CN117191792A - Visual detection method and system for defect of microstrip circulator - Google Patents
Visual detection method and system for defect of microstrip circulator Download PDFInfo
- Publication number
- CN117191792A CN117191792A CN202311089840.5A CN202311089840A CN117191792A CN 117191792 A CN117191792 A CN 117191792A CN 202311089840 A CN202311089840 A CN 202311089840A CN 117191792 A CN117191792 A CN 117191792A
- Authority
- CN
- China
- Prior art keywords
- defect
- area
- region
- microstrip circulator
- edge
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 211
- 238000001514 detection method Methods 0.000 title claims abstract description 139
- 230000000007 visual effect Effects 0.000 title abstract description 19
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims abstract description 69
- 239000010931 gold Substances 0.000 claims abstract description 69
- 229910052737 gold Inorganic materials 0.000 claims abstract description 69
- 229910000859 α-Fe Inorganic materials 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000011179 visual inspection Methods 0.000 claims description 17
- 238000005187 foaming Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 description 10
- 238000001914 filtration Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 3
- 208000003464 asthenopia Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005587 bubbling Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The embodiment of the invention discloses a visual detection method and a visual detection system for defects of a microstrip circulator. The method comprises the steps of collecting macroscopic images of a microstrip circulator to be tested; extracting a characteristic region based on the surface texture, the reflection degree and the region area of the macroscopic image to obtain an edge region, a gold band region and a ferrite region; detecting macroscopic defects based on the edge area, the gold band area and the ferrite area, screening according to the macroscopic defect detection result, and marking and recording the position of the area with suspected crack defects on the macroscopic image; collecting microscopic images of the positions corresponding to the marks and the position records in the micro-strip circulator to be tested, or traversing and collecting microscopic images of all the positions of the micro-strip circulator to be tested; performing microscopic detection of crack defects based on the microscopic image; and judging whether the part of the microstrip circulator to be detected corresponding to the mark and the position record or the part of the microstrip circulator to be detected which is currently acquired has cracks or not according to the microscopic detection result of the crack defect.
Description
Technical Field
The present invention relates to the field of machine vision and electromechanical control. And more particularly, to a method and system for visual inspection of microstrip circulator defects.
Background
Microstrip circulators are used as an important device for communication and radar systems. In the batch production task based on microstrip circulators, it is necessary to detect substrate defects (including edge chipping, gold band scratches, blisters and cracks) rapidly and accurately.
However, the defect detection aspect of the microstrip circulator has the following problems: heavy detection tasks caused by large yield; the volume of the microstrip circulator is generally smaller than that of the paper clip, and the detection is difficult due to the small volume; the detection personnel needs to use a magnifying glass to closely observe the sample to be detected, so that a great amount of time and energy are consumed, and the error detection rate is increased due to eye fatigue caused by long-time detection; when the crack defect is secondarily detected, a scanning electron microscope is needed, the purchase price of the scanning electron microscope is more than 300 ten thousand yuan, and the detection cost is high due to long starting time and low efficiency; the defects are various, each defect has the respective defect grade judgment, and the defect is seriously required to be scrapped.
Therefore, a visual inspection method and system for detecting the defect of the microstrip circulator are needed to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to provide a visual detection method and a visual detection system for a microstrip circulator defect, which are used for solving at least one of the problems in the prior art.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the first aspect of the invention provides a visual inspection method for defects of a microstrip circulator, comprising the following steps of
Collecting a macroscopic image of the microstrip circulator to be tested;
extracting a characteristic region based on the surface texture, the reflection degree and the region area of the macroscopic image to obtain an edge region, a gold band region and a ferrite region;
performing macroscopic defect detection based on the edge region, the gold band region and the ferrite region, screening according to the macroscopic defect detection result, and marking and recording the position of the region with suspected crack defects on the macroscopic image;
collecting microscopic images of parts corresponding to the marks and the position records in the micro-strip circulator to be tested, or traversing and collecting microscopic images of all parts of the micro-strip circulator to be tested;
performing microscopic detection of crack defects based on the microscopic image;
judging whether a crack exists in a part corresponding to the mark and position record or a part of the microstrip circulator to be detected, which is currently acquired, in the microstrip circulator to be detected according to the microscopic detection result of the crack defect.
Optionally, the macro defect detection based on the edge region, the gold band region and the ferrite region comprises
Detecting edge breakage defects of the edge area, and judging whether the edge area has the edge breakage defects or not;
if the edge area does not have the edge breakage defect, detecting the foaming defect of the gold belt area, and judging whether the foaming defect exists in the gold belt area;
if the gold zone area has no foaming defect, detecting gold zone scratch defect of the gold zone area, and judging whether the gold zone area has gold zone scratch defect or not;
and if the gold band area does not have the gold band scratch defect, carrying out crack defect macroscopic detection on the ferrite area, and judging whether the ferrite area has a suspected crack defect or not.
Optionally, the determining whether the ferrite region has suspected crack defects comprises
If the ferrite region has the suspected crack defect, marking and recording the position of the region with the suspected crack defect on the macroscopic image;
and if the ferrite region does not have suspected crack defects, traversing and collecting microscopic images of all parts of the microstrip circulator to be tested.
Optionally, the determining whether the part of the microstrip circulator to be tested corresponding to the mark and the position record or the currently collected part of the microstrip circulator to be tested has the crack according to the microscopic detection result of the crack defect includes
If the straightness of the first microscopic image of the position corresponding to the mark and the position record in the microstrip circulator to be tested is more than or equal to 0.7 and the gray value is less than 70% of the average gray value of the first microscopic image, cracks exist in the position corresponding to the mark and the position record in the microstrip circulator to be tested.
Optionally, the determining whether the part of the microstrip circulator to be tested corresponding to the mark and the position record or the currently collected part of the microstrip circulator to be tested has the crack according to the microscopic detection result of the crack defect further includes
If the straightness of the second microscopic image of the part of the microstrip circulator to be detected, which is currently acquired, is more than or equal to 0.7 and the gray value is less than 70% of the average gray value of the second microscopic image, cracks exist in the part of the microstrip circulator to be detected, which is currently acquired.
Optionally, the feature region extraction based on the surface texture, the reflection degree and the region area of the macroscopic image to obtain an edge region, a gold band region and a ferrite region comprises
Extracting an outer contour of the macroscopic image, and shrinking the outer contour inwards to form a new contour, wherein a region between the outer contour and the new contour is an edge region;
extracting a region with gray values in the new contour being greater than 150% of the average value of the gray values of the macroscopic image and the area being greater than or equal to 20% of the area of the macroscopic image as a gold band region;
and extracting the areas except the gold band area in the new outline as ferrite areas.
Optionally, the edge region edge breakage defect detection includes
Threshold segmentation and edge breakage region extraction are carried out on the edge region;
calculating the centrality and the rectangularity of the edge-breaking area, wherein when the centrality of the edge-breaking area is more than or equal to 0.7 and the rectangularity of the edge-breaking area is more than or equal to 0.7, the edge-breaking area has edge-breaking defects.
Optionally, the screening according to the result of the macro-defect detection comprises
Judging whether the defect size of the edge breakage defect is larger than 2% of the area of the microstrip circulator to be detected, and if not, detecting the foaming defect.
Optionally, the screening according to the result of the macro defect detection further comprises
Judging whether the position of the gold belt scratch defect is in a port bonding area or not;
and if not, carrying out macroscopic detection of the crack defect.
In a second aspect, the present invention provides a visual inspection system for microstrip circulator defects, the system comprising
The first acquisition module is used for acquiring a macroscopic image of the microstrip circulator to be detected;
the feature extraction module is used for extracting feature areas based on the surface texture, the reflection degree and the area of the macroscopic image to obtain an edge area, a gold zone area and a ferrite area;
the macroscopic detection module is used for detecting macroscopic defects based on the edge area, the gold band area and the ferrite area, screening according to the macroscopic defect detection result and marking and recording the positions of the areas with suspected crack defects on the macroscopic image;
the second acquisition module is used for acquiring microscopic images of the positions corresponding to the marks and the position records in the microstrip circulator to be detected or traversing and acquiring microscopic images of all the positions of the microstrip circulator to be detected;
the microscopic detection module is used for performing microscopic detection on the crack defects based on the microscopic image;
and the judging module is used for judging whether cracks exist at the positions corresponding to the marks and the position records or the positions of the microstrip circulator to be detected which are acquired currently in the microstrip circulator to be detected according to the microscopic detection result of the crack defects.
The beneficial effects of the invention are as follows:
the invention provides a visual detection method for the defects of a microstrip circulator, which can realize the general detection of products of different types, improves the detection accuracy and detection efficiency, reduces the detection cost, has smooth overall working flow, simple operation and high automation degree, and has significant significance for actual production.
Drawings
The following describes the embodiments of the present invention in further detail with reference to the drawings.
Fig. 1 shows a flowchart of a method for visually detecting a defect of a microstrip circulator according to an embodiment of the invention.
Fig. 2 shows a flow chart of edge breakage defect detection in the method for visually detecting the defect of the microstrip circulator according to the embodiment of the invention.
Fig. 3 shows a foaming defect detection flowchart in the visual detection method of the micro-strip circulator defect provided by the embodiment of the invention.
Fig. 4 shows a flowchart of detecting a gold band scratch defect in the visual detection method of the microstrip circulator defect provided by the embodiment of the invention.
Fig. 5 shows a flow chart of macroscopic detection of a crack defect in the visual detection method of a microstrip circulator defect provided by the embodiment of the invention.
Fig. 6 shows a microscopic detection flow chart of crack defects in the visual detection method of the microstrip circulator defects provided by the embodiment of the invention.
Fig. 7 is a schematic diagram of a port bonding region in a visual inspection method of a microstrip circulator defect according to an embodiment of the invention.
Detailed Description
In order to more clearly illustrate the present invention, the present invention will be further described with reference to examples and drawings. Like parts in the drawings are denoted by the same reference numerals. It is to be understood by persons skilled in the art that the following detailed description is illustrative and not restrictive, and that this invention is not limited to the details given herein.
The defect detection aspect of the existing microstrip circulator has the following problems: heavy detection tasks caused by large yield; the volume of the microstrip circulator is generally smaller than that of the paper clip, and the detection is difficult due to the small volume; the detection personnel needs to use a magnifying glass to closely observe the sample to be detected, so that a great amount of time and energy are consumed, and the error detection rate is increased due to eye fatigue caused by long-time detection; when the crack defect is secondarily detected, a scanning electron microscope is needed, the purchase price of the scanning electron microscope is more than 300 ten thousand yuan, and the detection cost is high due to long starting time and low efficiency; the defects are various, each defect has the respective defect grade judgment, and the defect is seriously required to be scrapped.
In view of the above, an embodiment of the present invention provides a method for visually detecting a defect of a microstrip circulator, the method includes collecting a macroscopic image of the microstrip circulator to be detected; extracting a characteristic region based on the surface texture, the reflection degree and the region area of the macroscopic image to obtain an edge region, a gold band region and a ferrite region; performing macroscopic defect detection based on the edge region, the gold band region and the ferrite region, screening according to the macroscopic defect detection result, and marking and recording the position of the region with suspected crack defects on the macroscopic image; collecting microscopic images of parts corresponding to the marks and the position records in the micro-strip circulator to be tested, or traversing and collecting microscopic images of all parts of the micro-strip circulator to be tested; performing microscopic detection of crack defects based on the microscopic image; judging whether a crack exists in a part corresponding to the mark and position record or a part of the microstrip circulator to be detected, which is currently acquired, in the microstrip circulator to be detected according to the microscopic detection result of the crack defect.
Specifically, as shown in fig. 1, the embodiment includes macro image acquisition, feature region extraction, macro defect detection, micro image acquisition, fine crack defect detection and output of detection results.
Further, the feature region extraction comprises extracting an edge region, a gold band region and a ferrite region of a microstrip circulator in a macroscopic acquisition image according to features such as texture, gray scale and size by using an image processing algorithm; the macroscopic defect detection comprises edge breakage defect detection, foaming defect detection, gold band scratch defect detection and crack defect coarse detection; the microscopic image acquisition is to transfer the microstrip circulator to be detected to a microscopic camera with larger magnification to acquire an image; the fine detection of the crack defect (microscopic detection of the crack defect) is the subsequent operation of coarse detection of the crack defect, the coarse detection of the crack defect is used for positioning suspected cracks, and the fine detection of the crack defect is used for classifying and identifying cracks and scratches.
Compared with the manual detection, the embodiment has the advantages of higher efficiency, lower cost of manpower and material resources and high degree of automation, and can achieve the effects of improving quality, reducing cost and enhancing efficiency.
In a specific example, as shown in fig. 1, the method includes S1, macro image acquisition, that is, an acquisition personnel places a sample to be detected of a microstrip circulator under a lens of a common industrial camera to acquire an image; preferably, the magnification of the common industrial camera is 1-5 times.
Further, S1 further includes preprocessing, that is, cutting and extracting the region containing the sample in the acquired picture by using image cutting, and removing other background regions.
S2, extracting a characteristic region, namely classifying three regions of an edge region, a gold zone region and a ferrite region according to the surface texture, the reflection degree and the region size of the sample of the microstrip circulator by using a visual processing algorithm;
s3, macroscopic defect detection, namely detection which can be performed without high magnification, including edge breakage defect detection, foaming defect detection, gold band scratch defect detection and crack defect coarse detection, wherein the purpose of the crack defect coarse detection is to mark and record the position of a region suspected to be crack defect on the microstrip circulator;
s4, microscopic image acquisition, namely transferring the microstrip circulator to a microscope camera with larger magnification to acquire images of the marked part in the step S3; preferably, the magnification of the microscope camera is 80 times or more.
S5, precisely detecting the crack defects, namely classifying the defects in the acquired image in the step S4 by using an image processing algorithm according to two characteristics of straightness and depth, removing scratches, and remaining real crack defects;
and S6, outputting a detection result, namely, according to the results output in the S3 and the S5, carrying out sample defect information summarization and output.
The method for constructing the macro-micro two-stage visual platform by using machine vision improves detection efficiency and reduces detection cost.
In one possible implementation, the macro defect detection based on the edge region, the gold band region, and the ferrite region includes: detecting edge breakage defects of the edge area, and judging whether the edge area has the edge breakage defects or not; if the edge area does not have the edge breakage defect, detecting the foaming defect of the gold belt area, and judging whether the foaming defect exists in the gold belt area; if the gold zone area has no foaming defect, detecting gold zone scratch defect of the gold zone area, and judging whether the gold zone area has gold zone scratch defect or not; and if the gold band area does not have the gold band scratch defect, carrying out crack defect macroscopic detection on the ferrite area, and judging whether the ferrite area has a suspected crack defect or not.
In one possible implementation manner, the edge region edge breakage defect detection includes threshold segmentation and edge breakage region extraction of the edge region; calculating the centrality and the rectangularity of the edge-breaking area, wherein when the centrality of the edge-breaking area is more than or equal to 0.7 and the rectangularity of the edge-breaking area is more than or equal to 0.7, the edge-breaking area has edge-breaking defects.
In a specific example, as shown in fig. 2-5, the region used by the edge-chipping detection algorithm is an edge region, and the watershed algorithm is first used to perform threshold segmentation; then extracting a broken edge region by using a Canny operator; and finally screening the final edge collapse area according to two indexes of the centrality and the rectangularity. Preferably, the watershed algorithm has a good segmentation effect on the continuous region, so that the golden zone region and the suspected broken edge region are separated by using the algorithm in the embodiment.
In a specific example, the area used by the blister defect detection algorithm is a gold band area, and the Otsu (maximum inter-class variance method) algorithm is first used for threshold segmentation; then removing noise points by using median filtering; finally, the blister area is marked. Preferably, the maximum inter-class variance method is more universal, and image segmentation is performed by using the algorithm in consideration of only some differences in gray values between the bubbling region on the gold band and the normal gold band region.
In a specific example, the region used by the golden band scratch defect detection algorithm is a golden band region, and the Otsu algorithm and median filtering are used for threshold segmentation and filtering; and then a BLOB (maximum connected domain analysis) algorithm is used for extracting scratch areas of the gold ribbon surface. Specifically, the purpose of this embodiment is to remove noise points on an image, where the mask type in median filtering is rectangular, and the edge processing mode is mirror image.
In a specific example, the area used for coarse detection of the crack defect (macroscopic detection of the crack defect) is a ferrite area, strong light needs to be firstly beaten on the surface of the microstrip circulator, then morphological processing is used for image enhancement, finally Hough straight line extraction is used for marking a suspected crack area, and the suspected crack area comprises scratches and cracks.
In one possible implementation manner, the determining whether the ferrite region has a suspected crack defect includes marking and recording a location of the suspected crack defect on the macroscopic image if the ferrite region has a suspected crack defect; and if the ferrite region does not have suspected crack defects, traversing and collecting microscopic images of all parts of the microstrip circulator to be tested.
In a possible implementation manner, the determining whether the part of the micro-strip circulator to be tested corresponding to the mark and the position record or the currently collected part of the micro-strip circulator to be tested has the crack according to the microscopic detection result of the crack defect includes if the straightness of a first microscopic image of the part of the micro-strip circulator to be tested corresponding to the mark and the position record is greater than or equal to 0.7 and the gray value is less than 70% of the average gray value of the first microscopic image, then the part of the micro-strip circulator to be tested corresponding to the mark and the position record has the crack.
In a possible implementation manner, the determining, according to the result of microscopic detection of the crack defect, whether a crack exists in a portion of the microstrip circulator to be tested, which corresponds to the mark and the position record, or a portion of the microstrip circulator to be tested that is currently collected, further includes if the straightness of a second microscopic image of the portion of the microstrip circulator to be tested that is currently collected is greater than or equal to 0.7 and the gray value is less than 70% of the average gray value of the second microscopic image, then the portion of the microstrip circulator to be tested that is currently collected has the crack.
In a specific example, as shown in fig. 6, the fine crack defect detection (microscopic crack defect detection) is performed by first performing threshold segmentation using the Otsu algorithm, then filtering noise using median filtering, then extracting all scratches and cracks using the BLOB algorithm, and finally extracting crack defects using both straightness and depth features.
In one possible implementation manner, the extracting the feature area based on the surface texture, the reflection degree and the area of the macro image to obtain the edge area, the gold band area and the ferrite area includes: extracting an outer contour of the macroscopic image, and shrinking the outer contour inwards to form a new contour, wherein a region between the outer contour and the new contour is an edge region; extracting a region with gray values in the new contour being greater than 150% of the average value of the gray values of the macroscopic image and the area being greater than or equal to 20% of the area of the macroscopic image as a gold band region; and extracting the areas except the gold band area in the new outline as ferrite areas.
In a specific example, the edge region extraction firstly extracts the outer contour of the microstrip circulator, then contracts the contour inwards by a specific distance to obtain a new contour, and the middle region of the last two contours is the edge region; preferably, the specific distance of retraction comprises 10% of retraction; extracting a gold band region on the microstrip circulator by using a visual processing algorithm and utilizing two characteristics of reflection degree and color; the ferrite region is the difference operation in visual processing of the complete region of the sample and the gold band region.
In one possible implementation manner, the screening according to the result of the macro defect detection includes judging whether the defect size of the edge breakage defect is greater than 2% of the area of the microstrip circulator to be detected, and if not, performing the foaming defect detection.
In a possible implementation manner, the screening according to the result of the macro defect detection further includes determining whether the position of the gold ribbon scratch defect is in a port bonding area; and if not, carrying out macroscopic detection of the crack defect.
In a specific example, as shown in fig. 7, before outputting the detection result, the sample marked with the defect needs to be screened for the last time, if the size of the edge breakage defect exceeds the threshold value, the defect needs to be prompted to be scrapped, otherwise, the defect is normally used; the gold belt scratch defect is screened according to whether the position is in a port bonding area, if so, scrapping is required to be prompted, otherwise, normal use is performed; the crack defects are screened according to whether the classification result is scratches or cracks, the result is that the cracks need to be prompted to be scrapped, and the result is that the scratches can be normally used.
In the embodiment, the sample image acquired by the vision acquisition platform is processed through the machine vision algorithm, the average time spent for detecting one sample is 2s, and the average time spent for detecting one sample by the traditional manual detection method is 30s, so that the detection efficiency is improved; by constructing a macro-micro two-stage visual detection platform, crack defect detection is divided into coarse detection and fine detection, so that the defect detection efficiency is ensured, and meanwhile, the defect identification accuracy is improved; by constructing a macro-micro two-stage visual platform, the detection cost is less than 1 ten thousand yuan, the purchase cost of a scanning electron microscope is more than one million yuan, and the detection cost and the purchase cost are lower than the purchase cost of the scanning electron microscope; the embodiment is simple to operate, the whole working flow is smooth, and the automation degree is high.
Another embodiment of the present invention provides a visual inspection system for a microstrip circulator defect, the system including a first acquisition module for acquiring a macroscopic image of a microstrip circulator to be inspected; the feature extraction module is used for extracting feature areas based on the surface texture, the reflection degree and the area of the macroscopic image to obtain an edge area, a gold zone area and a ferrite area; the macroscopic detection module is used for detecting macroscopic defects based on the edge area, the gold band area and the ferrite area, screening according to the macroscopic defect detection result and marking and recording the positions of the areas with suspected crack defects on the macroscopic image; the second acquisition module is used for acquiring microscopic images of the positions corresponding to the marks and the position records in the microstrip circulator to be detected or traversing and acquiring microscopic images of all the positions of the microstrip circulator to be detected; the microscopic detection module is used for performing microscopic detection on the crack defects based on the microscopic image; and the judging module is used for judging whether cracks exist at the positions corresponding to the marks and the position records or the positions of the microstrip circulator to be detected which are acquired currently in the microstrip circulator to be detected according to the microscopic detection result of the crack defects.
In a specific example, the image acquisition module is used for acquiring images in macro image acquisition and micro image acquisition; the image processing module is used for carrying out image processing on the original image to obtain a characteristic region and corresponding characteristic information; the defect detection module is used for screening and classifying the extracted characteristic areas to obtain final defect areas; and the management decision module is used for evaluating the extracted defect area to obtain decision information for detecting whether the sample piece needs to be scrapped or not.
In the embodiment, the sample image acquired by the vision acquisition platform is processed through the machine vision algorithm, the average time spent for detecting one sample is 2s, and the average time spent for detecting one sample by the traditional manual detection method is 30s, so that the detection efficiency is improved; by constructing a macro-micro two-stage visual detection platform, crack defect detection is divided into coarse detection and fine detection, so that the defect detection efficiency is ensured, and meanwhile, the defect identification accuracy is improved; by constructing a macro-micro two-stage visual platform, the detection cost is less than 1 ten thousand yuan, the purchase cost of a scanning electron microscope is more than one million yuan, and the detection cost and the purchase cost are lower than the purchase cost of the scanning electron microscope; the embodiment is simple to operate, the whole working flow is smooth, and the automation degree is high.
Still another embodiment of the present invention provides a micro-strip circulator defect visual inspection apparatus, including an industrial personal computer, a macro image acquisition camera, a micro image acquisition camera, and a micro platform, wherein the industrial personal computer is used for processing a defect inspection image and storing a defect inspection result, the macro and micro image acquisition cameras are used for acquiring images, and the micro platform is placed under the micro image acquisition platform for positioning a defect marked by a crack defect coarse inspection.
