CN117664991A - Defect detection system - Google Patents
Defect detection system Download PDFInfo
- Publication number
- CN117664991A CN117664991A CN202311800988.5A CN202311800988A CN117664991A CN 117664991 A CN117664991 A CN 117664991A CN 202311800988 A CN202311800988 A CN 202311800988A CN 117664991 A CN117664991 A CN 117664991A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- defect
- surface images
- image
- segmentation
- 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- Withdrawn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
- 230000007547 defect Effects 0.000 title claims abstract description 89
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 47
- 230000011218 segmentation Effects 0.000 claims abstract description 33
- 238000003709 image segmentation Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims description 81
- 239000003086 colorant Substances 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 description 7
- 238000005192 partition Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012216 screening Methods 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
- G01N21/8851—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
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 discloses a defect detection system, which comprises an image acquisition unit, an image segmentation unit, a segmentation recognition unit, an influence analysis unit, a defect recognition unit and an information output unit, relates to the technical field of defect detection, and solves the technical problems that the specific cause of a defect cannot be well determined in simple defect detection and the subsequent processing of products is inconvenient.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to a defect detection system.
Background
Defect detection generally refers to detection of surface defects of an article, wherein the surface defects are detected by adopting advanced machine vision detection technology, such as spots, pits, scratches, color differences, defects and the like on the surface of a workpiece.
According to the patent display of application number CN202310177291.0, the patent receives the determined abnormal partition, analyzes the abnormal points in the abnormal partition, establishes an external circle of the abnormal partition, establishes a coordinate system by taking the circle center as the origin, acquires distance parameters between the abnormal points and the circle center, processes the abnormal partitions in the electronic element in a similar manner, analyzes whether the positions of the abnormal points are regular, generates different signals through the signal generating unit, displays the generated regular signals through the display terminal, and can automatically analyze the electronic element or directly inspect production equipment when an external person views the regular signals.
Part of existing defect detection systems judge whether defects exist by analyzing images, and define the defects as defective products or abnormal products aiming at the defects, but the defect detection mode cannot well analyze the existing defects, and meanwhile cannot well combine data to judge whether the defects affect the whole, so that the type of the defects cannot be well determined by simple defect detection, and further, the defects are troublesome to subsequent product processing.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a defect detection system, which solves the problems that the specific reasons of defects cannot be well determined by simple defect detection and the subsequent treatment of products is inconvenient.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a defect detection system comprises an image acquisition unit, an image segmentation unit, a segmentation recognition unit, an influence analysis unit, a defect recognition unit and an information output unit.
The image acquisition unit is used for acquiring the surface image of the target object, and the specific acquisition mode is that the surface image of a product is acquired through a proper light source and an image sensor (CCD camera), wherein the target object can be an electronic product, a production material and the like, and the acquired surface image of the target object is transmitted to the image segmentation unit.
The image segmentation unit is used for acquiring the surface image of the target object, identifying the surface image to obtain image information, segmenting the obtained surface image to obtain a plurality of groups of segmented surface images, and transmitting the plurality of groups of segmented surface images to the segmentation identification unit, wherein the specific segmentation mode is as follows:
obtaining the corresponding side lengths of the surface images and respectively recording the side lengths as L1 and L2, then dividing the surface images by the smallest common divisor between the L1 and the L2, dividing the surface images into the surface images according to the n groups of the divided groups by the smallest common divisor when the smallest common divisor exists between the L1 and the L2 and the smallest common divisor is not equal to 1, and dividing the surface images into n=1, 2, …, m and the n values are equal to the smallest common divisor, wherein the specific corresponding side lengths are respectivelyAnd->When L1 and L2 do not have the least common divisor, the image is segmented according to the side length of 1 to obtain n-group segmentation surface images, and the obtained n-group segmentation surface images are transmitted to a segmentation recognition unit.
The segmentation recognition unit is used for acquiring the transmitted multiple groups of segmentation surface images, recognizing the colors of the segmentation surface images, classifying the normal surface images and the abnormal surface images according to the colors, acquiring the abnormal surface images, combining the abnormal surface images according to the marks to obtain abnormal recombined images, transmitting the abnormal recombined images to the defect recognition unit, and obtaining the abnormal recombined images in the following specific modes:
s1: performing label processing on a plurality of groups of segmented surface images according to a segmentation sequence and marking the segmented surface images as i, wherein i=1, 2, … and m, simultaneously acquiring standard surface images of a target object, performing color comparison on the plurality of groups of segmented surface images i and the standard surface images, classifying the segmented surface images with different colors as abnormal surface images, and classifying the segmented surface images with no difference in colors as normal surface images; specifically, the setting of the target object standard surface image is set by the operator himself, and the system can automatically recognize the color difference.
S2: all the abnormal surface images are obtained and recombined according to the labels to obtain an abnormal recombined image, the abnormal surface images before the abnormal recombined image is represented are located at the same position of the labels generated by segmentation, for example, the labels of the segmented abnormal surface images are 45, when the abnormal surface images are recombined, the abnormal surface images are still placed at the positions of the labels of 45, and the like, all the abnormal surface images are placed, and finally the abnormal recombined image is obtained.
The defect identification unit is used for acquiring the transmitted abnormal recombined image, carrying out shape drawing on the abnormal recombined image to obtain shape characteristics, simultaneously calculating characteristic values corresponding to the shape characteristics, matching the calculated characteristic values with a pre-stored comparison template to generate specific reasons of the defects, transmitting the specific reasons of the defects to the information output unit, and generating the specific reasons of the defects in the following modes:
p1: acquiring an abnormal recombined image, selecting a region with color difference from a standard surface image in the abnormal recombined image, marking the region as an abnormal region, and then carrying out shape drawing on the abnormal region to obtain shape characteristics of the abnormal recombined image; specifically, the abnormal region in the abnormal recombined image is selected through the difference of colors, and then the system automatically draws and generates the shape of the abnormal region according to the selected abnormal region.
P2: then h points on the selected shape feature are marked as analysis points, h=1, 2, … and k are marked as analysis points, the h analysis points are positioned on the same horizontal line, color values corresponding to the h analysis points are obtained and marked as Yh, the color values Yh corresponding to the h analysis points are sequenced according to the sampling sequence of the analysis points, the color difference values of two adjacent analysis points are calculated, and the color difference values specifically represent the numerical value difference values corresponding to R, G and B in RGB three colors; specifically, the h analysis points may be one horizontal line located in the transverse direction or one horizontal line located in the longitudinal direction, the specific direction is determined according to the transverse direction and the longitudinal direction, if the transverse direction is longer than the longitudinal direction, the transverse horizontal line is selected as a reference to select the analysis point, and if the longitudinal direction is longer than the transverse direction, the longitudinal horizontal line is selected as a reference to select the analysis point.
P3: and obtaining the change condition of the color value of the analysis point according to the obtained color difference value of the analysis point, and then comparing and matching the analysis point with a pre-stored comparison template to obtain the specific cause information of the defect, wherein the comparison template is expressed as the corresponding change condition of the color of the analysis point under different defect conditions obtained according to big data statistics.
And the information output unit is used for acquiring the transmitted defect specific reason information and displaying the defect specific reason information to an operator through the display equipment.
The invention provides a defect detection system. Compared with the prior art, the method has the following beneficial effects:
the method comprises the steps of dividing an image, screening the divided image with abnormality according to the color difference between the divided image and a standard image, recombining the abnormal image, drawing the shape of the abnormal area, and matching the obtained data with a comparison template to judge the specific cause of the defect.
Drawings
FIG. 1 is a block diagram of a system of the present invention;
FIG. 2 is a first image segmentation diagram of the present invention;
fig. 3 is a second image segmentation diagram according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 to 3, a defect detection system is provided, which includes: the device comprises an image acquisition unit, an image segmentation unit, a segmentation recognition unit, an influence analysis unit, a defect recognition unit and an information output unit, wherein all the units are in unidirectional electrical connection.
The image acquisition unit is used for acquiring the surface image of the target object, and the specific acquisition mode is that the surface image of a product is acquired through a proper light source and an image sensor (CCD camera), wherein the target object can be an electronic product, a production material and the like, and the acquired surface image of the target object is transmitted to the image segmentation unit.
The image segmentation unit is used for acquiring the surface image of the target object, identifying the surface image to obtain image information, segmenting the obtained surface image to obtain a plurality of groups of segmented surface images, and transmitting the plurality of groups of segmented surface images to the segmentation identification unit, wherein the specific segmentation mode is as follows:
obtaining the corresponding side lengths of the surface images and respectively recording the side lengths as L1 and L2, then dividing the surface images by the smallest common divisor between the L1 and the L2, dividing the surface images into the surface images according to the n groups of the divided groups by the smallest common divisor when the smallest common divisor exists between the L1 and the L2 and the smallest common divisor is not equal to 1, and dividing the surface images into n=1, 2, …, m and the n values are equal to the smallest common divisor, wherein the specific corresponding side lengths are respectivelyAnd->When L1 and L2 do not have the least common divisor, dividing the L1 and L2 according to the side length of 1 to obtain n groups of divided surface images, and then obtaining n groups of obtained imagesThe group segmentation surface image is transmitted to a segmentation recognition unit.
In combination with the actual analysis, if the minimum common divisor of the side lengths L1 and L2 is 25 and 45, respectively, the obtained divided surface images are 5 groups, and the side lengths of the single-group divided surface images are 5 and 9, respectively, which is the case that the minimum common divisor exists, and when the values of the L1 and L2 are 34 and 55, respectively, the minimum common divisor does not exist between the two, the areas of the two are calculated, the area is calculated to be 1 according to the side length of 1, and the 34×55 divided surface images are obtained by dividing according to the area 1.
The segmentation recognition unit is used for acquiring the transmitted multiple groups of segmentation surface images, recognizing the colors of the segmentation surface images, classifying the normal surface images and the abnormal surface images according to the colors, acquiring the abnormal surface images, combining the abnormal surface images according to the marks to obtain abnormal recombined images, transmitting the abnormal recombined images to the defect recognition unit, and obtaining the abnormal recombined images in the following specific modes:
s1: performing label processing on a plurality of groups of segmented surface images according to a segmentation sequence and marking the segmented surface images as i, wherein i=1, 2, … and m, simultaneously acquiring standard surface images of a target object, performing color comparison on the plurality of groups of segmented surface images i and the standard surface images, classifying the segmented surface images with different colors as abnormal surface images, and classifying the segmented surface images with no difference in colors as normal surface images; specifically, the setting of the target object standard surface image is set by the operator himself, and the system can automatically recognize the color difference.
In combination with the actual analysis, the sequence of the labels is shown in fig. 2 and 3, one is labeled according to fig. 2, the label is labeled according to the sequence from top to bottom, the other is labeled according to fig. 3, the label is labeled transversely, the default segmentation surface image is obtained by segmentation according to the side length of 1, the side lengths of 12 and 9 can be known from the figure, thus the obtained segmentation surface images are 108, and the area of a single segmentation surface image is 1.
S2: all the abnormal surface images are obtained and recombined according to the labels to obtain an abnormal recombined image, the abnormal surface images before the abnormal recombined image is represented are located at the same position of the labels generated by segmentation, for example, the labels of the segmented abnormal surface images are 45, when the abnormal surface images are recombined, the abnormal surface images are still placed at the positions of the labels of 45, and the like, all the abnormal surface images are placed, and finally the abnormal recombined image is obtained.
The defect identification unit is used for acquiring the transmitted abnormal recombined image, carrying out shape drawing on the abnormal recombined image to obtain shape characteristics, simultaneously calculating characteristic values corresponding to the shape characteristics, matching the calculated characteristic values with a pre-stored comparison template to generate specific reasons of the defects, transmitting the specific reasons of the defects to the information output unit, and generating the specific reasons of the defects in the following modes:
p1: acquiring an abnormal recombined image, selecting a region with color difference from a standard surface image in the abnormal recombined image, marking the region as an abnormal region, and then carrying out shape drawing on the abnormal region to obtain shape characteristics of the abnormal recombined image; specifically, the abnormal region in the abnormal recombined image is selected through the difference of colors, and then the system automatically draws and generates the shape of the abnormal region according to the selected abnormal region.
P2: then h points on the selected shape feature are marked as analysis points, h=1, 2, … and k are marked as analysis points, the h analysis points are positioned on the same horizontal line, color values corresponding to the h analysis points are obtained and marked as Yh, the color values Yh corresponding to the h analysis points are sequenced according to the sampling sequence of the analysis points, the color difference values of two adjacent analysis points are calculated, and the color difference values specifically represent the numerical value difference values corresponding to R, G and B in RGB three colors; specifically, the h analysis points may be one horizontal line located in the transverse direction or one horizontal line located in the longitudinal direction, the specific direction is determined according to the transverse direction and the longitudinal direction, if the transverse direction is longer than the longitudinal direction, the transverse horizontal line is selected as a reference to select the analysis point, and if the longitudinal direction is longer than the transverse direction, the longitudinal horizontal line is selected as a reference to select the analysis point.
P3: and obtaining the change condition of the color value of the analysis point according to the obtained color difference value of the analysis point, and then comparing and matching the analysis point with a pre-stored comparison template to obtain the specific cause information of the defect, wherein the comparison template is expressed as the corresponding change condition of the color of the analysis point under different defect conditions obtained according to big data statistics.
In combination with actual analysis, the color change condition of the analysis point is specifically shown as follows: one is that the color change is smooth, and the specific reason corresponding to the comparison template is that the color change is gradually increased from edge to middle and then gradually decreased from middle to edge: flaws, scratches, cracks, etc., are evaluated according to actual conditions.
And the information output unit is used for acquiring the transmitted defect specific reason information and displaying the defect specific reason information to an operator through the display equipment.
In the second embodiment, the present embodiment is implemented on the basis of the first embodiment, and differs from the first embodiment in that the division identifying unit transmits the generated defect-specific cause information to the influence analyzing unit.
The influence analysis unit is used for acquiring the transmitted defect specific reason information, acquiring basic data of the defect specific reason, calculating an influence value of the defect specific reason according to the basic data, comparing the influence value with a preset value to judge whether the whole is influenced or not, and generating judgment information, wherein the judgment information comprises: the influence exists or does not exist, judgment information is transmitted to the information output unit, and a specific mode for generating a secondary analysis result is as follows:
a1: firstly, establishing a rectangular coordinate system, acquiring two endpoints corresponding to specific reasons of the defects, acquiring coordinates corresponding to the two endpoints, and calculating a distance between the two endpoints according to a formula to obtain a length D1 of the specific reasons of the defects, wherein the distance between the two endpoints is calculated according to the formulaAnd (x 1, y 1) and (x 2, y 2) respectively represent two pointsIs defined by the coordinates of (a).
A2: then the width corresponding to the specific cause of the defect is obtained, the specific obtaining mode of the width is that two points which are farthest in the transverse direction or the longitudinal direction of the specific cause of the defect are obtained, the distance between the two points is obtained and is recorded as the width D2, meanwhile, the surface area corresponding to the specific cause of the defect is obtained by the system and is recorded as S, and then D1, D2 and S are substituted into the formulaCalculating to obtain an influence value Q of a specific cause of the defect, wherein S1 is the surface area of the target object, and a is a preset proportionality coefficient; the specific target object surface area is expressed as the area corresponding to the acquired surface image.
A3: comparing the impact value Q of the specific cause of the defect with a preset value Qy, when Q is more than or equal to Qy, indicating that the impact value of the defect exceeds the preset value, generating an impact signal, otherwise, when Q is less than Qy, indicating that the impact value of the defect does not exceed the preset value, generating an impact signal, and determining the specific preset value Qy by an operator according to actual conditions.
And the information output unit is used for acquiring the transmitted judgment information and displaying the judgment information to an operator through the display equipment.
Embodiment III as embodiment III of the present invention, the emphasis is on combining the implementation procedures of embodiment I and embodiment II.
Some of the data in the above formulas are numerical calculated by removing their dimensionality, and the contents not described in detail in the present specification are all well known in the prior art.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. A defect detection system, comprising:
the image segmentation unit is used for segmenting the surface image by taking the least common divisor corresponding to the side length of the surface image as a segmentation standard to obtain a plurality of groups of segmented surface images, and transmitting the segmented surface images to the segmentation recognition unit;
the segmentation recognition unit is used for classifying the images into a normal surface image and an abnormal surface image according to the colors corresponding to the multiple groups of segmentation surface images, combining the abnormal surface images according to the segmentation marks to obtain an abnormal recombined image, and transmitting the abnormal recombined image to the defect recognition unit;
the defect identification unit is used for marking the area with the color difference of the abnormal recombined image as an abnormal area, drawing the shape of the abnormal area to obtain shape characteristics, matching the shape characteristics with the characteristic values of a pre-stored comparison template to obtain specific reasons of the defect, and transmitting the specific reasons of the defect to the information output unit.
2. The defect detection system of claim 1, wherein the image segmentation unit obtains the plurality of sets of segmented surface images in the following specific manner:
and obtaining the corresponding side lengths of the surface images and respectively marking the side lengths as L1 and L2, then dividing the surface images by the least common divisor between L1 and L2, dividing the surface images into n groups of surface images according to the least common divisor when the least common divisor exists between L1 and L2 and the least common divisor is not equal to 1, dividing the surface images into n groups of surface images according to the least common divisor, and dividing the n groups of surface images according to the side lengths of 1 when the least common divisor does not exist between L1 and L2 to obtain n groups of surface images.
3. The defect detection system of claim 1, wherein the segmentation recognition unit classifies the plurality of sets of segmented surface images in the following specific manner:
a plurality of sets of divided surface images are labeled i in the dividing order and denoted i=1, 2, …, m, then the plurality of sets of divided surface images i are color-compared with a pre-stored standard surface image, and the divided surface images having differences in color are classified as abnormal surface images, and the divided surface images having no differences in color are classified as normal surface images.
4. The defect detection system of claim 1, wherein the segmentation recognition unit reorganizes the abnormal surface image in the following specific manner:
and obtaining all the abnormal surface images, recombining the abnormal surface images according to the labels to obtain an abnormal recombined image, and recombining according to the same label positions.
5. The defect detection system of claim 1, wherein the defect identification unit obtains defect-specific cause information by:
p1: acquiring an abnormal recombined image, selecting a region with color difference from a standard surface image in the abnormal recombined image, marking the region as an abnormal region, and then carrying out shape drawing on the abnormal region to obtain shape characteristics of the abnormal recombined image;
p2: h points on the selected shape feature are marked as analysis points, h=1, 2, … and k are marked as analysis points, the h analysis points are positioned on the same horizontal line, color values corresponding to the h analysis points are obtained and marked as Yh, the corresponding color values Yh are sequenced according to the sampling sequence of the analysis points, and the color difference value of two adjacent analysis points is calculated;
p3: and obtaining the change condition of the color value of the analysis point according to the obtained color difference value of the analysis point, and then comparing and matching the change condition with a pre-stored comparison template to obtain the defect specific cause information.
6. The defect detection system of claim 1, further comprising an impact analysis unit for calculating an impact value of a specific cause of the defect by:
a1: firstly, establishing a rectangular coordinate system, acquiring two endpoints corresponding to specific reasons of the defects, acquiring coordinates corresponding to the two endpoints, and calculating a distance between the two endpoints according to a formula to obtain a length D1 of the specific reasons of the defects;
a2: then the width corresponding to the specific cause of the defect is obtained, the specific obtaining mode of the width is that two points which are farthest in the transverse direction or the longitudinal direction of the specific cause of the defect are obtained, the distance between the two points is obtained and is recorded as the width D2, meanwhile, the surface area corresponding to the specific cause of the defect is obtained by the system and is recorded as S, and then D1, D2 and S are substituted into the formulaAnd calculating an influence value Q of the specific cause of the defect, and comparing the influence value Q with a preset value Qy, wherein S1 is the surface area of the target object, and a is a preset proportionality coefficient.
7. The defect detection system of claim 6, wherein the specific way for the impact analysis unit to compare the impact value with the preset value is:
when Q is more than or equal to Qy, the influence value of the defect exceeds a preset value, and meanwhile an influence signal is generated, otherwise when Q is less than Qy, the influence value of the defect does not exceed the preset value, and meanwhile an influence signal which does not exist is generated.
8. The defect detecting system according to claim 1, wherein the information output unit is configured to acquire the transmitted defect-specific cause information and judgment information while displaying them to the operator via the display device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311800988.5A CN117664991A (en) | 2023-12-25 | 2023-12-25 | Defect detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311800988.5A CN117664991A (en) | 2023-12-25 | 2023-12-25 | Defect detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117664991A true CN117664991A (en) | 2024-03-08 |
Family
ID=90073315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311800988.5A Withdrawn CN117664991A (en) | 2023-12-25 | 2023-12-25 | Defect detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117664991A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118297935A (en) * | 2024-05-07 | 2024-07-05 | 武汉奇克微电子技术有限公司 | Method and system for detecting appearance defects of resistor disc |
| CN118417724A (en) * | 2024-07-04 | 2024-08-02 | 宝鸡市永盛泰钛业有限公司 | Optimized production and processing method of zirconium alloy plate with constant temperature superplasticity |
-
2023
- 2023-12-25 CN CN202311800988.5A patent/CN117664991A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118297935A (en) * | 2024-05-07 | 2024-07-05 | 武汉奇克微电子技术有限公司 | Method and system for detecting appearance defects of resistor disc |
| CN118417724A (en) * | 2024-07-04 | 2024-08-02 | 宝鸡市永盛泰钛业有限公司 | Optimized production and processing method of zirconium alloy plate with constant temperature superplasticity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117664991A (en) | Defect detection system | |
| US7127099B2 (en) | Image searching defect detector | |
| US9064187B2 (en) | Method and system for item identification | |
| CN110035281B (en) | Dead pixel detection method and device and electronic equipment | |
| CN113030123B (en) | AOI detection feedback system based on Internet of things | |
| CN114463296B (en) | Light-weight part defect detection method based on single sample learning | |
| CN115308222B (en) | System and method for identifying poor chip appearance based on machine vision | |
| CN113034624A (en) | Temperature early warning image identification method, system, equipment and storage medium based on temperature sensing color-changing adhesive tape | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN114972230A (en) | Method and system for detecting defects of circuit board on production line | |
| KR101643713B1 (en) | Method for inspecting of product using learning type smart camera | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN115345876A (en) | Bolt thread defect detection method based on ultrasonic image | |
| CN113614774A (en) | Method and system for defect detection in image data of target coating | |
| CN113269758A (en) | Cigarette appearance detection method and test device based on machine vision | |
| CN110243475B (en) | Fabric color difference detection method based on machine vision recognition technology | |
| Radovan et al. | An approach for automated inspection of wood boards | |
| CN112329770B (en) | Instrument scale identification method and device | |
| KR20180022619A (en) | PCB panel inspection method and apparatus | |
| CN112288747A (en) | Intelligent detection method and device for steel billets | |
| JPS6073408A (en) | Pattern recognizing device | |
| TWI447382B (en) | Wood inspection methods and apparatus and program | |
| CN114441554B (en) | Detection method | |
| CN118501177A (en) | Appearance defect detection method and system for formed foil |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240308 |