(2) when the two linear array cameras are different in view field position on the metal surface and the coplanar light source projection plane is superposed with the imaging plane of the corresponding linear array camera:
θ＝(β-α)/2+arc tg((I2-I1)/(I2+I1))；
wherein theta represents a calculated value of a normal angle of the metal surface, alpha and beta respectively represent an included angle between the direction of a linear array camera viewing angle and a direction perpendicular to the moving direction of the plate, and I1And I2Respectively representing the gray scale of any point of the metal surface in the image acquired by the linear array camera, and k and n represent the mirror reflection coefficient of the metal surface and are determined according to the roughness of the metal surface.
Preferably, according to the pixel position difference of any point on the surface of the metal plate after the stereo matching in the images acquired by the two linear array cameras, the method for calculating the motion speed of the metal plate comprises the following steps:
V＝Pf/S；
wherein V represents the movement speed of the metal sheet to be detected, P represents the visual field distance of the linear array camera on the surface of the metal sheet, f represents the sampling line frequency of the linear array camera, and S represents the pixel position difference in the image acquired by the linear array camera after any point on the surface of the metal sheet to be detected is subjected to stereo matching.
In fig. 2, according to different arrangement modes of the cameras, light sources with different arrangement modes are selected to project the metal surface: 1) when the view field positions of the two linear array cameras on the metal surface are basically the same, the same LED strip-shaped or linear light source or laser light source is adopted to be shared to carry out projection in a direction perpendicular to the movement direction of the metal sheet; 2) when the two linear array cameras are different in view field position on the metal surface, no matter the two linear array cameras face to each other or are opposite to each other, two groups of coplanar light sources of the same type are selected and used, and the coplanar light sources adopt LED strip-shaped, linear light sources or laser light sources. Each view angle linear array camera is matched with a group of coplanar light sources, and each group of coplanar light sources projects to the metal surface along the imaging plane of the linear array camera matched with the coplanar light sources.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described apparatus embodiments are merely illustrative.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A metal surface defect detection method based on linear array camera stereoscopic vision is characterized by comprising the following steps:
s1: projecting the metal surface to be measured by adopting a shared light source or a plurality of coplanar light sources corresponding to the linear array cameras, and acquiring the metal surface image to be measured at different visual angles by a plurality of linear array cameras arranged at different visual angles;
s2: calculating the depth and the movement speed of the metal surface to be detected through stereo matching, and simultaneously determining the gray level corresponding relation of any point on the metal surface to be detected in images acquired by the linear array camera under different visual angles;
s3: calculating the normal angle of the metal surface to be detected according to the gray corresponding relation, and detecting the defects of the metal surface through the fusion of the normal angle and the depth three-dimensional information of the metal surface to be detected and the two-dimensional gray image;
the method for calculating the depth of the surface of the metal to be measured comprises the following steps:
h = (S-S 0)/(tgα+tgβ)；
wherein the content of the first and second substances,hwhich represents the depth of the metal surface,Srepresenting the pixel position difference of any point on the metal surface in the images acquired by the two linear array cameras after stereo matching,S 0indicating that the reference depth corresponds to a difference in position,αandβrespectively representing the included angles between the visual angle directions of the two linear array cameras and the movement direction vertical to the metal surface;
the calculation method of the normal angle of the surface of the metal to be measured comprises the following steps:
(1) when the two linear array cameras are basically the same in the metal surface view field position and share the same light source to vertically project the metal surface:
θ= (β-α)/4+(α+β)(1/2-1/π·arc cos ((|I 2-I 1|/k) n1/))sign(I 2-I 1)；
(2) when the two linear array cameras are different in view field position on the metal surface and the coplanar light source projection plane is superposed with the imaging plane of the corresponding linear array camera:
θ= (β-α)/2+arc tg ((I 2-I 1)/(I 2+I 1))；
wherein the content of the first and second substances,θrepresents the calculated value of the normal angle of the metal surface,αandβrespectively showing the included angle between the visual angle orientation of the two linear array cameras and the movement direction vertical to the metal surface,I 1andI 2respectively representing the gray scale corresponding to the image collected by the linear array camera at any point on the metal surface,kandnthe metal surface specular reflection coefficient is represented and is determined according to the metal surface roughness statistics.
2. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein:
the linear array cameras are arranged on the same side of the surface of the metal to be detected and are randomly arranged back and forth along the movement direction of the metal to be detected; as long as the condition that the visual angles of the linear array cameras face to the metal surface to be detected and the visual angles of the linear array cameras are not parallel is met.
3. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein: the included angle between the linear array camera visual angles is 20-150 degrees.
4. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein: the linear array camera is a common linear array camera or a time delay integral linear array camera.
5. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein: when the linear array cameras are at the same view field position on the metal surface, the linear array cameras project the metal surface to be measured along the direction perpendicular to the metal movement direction by sharing the same LED strip light source or laser light source.
6. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein: when the linear array cameras are different in view field positions on the metal surface, a plurality of coplanar light sources of the same type are matched with the linear array cameras for use, each coplanar light source of the same type projects to an imaging plane of the linear array camera matched with the coplanar light source, and the coplanar light sources adopt LED strip-shaped light sources or laser light sources.
7. The method for detecting defects on metal surfaces based on stereo vision of a line camera as claimed in claim 1, wherein: according to the pixel position difference of any point of the metal surface in the image acquired by the linear array camera after the stereo matching, the method for calculating the motion speed of the metal surface comprises the following steps:
V= Pf/S；
wherein the content of the first and second substances,Vwhich represents the speed of movement of the metal surface,Pthe distance of the field of view of the line camera on the metal surface is shown,frepresenting the sampled line frequency of the line camera,Sand representing the pixel position difference of any point on the metal surface in the acquired image of the linear array camera after stereo matching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010632056.4A CN111624206B (en) | 2020-07-03 | 2020-07-03 | Metal surface defect detection method based on linear array camera stereoscopic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010632056.4A CN111624206B (en) | 2020-07-03 | 2020-07-03 | Metal surface defect detection method based on linear array camera stereoscopic vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111624206A CN111624206A (en) | 2020-09-04 |
| CN111624206B true CN111624206B (en) | 2021-08-31 |
Family
ID=72270575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010632056.4A Active CN111624206B (en) | 2020-07-03 | 2020-07-03 | Metal surface defect detection method based on linear array camera stereoscopic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111624206B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113252567A (en) * | 2021-06-08 | 2021-08-13 | 菲特（天津）检测技术有限公司 | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate |
| CN113804696B (en) * | 2021-09-28 | 2023-01-20 | 北京科技大学 | Method for determining size and area of defect on surface of bar |
| CN114113135A (en) * | 2021-10-29 | 2022-03-01 | 北京兆维科技开发有限公司 | Method for distinguishing foreign matter defects on upper surface and lower surface of glass cover plate |
| CN114113104A (en) * | 2021-11-10 | 2022-03-01 | 厦门聚视智创科技有限公司 | Cell-phone back of body frame 3D face image device |
| CN114235847A (en) * | 2021-12-20 | 2022-03-25 | 深圳市尊绅投资有限公司 | Liquid crystal display panel glass substrate surface defect detection device and detection method |
| CN115511825A (en) * | 2022-09-23 | 2022-12-23 | 天津大学 | Surface defect visual detection method and device based on linear array camera |
| CN115334227B (en) * | 2022-10-18 | 2024-01-19 | 菲特（天津）检测技术有限公司 | Gear image acquisition device and method, gear image acquisition method and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110125A (en) * | 2007-07-25 | 2008-01-23 | 西北师范大学 | Method for constructing metal surface three-dimensional macroscopical feature based on digital picture technology |
| CN102830123A (en) * | 2012-08-16 | 2012-12-19 | 北京科技大学 | On-line detection method of small defect on metal plate strip surface |
| CN105787989A (en) * | 2016-03-18 | 2016-07-20 | 山东大学 | Measurement texture geometric feature reconstruction method based on photometric stereo |
| CN107607546A (en) * | 2017-09-19 | 2018-01-19 | 佛山缔乐视觉科技有限公司 | Leather defect inspection method, system and device based on photometric stereo vision |
| JP6355316B2 (en) * | 2013-10-10 | 2018-07-11 | 英治 神谷 | Defect detection method for light transmissive film |
| CN110308153A (en) * | 2019-08-03 | 2019-10-08 | 广西师范大学 | Metal works defect inspection method, system, storage medium and device based on single eye stereo vision |
-
2020
- 2020-07-03 CN CN202010632056.4A patent/CN111624206B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110125A (en) * | 2007-07-25 | 2008-01-23 | 西北师范大学 | Method for constructing metal surface three-dimensional macroscopical feature based on digital picture technology |
| CN102830123A (en) * | 2012-08-16 | 2012-12-19 | 北京科技大学 | On-line detection method of small defect on metal plate strip surface |
| JP6355316B2 (en) * | 2013-10-10 | 2018-07-11 | 英治 神谷 | Defect detection method for light transmissive film |
| CN105787989A (en) * | 2016-03-18 | 2016-07-20 | 山东大学 | Measurement texture geometric feature reconstruction method based on photometric stereo |
| CN107607546A (en) * | 2017-09-19 | 2018-01-19 | 佛山缔乐视觉科技有限公司 | Leather defect inspection method, system and device based on photometric stereo vision |
| CN110308153A (en) * | 2019-08-03 | 2019-10-08 | 广西师范大学 | Metal works defect inspection method, system, storage medium and device based on single eye stereo vision |
Non-Patent Citations (1)
| Title |
|---|
| 基于光度立体的金属板带表面缺陷三维检测方法;王磊;《中国博士学位论文全文数据库 工程科技Ⅰ辑》;20190715(第7期);第55-72页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111624206A (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111624206B (en) | Metal surface defect detection method based on linear array camera stereoscopic vision | |
| CN102830123B (en) | On-line detection method of small defect on metal plate strip surface | |
| RU2763417C2 (en) | System and related method for detecting small defects on/in glass sheet on process line | |
| US9709390B2 (en) | Method and a device for the inspection of surfaces of an examined object | |
| US6392754B1 (en) | Method and apparatus for measuring the profile of reflective surfaces | |
| CN101639452B (en) | 3D detection method for rail surface defects | |
| US7471383B2 (en) | Method of automated quantitative analysis of distortion in shaped vehicle glass by reflected optical imaging | |
| CN111650212B (en) | Metal surface normal direction three-dimensional information acquisition method based on linear array camera three-dimensional vision | |
| CN102495076A (en) | Method for detecting defects of metal zipper teeth of zipper on basis of machine vision | |
| CN106461575B (en) | Device and method for measuring distortion defect in manufactured float glass strip | |
| CN105866129A (en) | Product surface quality online detection method based on digital projection | |
| KR20140146636A (en) | Inspection device and inspection method for pattern phase difference filter | |
| CN110472722A (en) | Steel billet counting device and method based on machine vision technique | |
| CN104458764B (en) | Curved uneven surface defect identification method based on large-field-depth stripped image projection | |
| WO2016208622A1 (en) | Surface defect detection apparatus and surface defect detection method | |
| CN112432949A (en) | Method for detecting surface defects of gravure roller by using 3D photographing technology | |
| CN104567724A (en) | Method and scanner for the non-contact determination of the position and three-dimensional shape of products on a moving surface | |
| TWI490481B (en) | On - line Inspection Method for Panel 3D Defects | |
| CN110766683B (en) | Pearl finish grade detection method and system | |
| CN109064448A (en) | Medium-and low-speed maglev F rail rail gap detection method | |
| CN111369533B (en) | Rail profile detection method and device based on polarization image fusion | |
| CN108489830A (en) | Crack propagation measuring system | |
| US20220335586A1 (en) | Workpiece surface defect detection device and detection method, workpiece surface inspection system, and program | |
| CN111649697B (en) | Metal strip shape detection method based on stereo vision of linear array camera | |
| TWI700475B (en) | Device for automatically detecting track using reflection transformation imaging and optical stereoscopic image |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |