CN113252557B - Light source device for detecting stripe structure light spraying flaw - Google Patents
Light source device for detecting stripe structure light spraying flaw Download PDFInfo
- Publication number
- CN113252557B CN113252557B CN202110375313.5A CN202110375313A CN113252557B CN 113252557 B CN113252557 B CN 113252557B CN 202110375313 A CN202110375313 A CN 202110375313A CN 113252557 B CN113252557 B CN 113252557B
- Authority
- CN
- China
- Prior art keywords
- light
- light source
- stripe
- flaw
- arc
- 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
- 238000005507 spraying Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 238000009792 diffusion process Methods 0.000 claims abstract description 6
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims abstract description 5
- 229910052782 aluminium Inorganic materials 0.000 claims abstract description 5
- 238000005286 illumination Methods 0.000 claims abstract description 5
- 239000000758 substrate Substances 0.000 claims abstract description 5
- 230000007547 defect Effects 0.000 claims description 40
- 239000011248 coating agent Substances 0.000 claims description 6
- 238000000576 coating method Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000005498 polishing Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 239000010408 film Substances 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000012788 optical film Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002966 varnish Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a stripe structure light spraying flaw detection light source device, which comprises an arc-shaped lamp trough, an LED array light source, a diffusion plate and a light-transmitting film, wherein the arc-shaped lamp trough is provided with a plurality of light sources; the arc-shaped lamp groove is used for ensuring the uniform integral illumination of the detected product; the LED array light source comprises an aluminum substrate fixed inside the arc-shaped lamp trough and an LED lamp fixed on the aluminum substrate; the diffusion plate is used for carrying out light equalizing treatment on the LED array light source so as to ensure the uniformity of light; the light-transmitting film is printed with a sampling pattern for flaw collection, the light source can project a structured light pattern on a detected product through projection, and a spraying flaw sample is shot through the image collection system. The invention has the advantages that the light source device ensures that the image acquisition system can clearly acquire different types of flaws, has higher discrimination with the background, and lays a good image quality foundation for subsequent flaw detection. And the device is simple and convenient to install and has a great economic and applicable value.
Description
Technical Field
The invention particularly relates to a light source device for detecting stripe structure optical spraying flaws.
Background
In recent years, intelligent spray flaw detection has received much attention. Wherein, polishing is a very important ring in the detection of the coating defects, and the design of the light source directly influences the detection effect.
Currently, there are two main ways of polishing for detecting the spraying defects. The first mode of polishing is to project several groups of sine stripe lights with different phases through a liquid crystal display screen, and three-dimensional reconstruction is carried out on the surface of the car body by adopting a host phase unwrapping algorithm to position the flaw. The disadvantages of this mode are: the method has certain limitation on the flaws with no deformation on the surface, and cannot accurately detect the flaws; the light source only can detect static objects by integrally moving the mechanical arm, is high in manufacturing cost and has certain limitation on popularization. The second type of polishing mode is to adopt a uniform polishing mode, and to collect images by completely utilizing the reflected light characteristic of the coating surface flaws, the polishing mode has extremely strict requirements on the position placement and the algorithm of a camera, and the problem that clear shooting cannot be carried out on flaws with small deformation exists. The two polishing modes are combined, the defects are eliminated, the advantages are exerted, and a novel light source device is invented by combining the light source effect.
Disclosure of Invention
The present invention is directed to a light source device for detecting a stripe-structured light-spraying defect, which can solve the above-mentioned problems.
In order to meet the requirements, the technical scheme adopted by the invention is as follows: a light source device for detecting a stripe structure optical spraying defect is provided, which includes
The stripe structure light spraying flaw detection light source device has the advantages that:
the visual light source plays a very important role in detecting the flaws. The good light source system can enable the flaw to present clear characteristics, and the subsequent algorithm detection is convenient. The invention has the advantages that the light source device ensures that the image acquisition system can clearly acquire different types of flaws, has higher discrimination with the background, and lays a good image quality foundation for subsequent flaw detection. And the device is simple and convenient to install and has higher economic and applicable values.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 schematically shows a structural view of a stripe-structured light-coating defect detection light source device according to an embodiment of the present application in use.
Fig. 2 schematically shows a uniform light defect diagram.
Fig. 3 schematically shows a uniform light defect diagram.
FIG. 4 schematically illustrates a sampling pattern of a stripe-structured optical spray defect detection light source apparatus according to one embodiment of the present application.
Fig. 5 schematically shows a schematic diagram of a sampling example of a stripe-structured light-spraying defect detecting light source device according to an embodiment of the present application.
FIG. 6 schematically shows a raw image detected by the stripe-structured light-coating defect detecting light source device according to one embodiment of the present application.
FIG. 7 is a schematic diagram illustrating the defect results detected by the stripe-structure photo-spraying defect detection light source device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings and specific embodiments.
In the following description, references to "one embodiment," "an embodiment," "one example," "an example," etc., indicate that the embodiment or example so described may include a particular feature, structure, characteristic, property, element, or limitation, but every embodiment or example does not necessarily include the particular feature, structure, characteristic, property, element, or limitation. Furthermore, repeated use of the phrase "one embodiment according to the present application" does not necessarily refer to the same embodiment, although it may.
Certain features that are well known to those skilled in the art have been omitted from the following description for the sake of simplicity.
According to an embodiment of the present application, there is provided a stripe-structured light-spraying defect detection light source device, as shown in fig. 1 to 5, including the following structures:
1) Arc light trough: the reasonable appearance size structure is designed according to the appearance structure of the detection product, and the whole illumination of the detected product is ensured to be relatively uniform.
2) LED array light source: the LED array surface light source is used as a light source, the LED array surface light source is provided with an aluminum substrate and is fixed in the lamp trough in consideration of heat dissipation requirements, and the power and the arrangement density of the LED light source need to be designed according to illumination requirements and uniformity conditions, which is not described herein.
3) And (3) diffusion plate: the PC diffusion plate is used for carrying out light equalizing treatment on the LED luminous source, and the uniformity of light is ensured.
4) A light-transmitting film: the light-transmitting film is printed with a design pattern for flaw collection, a specific structured light pattern can be projected on a detected product through projection of a light source, and a spraying flaw sample is clearly shot through an image collection system. The innovative point of the device lies in that clear sample collection can be carried out on deformation defects and non-deformation defects at the same time. The traditional fringe light (sine wave and square wave) can be mainly used for detecting deformation defects, and can only be projected by using a liquid crystal screen or a projector, and the uniform light focuses on detecting the defects with the type of reflectivity change. The film can better combine the two into one, and the specific description and scheme are shown in the part 3.
According to an embodiment of the present application, a design concept of a specific light-transmitting film of a stripe-structured light-spraying defect detection light source device is as follows:
defects are largely classified into two types according to the type of image formation. One is when the surface varnish is damaged, and is mainly expressed in the form of hair, scratches, abrasions, and the like. Such imperfections, due to the greatly altered reflectivity of the reflective surface, are easily picked up by the image acquisition system by uniform illumination and present high contrast and sharp edge information for subsequent processing by the algorithm, as shown in fig. 2.
And the other types of defects such as particles, shrinkage holes, bulges and depressions only have certain deformation because the reflectivity of the sprayed surface is not changed by the defects, the reflection direction of the sprayed surface is changed, and the defects are large and small, so that the uniform polishing mode is difficult to photograph clearly. As shown in fig. 3, the particle defect features in the map are very weak and are not easy to detect by the following algorithm.
By combining the above conditions, the design of the stripe structured light needs to consider that the first type of defects can be clearly photographed, and also needs to make the second type of defects have obvious characteristic photographing, so that the subsequent deep learning target detection is facilitated. However, since the second type of defect does not change the reflection coefficient, it is difficult to photograph a defect only by changing the direction of reflected light. As shown in fig. 4, for illustration, only the concave defects and two light beams are considered, and it can be seen from the figure that the reflected light beams may cross due to the deformation of the sprayed surface, and if the intensities of the light beams 1 and 2 are not equal, images with different brightness are formed on the target surface of the camera, and specific image shape characteristics are presented due to different reflection microstructures at different depths of the concave plus different incident light intensities of the light source.
Summarizing the analysis results, a flaw sampling model with half uniform light and half stripe light is designed, non-deformation flaws such as scratches can be well sampled by the uniform light, deformation flaws such as pits can be clearly sampled by the stripe light, and the model and an actual sampling graph are shown in fig. 4 to 5.
It can be seen that the features of the pits in fig. 5 are not obvious enough near the uniform light, and both the conventional algorithm and the deep learning-based method are easy to miss detection. But the pits are very well characterized within the structured band of fringes. One benefit of this is that if we use deep learning, we can label only deformation-like flaws as positive samples, so that we have sufficient feature discrimination. In the same way, only non-deformation defects such as scratches and the like are marked in a uniform light band to be used as a positive sample. Through the calibration, all positive samples and the background can be guaranteed to have good identification degree, and the deep learning framework can better learn.
The stripe structure optical film can be printed and adjusted according to the size of an actual light source, so that high flexibility is provided, and the stripe structure optical film can be easily adapted to large-scale surface flaw detection or surface flaw detection with a small area without changing the whole system light source framework.
Since the larger the lateral luminance change slope is, the more distinctive the characteristic is for detecting the deformation-like stain, the intensity difference between black and white stripes can be set to the maximum (depending on the printing accuracy). The period design of the stripe structure light depends on the actual size of the detected flaw, and the minimum size of the flaw detection is assumed to be min flaw One period of the stripe is T, and then T needs to be satisfiedI.e. keeping the edge sampling period less than or equal to the minimum defect to be detected.
1. Detection of striped structured light defect shots
As shown in fig. 6, due to the obvious features, after deep learning, the defects of the target detection class can be accurately located after learning by using a deep learning framework of the target detection class. The left image is the original image, and the right image is the detected flaw and is displayed by the minimum bounding rectangle. It can be seen that the dent defect in the figure can be accurately detected. Simultaneously, can also accurately detect the scratch class flaw that appears in the even light when detecting sunken, it is completely coincided with the original intention of our design this type of light source.
By utilizing the novel light source device, two types of defects of deformation and non-deformation (including all defect types basically) can be clearly collected, and the defects can be accurately detected and positioned by a deep learning method, so that the novel light source device has great engineering applicability.
The above-mentioned embodiments only show several embodiments of the present invention, and the description thereof is specific and detailed, but should not be construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the claims.
Claims (3)
1. The utility model provides a stripe structure light spraying flaw detects light source device which characterized in that: comprises an arc-shaped lamp trough, an LED array light source, a diffusion plate and a light-transmitting film;
the arc-shaped lamp groove is used for ensuring the uniform integral illumination of the detected product;
the LED array light source comprises an aluminum substrate fixed inside the arc-shaped lamp trough and LED lamps fixed on the aluminum substrate;
the diffusion plate is used for carrying out light equalizing treatment on the LED array light source so as to ensure the uniformity of light;
a sampling pattern for flaw collection is printed on the light-transmitting film, a structured light pattern can be projected on a detected product through projection of a light source, and a sprayed flaw sample is shot through an image collection system;
half of the structured light pattern is uniform light and half of the structured light pattern is stripe light;
the light-transmitting film is used for realizing that half of uniform light is uniform light and half of stripe light is stripe light when in light emitting.
2. The streak-structured light coating defect detection light source device according to claim 1, wherein: the diffuser plate is a PC diffuser plate.
3. The streak-structured light coating defect detection light source device according to claim 1, wherein: the stripe light satisfies the following condition:
the minimum size for defect detection is minflaw, and one period width of the stripe is T, then T needs to satisfy T <2 minflaw.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110375313.5A CN113252557B (en) | 2021-04-08 | 2021-04-08 | Light source device for detecting stripe structure light spraying flaw |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110375313.5A CN113252557B (en) | 2021-04-08 | 2021-04-08 | Light source device for detecting stripe structure light spraying flaw |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113252557A CN113252557A (en) | 2021-08-13 |
CN113252557B true CN113252557B (en) | 2023-02-03 |
Family
ID=77220447
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110375313.5A Active CN113252557B (en) | 2021-04-08 | 2021-04-08 | Light source device for detecting stripe structure light spraying flaw |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113252557B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118329931B (en) * | 2024-06-07 | 2024-09-03 | 株洲兆源机电科技有限公司 | Electromagnetic wire surface flaw detection equipment and method |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007071562A (en) * | 2005-09-05 | 2007-03-22 | Toray Ind Inc | Surface inspection device, surface inspection method, and manufacturing method of film |
JP2007333608A (en) * | 2006-06-16 | 2007-12-27 | Toray Ind Inc | Inspection device and inspection method of irregular flaw on sheet |
CN101655463A (en) * | 2008-08-20 | 2010-02-24 | Asml控股股份有限公司 | Particle detection on object surface |
JP2011099726A (en) * | 2009-11-05 | 2011-05-19 | Fujitsu Ltd | Surface flaw inspection device and surface flaw inspection method |
JP2012173194A (en) * | 2011-02-23 | 2012-09-10 | Toray Ind Inc | Surface inspection device, surface inspection method, and film manufacturing devise |
CN104024827A (en) * | 2011-11-02 | 2014-09-03 | 株式会社理光 | Image processing apparatus, image-capturing method, and vehicle |
CN105466953A (en) * | 2015-12-28 | 2016-04-06 | 天津大学 | Steel ball surface defect detecting method based on reorganization of steel ball surface reflection pattern integrity |
CN107449370A (en) * | 2016-05-27 | 2017-12-08 | 艾可有限公司 | For the detection means and detection method on the surface for detecting the plane object as sample |
CN109791089A (en) * | 2016-12-15 | 2019-05-21 | 欧姆龙株式会社 | Check device, inspection method and program |
CN110261390A (en) * | 2019-06-13 | 2019-09-20 | 深圳市智能机器人研究院 | A kind of the surface defect Systems for optical inspection and method of diffusing reflection structure light |
TWM589791U (en) * | 2019-08-20 | 2020-01-21 | 智泰科技股份有限公司 | High-precision automatic object surface defect image capturing device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110031483A (en) * | 2019-05-05 | 2019-07-19 | 苏州天准科技股份有限公司 | A kind of glass flaws detection method based on transmission-type Structured Illumination |
-
2021
- 2021-04-08 CN CN202110375313.5A patent/CN113252557B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007071562A (en) * | 2005-09-05 | 2007-03-22 | Toray Ind Inc | Surface inspection device, surface inspection method, and manufacturing method of film |
JP2007333608A (en) * | 2006-06-16 | 2007-12-27 | Toray Ind Inc | Inspection device and inspection method of irregular flaw on sheet |
CN101655463A (en) * | 2008-08-20 | 2010-02-24 | Asml控股股份有限公司 | Particle detection on object surface |
JP2011099726A (en) * | 2009-11-05 | 2011-05-19 | Fujitsu Ltd | Surface flaw inspection device and surface flaw inspection method |
JP2012173194A (en) * | 2011-02-23 | 2012-09-10 | Toray Ind Inc | Surface inspection device, surface inspection method, and film manufacturing devise |
CN104024827A (en) * | 2011-11-02 | 2014-09-03 | 株式会社理光 | Image processing apparatus, image-capturing method, and vehicle |
CN105466953A (en) * | 2015-12-28 | 2016-04-06 | 天津大学 | Steel ball surface defect detecting method based on reorganization of steel ball surface reflection pattern integrity |
CN107449370A (en) * | 2016-05-27 | 2017-12-08 | 艾可有限公司 | For the detection means and detection method on the surface for detecting the plane object as sample |
CN109791089A (en) * | 2016-12-15 | 2019-05-21 | 欧姆龙株式会社 | Check device, inspection method and program |
CN110261390A (en) * | 2019-06-13 | 2019-09-20 | 深圳市智能机器人研究院 | A kind of the surface defect Systems for optical inspection and method of diffusing reflection structure light |
TWM589791U (en) * | 2019-08-20 | 2020-01-21 | 智泰科技股份有限公司 | High-precision automatic object surface defect image capturing device |
Also Published As
Publication number | Publication date |
---|---|
CN113252557A (en) | 2021-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN204629260U (en) | A kind of light source for crown cap defect intelligent detection equipment | |
KR860002073B1 (en) | Method for detecting nonuniformity of substrate coating | |
KR960036673A (en) | How to recognize and evaluate defects in reflective surface coatings | |
CN111693549A (en) | Method for detecting and classifying defects of mobile phone cover plate glass | |
CN113686879A (en) | Optical film defect visual detection system and method | |
CN105466953A (en) | Steel ball surface defect detecting method based on reorganization of steel ball surface reflection pattern integrity | |
IL179385A (en) | Device and method for detecting scratches | |
CN106153010A (en) | Anti-sunshine vision detection system and method based on LED and reflex reflection | |
CN113252557B (en) | Light source device for detecting stripe structure light spraying flaw | |
CN109859519A (en) | A kind of parking stall condition detecting system and its detection method | |
JP2006242886A (en) | Surface flaw inspection device | |
KR101006983B1 (en) | Panel inspection device | |
JP2011208941A (en) | Flaw inspection device and flaw inspection method | |
CN202903689U (en) | Presswork surface quality detecting device | |
JP2018163134A (en) | Surface inspection method and apparatus | |
JP4575202B2 (en) | Defect inspection method and defect inspection apparatus for transparent plate-like body | |
CN220688866U (en) | Shadowless coaxial surface light source for eliminating lattice point influence | |
CN107894420A (en) | A kind of lighting device of cable surface defect ONLINE RECOGNITION system | |
JPH0448251A (en) | bottle inspection equipment | |
CN211014053U (en) | High-precision automatic object surface flaw image capturing device | |
CN210572027U (en) | OLED screen polarization detection device | |
WO2024190081A1 (en) | Image recognition method and device | |
CN107192721B (en) | Illumination light source and surface defect detection device for flat glass surface defect detection | |
JPH0868767A (en) | Apparatus for inspecting flaw of body part of bottle | |
CN222979416U (en) | A multi-mode detection device |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Stripe structured light spraying defect detection light source device Granted publication date: 20230203 Pledgee: Chengdu SME financing Company Limited by Guarantee Pledgor: Chengdu Xiaosong Technology Co.,Ltd. Registration number: Y2024980031779 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |