CN113376183A - Glass defect detection method, system and equipment - Google Patents
Glass defect detection method, system and equipment Download PDFInfo
- Publication number
- CN113376183A CN113376183A CN202110636976.8A CN202110636976A CN113376183A CN 113376183 A CN113376183 A CN 113376183A CN 202110636976 A CN202110636976 A CN 202110636976A CN 113376183 A CN113376183 A CN 113376183A
- Authority
- CN
- China
- Prior art keywords
- glass
- color information
- coordinate
- defect
- acquiring
- 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.)
- Withdrawn
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
- G01N21/95—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
Abstract
The invention provides a glass defect detection method, a system and equipment, which comprises the following steps: step S1: acquiring photos of all surfaces of glass; step S2: establishing a plane coordinate system for each surface photo of the glass, acquiring a coordinate image, and identifying and screening the glass with the appearance defects; step S3: graying the image, setting a grayscale threshold, screening the image exceeding the threshold range as a defect picture to be identified, and acquiring a grayed picture; step S4: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo; step S5: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, judging a pixel coordinate set of the defect position, and acquiring the defect position coordinate set. The defects of the glass can be accurately found out through graying and color information comparison, the positions of the defects are corresponding to the coordinates, the detection process is simplified, the detection accuracy is improved, manual detection is avoided, and the false detection rate is reduced.
Description
Technical Field
The invention relates to the field of image detection, in particular to a glass defect detection method, a system and equipment.
Background
In the production process of glass sheets, various defects such as bubbles, scratches, stones, inclusions, warping and the like are easy to occur, and when the defective glass enters expensive equipment, the defective glass may be broken to damage the equipment or affect the quality of products, so that the defect detection of the glass is required to improve the quality and the production efficiency of the glass. Conventional glass defect inspection is typically manual.
However, most of the existing glass defect detection methods are manual detection, and the detection speed is low and the detection accuracy is low.
Disclosure of Invention
The invention provides a glass defect detection method, a system and equipment, aiming at overcoming the technical problems that most of the existing glass defect detection is manual detection, the detection speed is low, and the detection accuracy is low.
The invention provides a glass detection method, which comprises the following steps: step S1: acquiring photos of all surfaces of glass; step S2: establishing a plane coordinate system for each surface photo of the glass, acquiring a coordinate image, and identifying and screening the glass with the appearance defects; step S3: graying the image, setting a grayscale threshold, screening the image exceeding the threshold range as a defect picture to be identified, and acquiring a grayed picture; step S4: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo; step S5: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, judging a pixel coordinate set of the defect position, and acquiring the defect position coordinate set.
Preferably, the specific steps at step S2 further include steps S21 to S22: step S21: placing lines in the vertical direction and the horizontal direction at equal intervals on the pictures on the surfaces of the glass, and forming a coordinate system; step S22: and judging whether the external lines on the glass surface picture are parallel or vertical to the lines on the coordinate system or not so as to identify and screen the glass with the appearance defects.
Preferably, step S1 is preceded by the following steps: step S0: the glass is placed on the light source and the camera takes a picture of the glass under the light source.
Preferably, step S5 is followed by: step S6: and acquiring a preset value of glass color information, comparing the color information of the defect position with the preset value, detecting the accuracy of the identified defect position, and correspondingly pairing the pixel position identified as the defect with the glass to acquire the glass with the defect.
Preferably, the specific steps at step S4 further include steps S41 to S42: step S41: acquiring color information of pixel points in a gray-scale photo; step S42: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
Preferably, step S5 includes the steps of: step S51: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures; step S52: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information; step S53: and collecting the pixel point coordinates to obtain the coordinates of the defect position.
A glass inspection system, comprising: a photograph acquisition unit: the device is used for acquiring photos of all surfaces of the glass; a coordinate image acquisition unit: the glass is used for establishing a plane coordinate system on each surface photo of the glass, and identifying and screening the appearance defects; a grayed-picture acquisition unit: graying the image, setting a grayscale threshold value, and screening the image exceeding the threshold value range as a defect picture to be identified; a color information acquisition unit: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo; a defect position coordinate set acquisition unit: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, collecting a pixel coordinate set of the defect position, and acquiring the coordinate set of the defect position.
Preferably, the color information acquisition unit includes: a pixel point color information acquisition unit: acquiring color information of pixel points in a gray-scale photo; a pixel point matching unit: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
Preferably, the defect position coordinate set acquiring unit includes: an area-grayed-photograph acquisition unit: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures; an abnormal pixel point coordinate obtaining unit: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information; a coordinate acquisition unit of the defective area: and collecting the pixel point coordinates to obtain the coordinates of the defect area.
The glass detection equipment comprises a camera, a light emitting source, a storage and a processor, wherein the camera is connected with the processor, and the light emitting source is arranged below the camera; the camera is used for shooting and collecting pictures of all surfaces of the glass, and the glass to be detected covers the luminous source; a computer program stored in the memory, the computer program being arranged to perform one of the above-mentioned glass detection methods when run; the processor is configured to execute one of the glass inspection methods described above via the computer program.
Compared with the prior art, the glass detection method, the glass detection system and the glass detection equipment provided by the invention have the following advantages:
1. a glass detection method is characterized in that a defect area is distinguished from a normal area through image graying, the recognition accuracy of a machine to an image is improved, the machine is enabled to compare color information of adjacent pixel photos through the color information of the pixel points corresponding to the coordinates of the pixel points to obtain the pixel points of defects, the coordinate positions of the defect positions are correspondingly judged through the coordinate positions of the pixel points, accordingly, the defect positions of the glass and the glass are obtained, the defects of the glass can be accurately found through graying and color information comparison, the defect positions are corresponding to the coordinate positions, the detection process is simplified, the detection accuracy is improved, manual detection is avoided, and the false detection rate is reduced.
2. The coordinate system is established to glass surface photo, and lines and outside lines through the coordinate system are compared, get rid of the glass that has appearance defect, improve and reject out the scope that detects with the glass of appearance defect, reduce the total number that glass detected for the total speed that detects, simplify the process that detects, improve the use experience that detects.
3. The light source can enable the defect position of the glass to reflect light emitted by the light source when the camera shoots the glass, so that the defect of the glass is highlighted, and the convenience of glass detection is improved.
4. Through comparing with the default, detect glass's defective position once more, can improve and detect the accuracy, avoid influencing the result that detects because of light scheduling problem, reduce because of the mistake survey leads to glass to be decided as to take defective glass.
5. The color information of the pixel point is obtained, the pixel point with the defect directly obtains the pixel point coordinate through the color information through matching the coordinate of the pixel point with the color information, namely the position of the pixel point is located, the coordinate corresponds to the specific position, the detection accuracy is improved, the position detection error can be reduced, the size of the defect can be accurately judged, and the detection diversity is improved.
6. The areas of the gray photos are divided through the coordinates, the color information of the adjacent areas is carried out according to the areas, the pixel point coordinates with abnormal color information are obtained, the number of contrasts can be reduced, the detection time can be shortened through the area contrast, the detection speed is improved, meanwhile, the pixel points which do not meet the conditions can be prevented from being detected through the area contrast, and the detection accuracy is improved.
7. A glass detection system uses a glass detection method, and performs comparison of adjacent pixels through image graying and color information of the pixels to obtain the pixels with defects and coordinates of the pixels, further obtain specific coordinate positions of the defects, judge whether glass is with the defects or not, simplify the detection process, and improve the use experience of users.
8. A glass detection device uses the glass detection method provided by the above, the defects of the appearance can be firstly distinguished and selected from the glass to be detected, the total amount of subsequent detection is reduced, the detection speed is improved, the positions of the glass defects are obtained through color information comparison of images and corresponding matching of coordinate information and color information, the sizes of the defects can be obtained, the detection diversity is improved, the detection process is simplified, further, the detection speed is improved through regional comparison, the misjudgment degree of detection is reduced, and the detection accuracy is improved.
Drawings
FIG. 1 is a flow chart of a method for detecting defects in glass according to a first embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S2 in the method for detecting glass defects according to the first embodiment of the present invention;
FIG. 3 is a detailed flowchart of step S4 in the method for detecting glass defects according to the first embodiment of the present invention;
FIG. 4 is a detailed flowchart of step S5 in the method for detecting glass defects according to the first embodiment of the present invention;
FIG. 5 is a block diagram of a glass defect inspection system according to a second embodiment of the present invention;
FIG. 6 is a block diagram of a color information acquisition unit in a glass defect detection system according to a second embodiment of the present invention;
FIG. 7 is a block diagram of a defect location coordinate set acquisition unit in a glass defect detection system according to a second embodiment of the present invention;
FIG. 8 is a schematic view of the overall structure of a glass defect inspection apparatus according to a third embodiment of the present invention.
Description of reference numerals:
100. a glass defect detection system; 10. a photo acquisition unit; 20. a coordinate image acquisition unit; 30. a grayed picture acquisition unit; 40. a color information acquisition unit; 50. a defect position coordinate set acquisition unit;
401. a pixel point color information acquisition unit; 402. a pixel point matching unit; 501. an area grayed picture acquisition unit; 502. an abnormal pixel point coordinate obtaining unit; 503. a coordinate acquisition unit of the defective area;
1. a glass defect detection apparatus; 11. a camera; 12. a processor; 13. a reservoir.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, a first embodiment of the present invention provides a method for detecting glass defects, including the following steps:
step S1: acquiring photos of all surfaces of glass;
it can be understood that the pictures of all the surfaces are obtained, the defects of the glass can be analyzed and detected from multiple angles, the number of detected samples is increased, the detection is performed from multiple samples, careless detection is avoided, and the detection accuracy is improved.
Step S2: establishing a plane coordinate system for each surface photo of the glass, acquiring a coordinate image, and identifying and screening the glass with the appearance defects;
it can be understood that the coordinate matching of the pixel points can be carried out on the pixel points on the image by establishing a plane coordinate system, and meanwhile, the appearance defects (such as bending, warping and the like) can be selected from the detection samples by judging the appearance of the glass through the coordinate system, so that the number of the subsequent detection samples can be reduced, and the detection speed can be improved.
Step S3: graying the image, setting a grayscale threshold, screening the image exceeding the threshold range as a defect picture to be identified, and acquiring a grayed picture;
it can be understood that the image graying processing is carried out, the special single-channel information in the grayed image is detected, the grayscale threshold of the standard image is set, whether the grayscale value in the image exceeds the set threshold or not is judged, and the exceeding threshold is recorded as a defect picture to be identified, so that the whole detection process is simplified.
Step S4: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo;
the method can be understood that the positions of specific pixel points are obtained by correspondingly matching the pixel points and the coordinate values and correspondingly matching the coordinate values with specific pixel points, and the color information of the pixel points corresponds to the coordinate values of the pixel points, so that the color information of the pixel points of the gray photos is correspondingly matched with the coordinate values, the defect positions can be directly obtained through the coordinate values of the pixel points, and the detection speed is improved.
Step S5: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, judging a pixel coordinate set of the defect position, and acquiring the defect position coordinate set.
It can be understood that the color information is compared between adjacent pixels of the gray-scale photo to judge the pixel coordinate set of the defect position, so as to obtain the coordinate of the defect position, and the isomorphic coordinate obtains the specific coordinate of the defect position, so that the defect detection accuracy can be improved, and the detection speed can be accelerated.
The method for detecting the glass can be understood, a defective area is distinguished from a normal area through image graying, the recognition accuracy of a machine to an image is improved, the machine can compare color information of adjacent pixel photos through the coordinates of pixel points corresponding to the color information of the pixel points to obtain the pixel points of defects, the coordinate positions of the defective positions are correspondingly judged through the coordinate positions of the pixel points, accordingly, the defective positions of the defective glass and the defective positions of the glass are obtained, the defects of the glass can be accurately found through graying and color information comparison, the defective positions are corresponding to the coordinates, the detection process is simplified, the detection accuracy is improved, manual detection is avoided, and the false detection rate is reduced.
Step S1 is preceded by the following steps:
step S0: the glass is placed on the light source and the camera takes a picture of the glass under the light source.
It can be understood that the light source can enable the defect position of the glass to reflect the light emitted by the light source when the camera shoots the glass, so that the defect of the glass is highlighted, and the convenience of glass detection is improved.
Step S5 is followed by:
step S6: and acquiring a preset value of glass color information, comparing the color information of the defect position with the preset value, detecting the accuracy of the identified defect position, and correspondingly pairing the pixel position identified as the defect with the glass to acquire the glass with the defect.
It can be understood that the defect position of the glass is detected again by comparing the defect position with the preset value, so that the detection accuracy can be improved, the detection result is prevented from being influenced by light rays and other problems, and the defect that the glass is mistakenly determined as the glass with defects due to misdetection is reduced.
Referring to fig. 2, the step S2 includes steps S21 to S22:
step S21: placing lines in the vertical direction and the horizontal direction at equal intervals on the pictures on the surfaces of the glass, and forming a coordinate system;
step S22: and judging whether the external lines on the glass surface picture are parallel or vertical to the lines on the coordinate system or not so as to identify and screen the glass with the appearance defects.
The method has the advantages that a coordinate system is established for the glass surface picture, lines of the coordinate system are compared with external lines, glass with appearance defects is eliminated, the detection range of the glass with the appearance defects is widened, the total number of glass detection is reduced, and the total detection speed is increased.
Referring to fig. 3, the step S4 includes steps S41 to S42:
step S41: acquiring color information of pixel points in a gray-scale photo;
step S42: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
The method can be understood to obtain the color information of the pixel points, and the pixel points with the defects directly obtain the coordinates of the pixel points through the color information by matching the coordinates of the pixel points with the color information, namely the positions of the pixel points, and correspond to the specific positions through the coordinates, so that the detection accuracy is improved, the errors of position detection can be reduced, the sizes of the defects can be accurately judged at the same time, and the detection diversity is improved.
Referring to fig. 4, the step S5 includes steps S51 to S52:
step S51: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures;
step S52: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information;
step S53: and collecting the pixel point coordinates to obtain the coordinates of the defect position.
The method can be understood that the area of the gray photo is divided through the coordinates, the color information of the adjacent area is carried out according to the area, the pixel point coordinates with abnormal color information are obtained, the comparison quantity can be reduced, the detection time can be reduced through the area comparison, the detection speed is improved, meanwhile, the pixel points which do not meet the conditions can be prevented from being detected through the area comparison, and the detection accuracy is improved.
Referring to fig. 5, a second embodiment of the present invention provides a glass defect detecting system 100, comprising:
the photograph acquisition unit 10: the device is used for acquiring photos of all surfaces of the glass;
the coordinate image acquisition unit 20: the glass is used for establishing a plane coordinate system on each surface photo of the glass, and identifying and screening the appearance defects;
grayed-picture acquiring unit 30: graying the image, setting a grayscale threshold value, and screening the image exceeding the threshold value range as a defect picture to be identified;
the color information acquisition unit 40: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo;
defect position coordinate set acquisition unit 50: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, collecting a pixel coordinate set of the defect position, and acquiring the coordinate set of the defect position.
The method can be understood that the color information is compared between the adjacent pixels, the coordinates of the defective pixel points are judged, the coordinate set of the defective pixel points is obtained through comparison between the adjacent pixels, the coordinate set of the defective positions is obtained in sequence, the detection accuracy of the defective positions is improved, and meanwhile the detection speed is improved.
Referring to fig. 6, the color information obtaining unit 40 includes:
the pixel color information obtaining unit 401: acquiring color information of pixel points in a gray-scale photo;
pixel point matching unit 402: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
The method can be understood that the color information and the coordinate values of the pixel points in the gray-scale photo are matched, so that when the pixel points are compared subsequently, the coordinate values of the corresponding pixel points can be rapidly matched from the defect pixel points through the matching of the color information and the coordinate values of the pixel points, the specific coordinate set of the defect pixel points is obtained, and the detection speed and accuracy are improved.
Referring to fig. 7, the defect location coordinate set obtaining unit 50 includes:
the area-grayed-photograph acquiring unit 501: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures;
the abnormal pixel point coordinate obtaining unit 502: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information;
the coordinate acquiring unit 503 of the defective area: and collecting the pixel point coordinates to obtain the coordinates of the defect area.
The method can be understood that the area of the gray photo is divided through the coordinates, the color information of the adjacent area is carried out according to the area, the pixel point coordinates with abnormal color information are obtained, the comparison quantity can be reduced, the detection time can be reduced through the area comparison, the detection speed is improved, meanwhile, the pixel points which do not meet the conditions can be prevented from being detected through the area comparison, and the detection accuracy is improved.
It can be understood that, in the glass detection system provided in the second embodiment of the present invention, by using the glass detection method provided in the first embodiment, the gray image and the color information of the pixel point are compared with each other to obtain the pixel point and the pixel point coordinate of the defect, and further obtain the specific coordinate position of the defect, determine whether the glass is defective, simplify the detection process, and improve the user experience.
Referring to fig. 8, a glass defect detecting apparatus 1 for detecting a glass defect position according to a third embodiment of the present invention includes a camera 11, a light source, a storage 13 and a processor 12.
The camera 11 is connected with the processor 12, and the light emitting source is arranged below the camera 11; the camera 11 is used for shooting and collecting pictures of all surfaces of the glass, and the glass to be detected covers the luminous source;
a computer program stored in the memory, the computer program being arranged to perform the glass inspection method of the first embodiment when executed; the processor 12 is arranged to execute a glass inspection method as described in the first embodiment by means of the computer program.
It can be understood that the third embodiment of the present invention provides a glass inspection apparatus, which uses the glass inspection method provided by the first embodiment, to distinguish the shape defect first, and select it from the glass to be inspected, to reduce the total amount of subsequent inspection, to increase the inspection speed, to obtain the position of the glass defect through the color information comparison of the image and the corresponding matching between the coordinate information and the color information, and to obtain the size of the defect, to increase the inspection diversity, and to simplify the inspection process, further, to increase the inspection speed, to reduce the misjudgment degree of the inspection, and to increase the inspection accuracy through the comparison of the regions.
Compared with the prior art, the glass detection method, the glass detection system and the glass detection equipment provided by the invention have the following advantages:
1. a glass detection method is characterized in that a defect area is distinguished from a normal area through image graying, the recognition accuracy of a machine to an image is improved, the machine is enabled to compare color information of adjacent pixel photos through the color information of the pixel points corresponding to the coordinates of the pixel points to obtain the pixel points of defects, the coordinate positions of the defect positions are correspondingly judged through the coordinate positions of the pixel points, accordingly, the defect positions of the glass and the glass are obtained, the defects of the glass can be accurately found through graying and color information comparison, the defect positions are corresponding to the coordinate positions, the detection process is simplified, the detection accuracy is improved, manual detection is avoided, and the false detection rate is reduced.
2. The coordinate system is established to glass surface photo, and lines and outside lines through the coordinate system are compared, get rid of the glass that has appearance defect, improve and reject out the scope that detects with the glass of appearance defect, reduce the total number that glass detected for the total speed that detects, simplify the process that detects, improve the use experience that detects.
3. The light source can enable the defect position of the glass to reflect light emitted by the light source when the camera shoots the glass, so that the defect of the glass is highlighted, and the convenience of glass detection is improved.
4. Through comparing with the default, detect glass's defective position once more, can improve and detect the accuracy, avoid influencing the result that detects because of light scheduling problem, reduce because of the mistake survey leads to glass to be decided as to take defective glass.
5. The color information of the pixel point is obtained, the pixel point with the defect directly obtains the pixel point coordinate through the color information through matching the coordinate of the pixel point with the color information, namely the position of the pixel point is located, the coordinate corresponds to the specific position, the detection accuracy is improved, the position detection error can be reduced, the size of the defect can be accurately judged, and the detection diversity is improved.
6. The areas of the gray photos are divided through the coordinates, the color information of the adjacent areas is carried out according to the areas, the pixel point coordinates with abnormal color information are obtained, the number of contrasts can be reduced, the detection time can be shortened through the area contrast, the detection speed is improved, meanwhile, the pixel points which do not meet the conditions can be prevented from being detected through the area contrast, and the detection accuracy is improved.
7. A glass detection system uses a glass detection method, and performs comparison of adjacent pixels through image graying and color information of the pixels to obtain the pixels with defects and coordinates of the pixels, further obtain specific coordinate positions of the defects, judge whether glass is with the defects or not, simplify the detection process, and improve the use experience of users.
8. A glass detection device uses the glass detection method provided by the above, the defects of the appearance can be firstly distinguished and selected from the glass to be detected, the total amount of subsequent detection is reduced, the detection speed is improved, the positions of the glass defects are obtained through color information comparison of images and corresponding matching of coordinate information and color information, the sizes of the defects can be obtained, the detection diversity is improved, the detection process is simplified, further, the detection speed is improved through regional comparison, the misjudgment degree of detection is reduced, and the detection accuracy is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A glass detection method is characterized in that: the method comprises the following steps:
step S1: acquiring photos of all surfaces of glass;
step S2: establishing a plane coordinate system for each surface photo of the glass, acquiring a coordinate image, and identifying and screening the glass with the appearance defects;
step S3: graying the image, setting a grayscale threshold, screening the image exceeding the threshold range as a defect picture to be identified, and acquiring a grayed picture;
step S4: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo;
step S5: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, judging a pixel coordinate set of the defect position, and acquiring the defect position coordinate set.
2. The glass inspection method according to claim 1, wherein: the specific step at step S2 further includes steps S21 to S22:
step S21: placing lines in the vertical direction and the horizontal direction at equal intervals on the pictures on the surfaces of the glass, and forming a coordinate system;
step S22: and judging whether the external lines on the glass surface picture are parallel or vertical to the lines on the coordinate system or not so as to identify and screen the glass with the appearance defects.
3. The glass inspection method according to claim 1, wherein: step S1 is preceded by the following steps:
step S0: the glass is placed on the light source and the camera takes a picture of the glass under the light source.
4. The glass inspection method according to claim 1, wherein: step S5 is followed by:
step S6: and acquiring a preset value of glass color information, comparing the color information of the defect position with the preset value, detecting the accuracy of the identified defect position, and correspondingly pairing the pixel position identified as the defect with the glass to acquire the glass with the defect.
5. The glass inspection method according to claim 1, wherein: the specific step at step S4 further includes steps S41 to S42:
step S41: acquiring color information of pixel points in a gray-scale photo;
step S42: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
6. The glass inspection method according to claim 1, wherein: step S5 includes the following steps:
step S51: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures;
step S52: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information;
step S53: and collecting the pixel point coordinates to obtain the coordinates of the defect position.
7. A glass inspection system characterized by: the method comprises the following steps:
a photograph acquisition unit: the device is used for acquiring photos of all surfaces of the glass;
a coordinate image acquisition unit: the glass is used for establishing a plane coordinate system on each surface photo of the glass, and identifying and screening the appearance defects;
a grayed-picture acquisition unit: graying the image, setting a grayscale threshold value, and screening the image exceeding the threshold value range as a defect picture to be identified;
a color information acquisition unit: corresponding the pixel points of the gray-scale photo to the coordinate values of the gray-scale photo to obtain the color information of the gray-scale photo;
a defect position coordinate set acquisition unit: and comparing the color information of the pixelized photos with the color information of the adjacent pixels of each grayed photo, collecting a pixel coordinate set of the defect position, and acquiring the coordinate set of the defect position.
8. The glass inspection system of claim 7, wherein: the color information acquisition unit includes:
a pixel point color information acquisition unit: acquiring color information of pixel points in a gray-scale photo;
a pixel point matching unit: and matching the pixel point coordinate values of the gray photos with the pixel point color information.
9. The glass inspection system of claim 7, wherein: the defect position coordinate set acquisition unit includes:
an area-grayed-photograph acquisition unit: dividing each grayed picture into a plurality of areas according to coordinates, and acquiring the area grayed pictures;
an abnormal pixel point coordinate obtaining unit: comparing the color information of adjacent regions according to the regions and the color information of adjacent positions in the regions to obtain the coordinates of the pixel points with abnormal color information;
a coordinate acquisition unit of the defective area: and collecting the pixel point coordinates to obtain the coordinates of the defect area.
10. The utility model provides a glass detection equipment, includes camera, light emitting source, accumulator and treater, its characterized in that:
the camera is connected with the processor, and the light emitting source is arranged below the camera;
the camera is used for shooting and collecting pictures of all surfaces of the glass, and the glass to be detected covers the luminous source;
a computer program stored in the memory, the computer program being arranged to perform a glass inspection method as claimed in any one of claims 1 to 6 when executed;
the processor is configured to execute a glass inspection method as claimed in any one of claims 1 to 6 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636976.8A CN113376183A (en) | 2021-06-08 | 2021-06-08 | Glass defect detection method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636976.8A CN113376183A (en) | 2021-06-08 | 2021-06-08 | Glass defect detection method, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113376183A true CN113376183A (en) | 2021-09-10 |
Family
ID=77576649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110636976.8A Withdrawn CN113376183A (en) | 2021-06-08 | 2021-06-08 | Glass defect detection method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113376183A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708268A (en) * | 2022-06-08 | 2022-07-05 | 深圳市智宇精密五金塑胶有限公司 | Hardware part defect detection method and system |
-
2021
- 2021-06-08 CN CN202110636976.8A patent/CN113376183A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708268A (en) * | 2022-06-08 | 2022-07-05 | 深圳市智宇精密五金塑胶有限公司 | Hardware part defect detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101995223B (en) | Chip appearance detection method and system | |
| KR102058427B1 (en) | Apparatus and method for inspection | |
| WO2017020829A1 (en) | Resolution testing method and resolution testing device | |
| US20110069892A1 (en) | Method of comparing similarity of 3d visual objects | |
| CN110929720B (en) | Component detection method based on LOGO matching and OCR | |
| CN111812103A (en) | Image acquisition device, visual detection system and detection point extraction method | |
| CN115053258A (en) | Display panel detection method, device and system | |
| CN113269769A (en) | Defect detection method, system and equipment based on image registration | |
| TW201317904A (en) | Tag detecting system, apparatus and method for detecting tag thereof | |
| CN108445010A (en) | Automatic optical detection method and device | |
| US20140320638A1 (en) | Electronic device and method for detecting surface flaw of sample | |
| KR101643713B1 (en) | Method for inspecting of product using learning type smart camera | |
| CN113376183A (en) | Glass defect detection method, system and equipment | |
| CN112304969A (en) | Display module detection device, method, apparatus and system and storage medium | |
| CN110596118A (en) | Print pattern detection method and print pattern detection device | |
| CN117115153B (en) | Intelligent printed circuit board quality detection method based on visual assistance | |
| CN102609699A (en) | Device and method for recognizing number of cast workpiece scanned by laser | |
| CN112802017A (en) | Method and device for detecting product external qualification based on workbench | |
| CN109387527A (en) | On a kind of film in film defect detection method | |
| JP2009264876A (en) | Inspection system of product quality, and its method | |
| WO2023034441A1 (en) | Imaging test strips | |
| CN112987356B (en) | Liquid crystal display panel bottom foreign matter filtering device | |
| CN107545560B (en) | Method and device for detecting air bubbles on tire sidewall | |
| CN110441315B (en) | Electronic component testing apparatus and method | |
| CN114066890A (en) | Gear defect detection method and device, computer equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210910 |