CN117054447A - Method and device for detecting edge defects of special-shaped glass - Google Patents
Method and device for detecting edge defects of special-shaped glass Download PDFInfo
- Publication number
- CN117054447A CN117054447A CN202311105249.4A CN202311105249A CN117054447A CN 117054447 A CN117054447 A CN 117054447A CN 202311105249 A CN202311105249 A CN 202311105249A CN 117054447 A CN117054447 A CN 117054447A
- Authority
- CN
- China
- Prior art keywords
- shaped glass
- special
- edge
- image
- conveying
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 137
- 230000007547 defect Effects 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000003384 imaging method Methods 0.000 claims description 44
- 238000007688 edging Methods 0.000 claims description 23
- 238000007689 inspection Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 18
- 238000003708 edge detection Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000001678 irradiating effect Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000011088 calibration curve Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P40/00—Technologies relating to the processing of minerals
- Y02P40/50—Glass production, e.g. reusing waste heat during processing or shaping
- Y02P40/57—Improving the yield, e-g- reduction of reject rates
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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application belongs to the field of glass detection, and particularly relates to a method and a device for detecting edge defects of special-shaped glass.
Description
Technical Field
The application relates to the technical field of glass detection, in particular to a method and a device for detecting edge defects of special-shaped glass.
Background
In the glass production process, manufacturers can polish and chamfer the glass edges, so that the glass edges are required for production technology and safety on one hand and are attractive on the other hand. Along with the development of the market, the appearance of glass is not limited to rectangle any more, and the difficulty of edging is also increasing, so that the quality of edging caused is difficult to guarantee, and the demand for defect detection of special-shaped glass edging is more and more urgent.
Disclosure of Invention
The embodiment of the application provides a method and a device for detecting edge defects of special-shaped glass, which are used for detecting the edge defects of the special-shaped glass which moves rapidly.
To this end, according to an aspect of the present application, there is provided a method for detecting edge defects of a shaped glass, comprising the steps of:
s1, providing a conveying device for conveying special-shaped glass, wherein the width direction of the special-shaped glass is perpendicular to the conveying direction of the conveying device;
s2, parallel light sources and imaging modules are distributed on two opposite sides of the conveying device along the conveying direction, the parallel light sources are used for irradiating the edge parts of the special-shaped glass in the width direction, the imaging modules comprise linear array cameras, the linear array cameras are used for collecting the parts of the edge parts of the special-shaped glass in the width direction, which are irradiated by the parallel light sources, the lenses of the linear array cameras are configured to focus on the position of the edge part of the special-shaped glass, which is the widest, and when the width of the special-shaped glass is narrowed, the linear array cameras collect blurred defocused images;
s3, performing sharpening treatment on the defocused image to obtain a restored image;
s4, analyzing the restored image, judging whether defects exist at the edge of the special-shaped glass, and classifying the existing defects.
Optionally, step S2 further includes: and shading the parallel light source, the imaging module and the detected special-shaped glass.
Optionally, in step S2, each imaging module includes two line cameras, the two line cameras are respectively used for collecting the parts of the edges in the width direction irradiated by the parallel light sources from different directions, and the lenses of the two line cameras are configured to be commonly focused at the position of the widest edge of the shaped glass.
Optionally, the two linear array cameras are respectively arranged on the upper side and the lower side of a conveying surface of the conveying device, the conveying surface is used for bearing special-shaped glass, and optical axes of lenses of the two linear array cameras are respectively at an included angle of 45 degrees with the conveying surface.
Optionally, step S3 includes the steps of:
s31, collecting images of edges of special-shaped glass at each pixel position Z of the linear array camera, and generating a fitting curve function g of pixel number-pixel value z (x);
S32, the fitting curve function of the position of the clear image is called g 0 (x) The direction of the pixel increase is positive and the direction of the pixel decrease is negative, by the formula g 0 (x)=g z (x)·i z (x) Determining a corresponding relation change function i z (x) Wherein g 0 (x) And g z (x) Are all multi-order functions;
s33, determining a relation change function i of all pixel positions Z z (x) Then, performing image calibration correction;
s34, fitting curve function g of actual pixel position Z z′ (x) By a relation change function i z′ (x) Fitting curve function g changing into clear image 0′ (x)。
Optionally, step S33 includes the steps of:
s331, placing the edge of the non-defective special-shaped glass in the width direction to a linear array camera for adjusting the focal length of the camera until the edge in the width direction is at the center of the linear array camera and the image is complete, and determining the focal length;
s332, taking the center position of the side imaging of the special-shaped glass in the width direction as a pixel coordinate, and recording as a 0 point;
s333, uniformly moving the special-shaped glass, starting a continuous acquisition mode by the linear array camera until the edge of the special-shaped glass moves out of the linear array camera, and stopping acquisition, wherein the camera stores image data of all pixel positions;
s334, screening pixel positions of the edge of the special-shaped glass in the image data by software, recording curves of all pixel positions, identifying 0 points by the curves of all pixel positions, finding out corresponding conversion relations, and storing templates;
s335, placing the special-shaped glass at a random pixel position, collecting an image through a linear array camera, restoring through calling template parameters, adding external adjusting parameters, enabling a calibration curve to be consistent with a 0-point curve, and generating detection parameters of the special-shaped glass and a template matched with the detection parameters.
Optionally, step S4 includes: comparison g 0′ (x) Synthesized image and g 0 (x) The synthesized standard image is used for detecting defects through threshold values, texture segmentation, feature extraction and image matching.
According to another aspect of the application, there is provided a device for detecting defects at edges of shaped glass, using the detection method as described above, the device comprising a conveying device, an analysis processing module, two sets of parallel light sources and two sets of imaging modules, the conveying device being used for conveying shaped glass; a group of parallel light sources and a group of imaging modules are arranged on two opposite sides of the conveying device along the conveying direction, the parallel light sources are used for irradiating the edge parts of the special-shaped glass in the width direction, the imaging modules comprise linear array cameras, the linear array cameras are used for collecting the parts of the edge parts of the special-shaped glass in the width direction, which are irradiated by the parallel light sources, and the lenses of the linear array cameras are configured to focus on the position of the widest edge part of the special-shaped glass; the analysis processing module is electrically connected with the two groups of imaging modules, and is used for analyzing pictures acquired by the two imaging modules, judging whether defects exist at the edge of the special-shaped glass and classifying the existing defects.
Optionally, the detecting device further includes a front edge detecting module and a rear edge detecting module, where the front edge detecting module and the rear edge detecting module are used for detecting front and rear edges of the shaped glass in the conveying direction respectively.
Optionally, the front edge detection module and the rear edge detection module are symmetrically arranged with respect to the width direction of the special-shaped glass, the front edge detection module and the rear edge detection module each include a detection camera, a first reflection prism, a second reflection prism, an upper edging detection light source and a lower edging detection light source, the upper edging detection light source and the lower edging detection light source respectively irradiate edges of the special-shaped glass in the conveying direction from the upper direction and the lower direction, the first reflection prism and the second reflection prism are respectively positioned on the upper side and the lower side of a conveying surface of the conveying device, the detection camera is positioned above the first reflection prism, the first reflection prism is used for adjusting an imaging angle of the detection camera, and the second reflection prism is used for switching a scanning line position of the detection camera; the detection camera can collect images of upper edging of the edge of the special-shaped glass in the conveying direction through the first reflecting prism, and can collect images of lower edging of the edge of the special-shaped glass in the conveying direction through the first reflecting prism and the second reflecting prism.
The method and the device for detecting the edge defects of the special-shaped glass have the beneficial effects that: compared with the prior art, the detection method of the edge defect of the special-shaped glass has the advantages that the imaging module is designed to be static relative to the conveying device, the lens of the linear camera in the imaging module is configured to focus on the widest edge position of the special-shaped glass, the parallel light source provides uniform illumination, illumination energy does not change along with the change of distance, the defocused image acquired corresponding to the width change of the special-shaped glass is subjected to the sharpness processing, the restored image is obtained and then analyzed and judged, and the detection range can be adapted to the edge detection of the special-shaped glass moving at high speed and covers different types of glass.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a flow chart showing steps of a method for detecting edge defects of a shaped glass according to an embodiment of the present application;
FIG. 2 is a view showing a detecting apparatus (only one side portion in the width direction of the shaped glass is schematically shown) employed in a method for detecting a defect at a side portion of the shaped glass according to an embodiment of the present application;
FIG. 3 is a clear focused image of the edges of a shaped glass in the width direction taken by an imaging module according to one embodiment of the present application;
FIG. 4 is a graph of camera pixel position versus pixel value for the image extraction shown in FIG. 3;
FIG. 5 is a blurred image of defocus of the edge portion in the width direction of a shaped glass acquired by an imaging module according to an embodiment of the present application;
FIG. 6 is a graph of camera pixel position versus pixel value for the image extraction shown in FIG. 5;
FIG. 7 is a blurred image of the edge portion of the shaped glass in the width direction acquired by the imaging module and most out of focus in accordance with an embodiment of the present application;
FIG. 8 is a graph of camera pixel position versus pixel value for the image extraction shown in FIG. 7;
FIG. 9 is a flowchart of an algorithm for performing a sharpening process on a defocused image to obtain a restored image in a detection method according to an embodiment of the present application;
FIG. 10 is a calibration flow chart of a detection method according to an embodiment of the present application;
FIG. 11 is a flow chart illustrating the operation of the detection apparatus according to an embodiment of the present application;
fig. 12 is a schematic structural view of a front side detecting module and a rear side detecting module in the detecting apparatus according to the embodiment of the present application.
Description of main reference numerals:
10. profiled glass;
20. a front edge detection module;
30. a rear edge detection module;
100. a parallel light source;
200. an imaging module; 210. a line camera;
300. detecting a camera;
400. a first reflecting prism;
500. a second reflecting prism;
600. a edging detection light source is arranged;
700. and (5) detecting a light source by lower edging.
Detailed Description
In order that the application may be readily understood, a more complete description of the application will be rendered by reference to the appended drawings. Preferred embodiments of the present application are shown in the drawings. This application may, however, be embodied in many other different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" or "disposed" on another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.
It is to be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are merely for convenience in describing and simplifying the description based on the orientation or positional relationship shown in the drawings, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus are not to be construed as limiting the application.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
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 application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
According to an aspect of the present application, an embodiment of the present application provides a method for detecting edge defects of a shaped glass, as shown in fig. 1 and 2, the method comprising the steps of:
s1, providing a conveying device (not shown in the figure) for conveying the shaped glass 10, wherein the conveying device comprises, but is not limited to, a roller conveyor, and the width direction of the shaped glass 10 is perpendicular to the conveying direction of the conveying device;
s2, arranging parallel light sources 100 and imaging modules 200 on two opposite sides of the conveying device along the conveying direction, wherein the parallel light sources 100 are used for irradiating the edge parts of the special-shaped glass 10 (namely the long edges of the special-shaped glass 10) in the width direction, the imaging modules 200 comprise linear cameras 210, the linear cameras 210 are used for collecting the parts of the edge parts of the special-shaped glass 10 in the width direction, which are irradiated by the parallel light sources 100, lenses of the linear cameras 210 are configured to focus on the widest edge parts of the special-shaped glass 10, and when the width of the special-shaped glass 10 is narrowed, the linear cameras 210 collect blurred defocused images;
s3, performing sharpening treatment on the defocused image to obtain a restored image;
s4, analyzing the restored image, judging whether defects exist at the edge of the special-shaped glass 10, and classifying the existing defects.
In the embodiment of the application, the imaging module 200 is designed to be static relative to the conveying device, the lens of the linear camera 210 in the imaging module 200 is configured to focus on the widest edge position of the shaped glass 10, the parallel light source 100 provides uniform illumination, illumination energy does not change along with the change of distance, the defocused image acquired corresponding to the change of width of the shaped glass 10 is subjected to the sharpness processing, the restored image is obtained, and then the analysis and judgment are performed, so that the detection range can be adapted to the edge detection of the shaped glass 10 moving at high speed, and the detection range covers different types of glass.
The parallel light source 100 can use a high-power point light source to emit parallel light in combination with a lens, and the center of the light spot is a glass edge. The linear camera 210 can be an 8K camera, and can select 4K or 16K according to the width change of the shaped glass 10. The lens of the line camera 210 uses a short focal lens with less distortion and curvature of field.
In one embodiment, step S2 further comprises: the parallel light source 100, the imaging module 200, and the detected shaped glass 10 are subjected to light shielding treatment.
Through shading, the interference of external light is avoided, and the accuracy of image acquisition is improved.
Specifically, the light shielding module provides a dark space where the whole imaging module 200, the parallel light source 100 and the detected shaped glass 10 are all enclosed, external stray light cannot enter, and only light emitted by the parallel light source exists in the space.
In one embodiment, as shown in fig. 1 and 2, in step S2, each imaging module 200 includes two line cameras 210, the two line cameras 210 are respectively used to collect the portions of the sides in the width direction illuminated by the parallel light sources 100 from different directions, and the lenses of the two line cameras 210 are configured to be commonly focused at the widest side position of the shaped glass 10.
By setting as above, the two line cameras 210 are used to collect the edge images of the shaped glass 10 from different directions, and then the collected images are combined, so that the glass surface close to the edge on the shaped glass 10 can be detected, and the detection accuracy is improved.
Specifically, the two line cameras 210 are respectively disposed on the upper and lower sides of the conveying surface of the conveying device, the conveying surface is used for carrying the shaped glass 10, and the optical axes of the lenses of the two line cameras 210 are both at an included angle of 45 ° with the conveying surface.
In one embodiment, as shown in fig. 9, step S3 includes the steps of:
s31, collecting images of each pixel position Z of the linear array camera at the edge of the special-shaped glass, and generating a fitting curve function g of pixel number-pixel value z (x);
S32, the fitting curve function of the position of the clear image is called g 0 (x) Image ofThe direction of the increase of the pixel is positive, the direction of the decrease of the pixel is negative, and the formula g is passed 0 (x)=g z (x)·i z (x) Determining a corresponding relation change function i z (x) Wherein g 0 (x) And g z (x) Are multi-order functions of curve fitting. According to practical experience, the requirement can be generally met by taking 5 steps, g (x) =a.x 5 +b·x 4 +c·x 3 +d·x 2 After two functions are obtained, i is reversely deduced through the relation change of the two functions z (x) In practice it was found that i within every 200 pixels z (x) The higher-order terms of the two-dimensional image are basically consistent, the difference of the lower-order terms is smaller, and the adjacent 100 pixels are actually taken as the same transformation curve, so that the calculated amount can be greatly reduced;
s33, determining a relation change function i of all pixel positions Z z (x) Then, performing image calibration correction;
s34, fitting curve function g of actual pixel position Z z′ (x) By a relation change function i z′ (x) Fitting curve function g changing into clear image 0′ (x)。
As shown in fig. 3-8, the image of the edge in the image module and the corresponding converted camera pixel value curve are shown, wherein the abscissa is the pixel number (pixel position) and the ordinate is the pixel value.
The light emission of any object is information transmission, and the information of the light does not disappear in the process from focusing to defocusing, but the formed image is blurred due to the degradation and fusion of the information, and cannot be clearly captured. The traditional image blur restoration is carried out by analyzing the whole image, the application scene is very complex, and the embodiment of the application utilizes a single simple external environment and illumination condition to carry out analysis and restoration on a single-row image.
The relation change function i z (x) In theory, the glass is only relevant to a lens and a light source, and all glasses accord with the rule on the premise that the lens and the light source are unchanged. The model is ideal, and in the actual detection process, because of the fine difference of the glass, different models are needed to be made on different glass edges, and after the models are generated, the environment is providedThe variation of (c) leads to a deterioration of the image effect, in which case an external modification parameter t needs to be introduced z (x) The environment is corrected. G is obtained after calibration 0′ (x)=g z′ (x)·i z′ (x)+t z′ (x)。
In a specific embodiment, as shown in fig. 10, step S33 includes the steps of:
s331, placing the edge of the non-defective special-shaped glass in the width direction on a linear array camera to adjust the focal length of the camera until the edge in the width direction is at the center of the linear array camera and the image is complete, and determining the focal length;
s332, taking the center position of the side imaging of the special-shaped glass in the width direction as a pixel coordinate, and recording as a 0 point;
s333, uniformly moving the special-shaped glass, starting a continuous acquisition mode by the linear array camera until the edge of the special-shaped glass moves out of the linear array camera, and stopping acquisition, wherein the camera stores image data of all pixel positions;
s334, screening pixel positions of the edge of the special-shaped glass in the image data by software, recording curves of all pixel positions, identifying 0 points by the curves of all pixel positions, finding out corresponding conversion relations, and storing templates;
s335, placing the special-shaped glass at a random pixel position, collecting an image through a linear array camera, restoring through calling template parameters, adding external adjusting parameters, enabling a calibration curve to be consistent with a 0-point curve, and generating detection parameters of the special-shaped glass and a template matched with the detection parameters.
In a specific embodiment, step S4 includes: comparison g 0′ (x) Synthesized image and g 0 (x) The synthesized standard image is used for detecting defects through threshold values, texture segmentation, feature extraction and image matching.
In summary, compared with the prior art that the optical transfer function of the whole image is used for inference, some basic methods of inverse filtering are used, or advanced algorithms such as blind deconvolution, least square deconvolution, non-negative matrix factorization and the like are added for image restoration, too much advanced functions used in the middle take too long time. In the prior art, the detection is performed in a mode of matching the manipulator with the camera, so that the rapid detection requirement cannot be met.
According to another aspect of the present application, an embodiment of the present application further provides a device for detecting edge defects of a shaped glass, using the detection method in any of the above embodiments, as shown in fig. 2 and 12, where the device includes a conveying device (not shown in the drawings), an analysis processing module (not shown in the drawings), two sets of parallel light sources 100, and two sets of imaging modules 200, and the conveying device is used for conveying the shaped glass 10; a group of parallel light sources 100 and a group of imaging modules 200 are arranged on opposite sides of the conveying device along the conveying direction, the parallel light sources 100 are used for irradiating the edges of the shaped glass 10 along the width direction, the imaging modules 200 comprise a linear array camera 210, the linear array camera 210 is used for collecting the parts of the edges of the shaped glass 10 along the width direction irradiated by the parallel light sources, and the lenses of the linear array camera 210 are configured to focus on the widest edge position of the shaped glass 10; the analysis processing module is electrically connected to the two imaging modules 200, and is used for analyzing the pictures acquired by the two imaging modules 200, judging whether defects exist at the edge of the special-shaped glass, and classifying the existing defects.
The analysis processing module comprises an FPGA, a display card and a multiple data processing architecture of a computer host, and is used for meeting the complex detection environment and detection speed.
The detection device adopts the detection method in the embodiment, so that the detection device also has the advantages of adapting to the edge detection of the special-shaped glass moving at high speed, covering different types of glass in the detection range, and the like, and the detection device is not limited herein.
In one embodiment, as shown in fig. 12, the inspection apparatus further includes a front edge inspection module 20 and a rear edge inspection module 30, and the front edge inspection module 20 and the rear edge inspection module 30 are used to inspect the front and rear edges of the shaped glass 10 in the conveying direction (i.e., the narrow edges of the shaped glass 10), respectively.
Through the above arrangement, the parallel light sources and the imaging modules which are arranged on the opposite sides of the conveying device along the conveying direction are matched with the front edge detection module 20 and the rear edge detection module 30, so that the defect detection on the front, rear, left and right sides of the special-shaped glass 10 can be realized.
In a specific embodiment, as shown in fig. 12, the front edge detection module 20 and the rear edge detection module 30 are symmetrically arranged with respect to the width direction of the shaped glass 10, each of the front edge detection module 20 and the rear edge detection module 30 includes a detection camera 300, a first reflection prism 400, a second reflection prism 500, an upper edging detection light source 600 and a lower edging detection light source 700, the upper edging detection light source 600 and the lower edging detection light source 700 respectively irradiate edges of the shaped glass 10 in the conveying direction from the upper and lower directions, the first reflection prism 400 and the second reflection prism 500 are respectively positioned on the upper and lower sides of the conveying surface of the conveying device, the detection camera 300 is positioned above the first reflection prism 400, the first reflection prism 400 is used for adjusting the imaging angle of the detection camera 300, and the second reflection prism 500 is used for switching the scanning line position of the detection camera 300; the detection camera 300 can collect an image of the upper edging of the edge portion of the shaped glass 10 in the conveying direction by the first reflection prism 400, and the detection camera 300 can collect an image of the lower edging of the edge portion of the shaped glass 10 in the conveying direction by the first reflection prism 400 and the second reflection prism 500.
Specifically, when the shaped glass 10 moves to the solid line position in the drawing, the inspection camera 300 sees the lower edging of the shaped glass 10 through the second reflecting prism 500, and when reaching the broken line position in the drawing, the inspection camera 300 sees the upper edging through the first reflecting prism 400 while blocking the second reflecting prism 500, and the second reflecting prism 500 no longer forms an image.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. The method for detecting the edge defects of the special-shaped glass is characterized by comprising the following steps of:
s1, providing a conveying device for conveying special-shaped glass, wherein the width direction of the special-shaped glass is perpendicular to the conveying direction of the conveying device;
s2, parallel light sources and imaging modules are distributed on two opposite sides of the conveying device along the conveying direction, the parallel light sources are used for irradiating the edge parts of the special-shaped glass in the width direction, the imaging modules comprise linear array cameras, the linear array cameras are used for collecting the parts of the edge parts of the special-shaped glass in the width direction, which are irradiated by the parallel light sources, the lenses of the linear array cameras are configured to focus on the position of the edge part of the special-shaped glass, which is the widest, and when the width of the special-shaped glass is narrowed, the linear array cameras collect blurred defocused images;
s3, performing sharpening treatment on the defocused image to obtain a restored image;
s4, analyzing the restored image, judging whether defects exist at the edge of the special-shaped glass, and classifying the existing defects.
2. The method according to claim 1, wherein step S2 further comprises: and shading the parallel light source, the imaging module and the detected special-shaped glass.
3. The detection method according to claim 1, wherein in step S2, each of the imaging modules includes two line cameras for collecting, respectively, portions of the side portions in the width direction illuminated by the parallel light sources from different directions, and lenses of the two line cameras are configured to be commonly focused at the widest side portion position of the shaped glass.
4. The detection method according to claim 3, wherein the two line cameras are respectively arranged on the upper side and the lower side of a conveying surface of the conveying device, the conveying surface is used for bearing the shaped glass, and optical axes of lenses of the two line cameras are respectively at an included angle of 45 degrees with the conveying surface.
5. The method according to any one of claims 1 to 4, wherein step S3 comprises the steps of:
s31, collecting images of edges of special-shaped glass at each pixel position Z of the linear array camera, and generating a fitting curve function g of pixel number-pixel value z (x);
S32, the fitting curve function of the position of the clear image is called g 0 (x) The direction of the pixel increase is positive and the direction of the pixel decrease is negative, by the formula g 0 (x)=g z (x)·i z (x) Determining a corresponding relation change function i z (x) Wherein g 0 (x) And g z (x) Are all multi-order functions;
s33, determining a relation change function i of all pixel positions Z z (x) Then, performing image calibration correction;
s34, fitting curve function g of actual pixel position Z z′ (x) By a relation change function i z′ (x) Fitting curve function g changing into clear image 0′ (x)。
6. The detection method according to claim 5, wherein step S33 includes the steps of:
s331, placing the edge of the non-defective special-shaped glass in the width direction to a linear array camera for adjusting the focal length of the camera until the edge in the width direction is at the center of the linear array camera and the image is complete, and determining the focal length;
s332, taking the center position of the side imaging of the special-shaped glass in the width direction as a pixel coordinate, and recording as a 0 point;
s333, uniformly moving the special-shaped glass, starting a continuous acquisition mode by the linear array camera until the edge of the special-shaped glass moves out of the linear array camera, and stopping acquisition, wherein the camera stores image data of all pixel positions;
s334, screening pixel positions of the edge of the special-shaped glass in the image data by software, recording curves of all pixel positions, identifying 0 points by the curves of all pixel positions, finding out corresponding conversion relations, and storing templates;
s335, placing the special-shaped glass at a random pixel position, collecting an image through a linear array camera, restoring through calling template parameters, adding external adjusting parameters, enabling a calibration curve to be consistent with a 0-point curve, and generating detection parameters of the special-shaped glass and a template matched with the detection parameters.
7. The method according to claim 5, wherein step S4 includes: comparison g 0′ (x) Synthesized image and g 0 (x) The synthesized standard image is used for detecting defects through threshold values, texture segmentation, feature extraction and image matching.
8. A device for detecting defects of edge parts of special-shaped glass, which is characterized by adopting the detection method as claimed in any one of claims 1-7, wherein the detection device comprises a conveying device, an analysis processing module, two groups of parallel light sources and two groups of imaging modules, and the conveying device is used for conveying the special-shaped glass; a group of parallel light sources and a group of imaging modules are arranged on two opposite sides of the conveying device along the conveying direction, the parallel light sources are used for irradiating the edge parts of the special-shaped glass in the width direction, the imaging modules comprise linear array cameras, the linear array cameras are used for collecting the parts of the edge parts of the special-shaped glass in the width direction, which are irradiated by the parallel light sources, and the lenses of the linear array cameras are configured to focus on the position of the widest edge part of the special-shaped glass; the analysis processing module is electrically connected with the two groups of imaging modules, and is used for analyzing pictures acquired by the two imaging modules, judging whether defects exist at the edge of the special-shaped glass and classifying the existing defects.
9. The apparatus according to claim 8, further comprising a front edge detection module and a rear edge detection module for detecting front and rear edges of the shaped glass in the conveying direction, respectively.
10. The inspection apparatus according to claim 9, wherein the front edge inspection module and the rear edge inspection module are symmetrically arranged with respect to a width direction of the shaped glass, each of the front edge inspection module and the rear edge inspection module includes an inspection camera, a first reflection prism for adjusting an imaging angle of the inspection camera, an upper edging inspection light source and a lower edging inspection light source for irradiating edges of the shaped glass in the conveying direction from upper and lower directions, respectively, the first reflection prism and the second reflection prism being located on upper and lower sides of a conveying surface of the conveying apparatus, respectively, the inspection camera being located above the first reflection prism, the first reflection prism being for adjusting an imaging angle of the inspection camera, the second reflection prism being for switching a scanning line position of the inspection camera; the detection camera can collect images of upper edging of the edge of the special-shaped glass in the conveying direction through the first reflecting prism, and can collect images of lower edging of the edge of the special-shaped glass in the conveying direction through the first reflecting prism and the second reflecting prism.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311105249.4A CN117054447A (en) | 2023-08-30 | 2023-08-30 | Method and device for detecting edge defects of special-shaped glass |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311105249.4A CN117054447A (en) | 2023-08-30 | 2023-08-30 | Method and device for detecting edge defects of special-shaped glass |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117054447A true CN117054447A (en) | 2023-11-14 |
Family
ID=88660689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311105249.4A Pending CN117054447A (en) | 2023-08-30 | 2023-08-30 | Method and device for detecting edge defects of special-shaped glass |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117054447A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117405693A (en) * | 2023-12-13 | 2024-01-16 | 深圳市泰启光电有限公司 | Equipment and method for processing quality inspection of touch screen substrate |
-
2023
- 2023-08-30 CN CN202311105249.4A patent/CN117054447A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117405693A (en) * | 2023-12-13 | 2024-01-16 | 深圳市泰启光电有限公司 | Equipment and method for processing quality inspection of touch screen substrate |
CN117405693B (en) * | 2023-12-13 | 2024-02-23 | 深圳市泰启光电有限公司 | Equipment and method for processing quality inspection of touch screen substrate |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7683946B2 (en) | Detection and removal of blemishes in digital images utilizing original images of defocused scenes | |
CN110243831B (en) | Surface defect acquisition system, surface defect detection method, surface defect detection device and storage medium | |
CN110596132A (en) | System suitable for industrial image detection | |
CN106645197B (en) | Online detection system for detecting particles on surface of precision optical element and application method | |
US20070253638A1 (en) | Digital Image Acquisition and Processing System | |
US20050068448A1 (en) | Method of detecting and correcting dust in digital images based on aura and shadow region analysis | |
CN117054447A (en) | Method and device for detecting edge defects of special-shaped glass | |
CN113608378B (en) | Full-automatic defect detection method and system based on LCD (liquid crystal display) process | |
WO2022126870A1 (en) | Three-dimensional imaging method and method based on light field camera and three-dimensional imaging measuring production line | |
CN116223519A (en) | Wafer detection equipment, detection method, system and readable storage medium | |
CN110648301A (en) | Device and method for eliminating imaging reflection | |
CN116359233A (en) | Square battery appearance defect detection method and device, storage medium and electronic equipment | |
JP2012185149A (en) | Defect inspection device and defect inspection processing method | |
CN116543247A (en) | Data set manufacturing method and verification system based on photometric stereo surface reconstruction | |
CN106772974B (en) | The system and method for quick three-dimensional refractive index micro-imaging | |
CN112748071A (en) | Transparent or translucent medium defect detection system and method | |
CN112866689B (en) | SFR algorithm-based optical focusing method | |
CN111103309A (en) | Method for detecting flaws of transparent material object | |
CN109612408B (en) | Method and device for testing emission angle of semiconductor laser and readable storage medium | |
KR102259721B1 (en) | Apparatus and method for surface inspection | |
CN112798608B (en) | Optical detection device and optical detection method for side wall of inner cavity of mobile phone camera support | |
CN111912854B (en) | Large-area surface defect optical detection system and method based on galvanometer rapid scanning | |
CN110838107A (en) | Method and device for intelligently detecting defects of 3C transparent component by variable-angle optical video | |
CN113034455B (en) | Method for detecting pockmarks of planar object | |
CN117078666B (en) | Two-dimensional and three-dimensional combined defect detection method, device, medium and equipment |
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 |