In the description of the present invention, it should be noted that the azimuth or positional relationship indicated by the terms "upper", "lower", etc. are based on the azimuth or positional relationship shown in the drawings, and are merely for convenience of describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element in question must have a specific azimuth, be constructed and operated in a specific azimuth, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
It is further noted that in the description of the present invention, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It should be understood that the foregoing examples of the present invention are provided merely for clearly illustrating the present invention and are not intended to limit the embodiments of the present invention, and that various other changes and modifications may be made therein by one skilled in the art without departing from the spirit and scope of the present invention as defined by the appended claims.
Claims (10)
1. A visual inspection method for microstrip circulator defects is characterized by comprising the following steps of
Collecting a macroscopic image of the microstrip circulator to be tested;
extracting a characteristic region based on the surface texture, the reflection degree and the region area of the macroscopic image to obtain an edge region, a gold band region and a ferrite region;
performing macroscopic defect detection based on the edge region, the gold band region and the ferrite region, screening according to the macroscopic defect detection result, and marking and recording the position of the region with suspected crack defects on the macroscopic image;
collecting microscopic images of parts corresponding to the marks and the position records in the micro-strip circulator to be tested, or traversing and collecting microscopic images of all parts of the micro-strip circulator to be tested;
performing microscopic detection of crack defects based on the microscopic image;
judging whether a crack exists in a part corresponding to the mark and position record or a part of the microstrip circulator to be detected, which is currently acquired, in the microstrip circulator to be detected according to the microscopic detection result of the crack defect.
2. The method for visual inspection of a microstrip circulator defect of claim 1, wherein,
the macro defect detection based on the edge region, the gold band region and the ferrite region comprises
Detecting edge breakage defects of the edge area, and judging whether the edge area has the edge breakage defects or not;
if the edge area does not have the edge breakage defect, detecting the foaming defect of the gold belt area, and judging whether the foaming defect exists in the gold belt area;
if the gold zone area has no foaming defect, detecting gold zone scratch defect of the gold zone area, and judging whether the gold zone area has gold zone scratch defect or not;
and if the gold band area does not have the gold band scratch defect, carrying out crack defect macroscopic detection on the ferrite area, and judging whether the ferrite area has a suspected crack defect or not.
3. The method for visual inspection of a microstrip circulator defect of claim 2, wherein,
the judging whether the ferrite region has suspected crack defects comprises
If the ferrite region has the suspected crack defect, marking and recording the position of the region with the suspected crack defect on the macroscopic image;
and if the ferrite region does not have suspected crack defects, traversing and collecting microscopic images of all parts of the microstrip circulator to be tested.
4. A method for visual inspection of a microstrip circulator defect as claimed in claim 3, wherein,
judging whether cracks exist at the part corresponding to the mark and the position record or the currently acquired part of the microstrip circulator to be detected in the microstrip circulator to be detected according to the microscopic detection result of the crack defects comprises
If the straightness of the first microscopic image of the position corresponding to the mark and the position record in the microstrip circulator to be tested is more than or equal to 0.7 and the gray value is less than 70% of the average gray value of the first microscopic image, cracks exist in the position corresponding to the mark and the position record in the microstrip circulator to be tested.
5. A method for visual inspection of a microstrip circulator defect as claimed in claim 3, wherein,
judging whether cracks exist at the positions corresponding to the marks and the position records in the microstrip circulator to be detected or at the positions of the microstrip circulator to be detected which are currently acquired according to the microscopic detection result of the crack defects, wherein the method further comprises the steps of
If the straightness of the second microscopic image of the part of the microstrip circulator to be detected, which is currently acquired, is more than or equal to 0.7 and the gray value is less than 70% of the average gray value of the second microscopic image, cracks exist in the part of the microstrip circulator to be detected, which is currently acquired.
6. The method for visual inspection of a microstrip circulator defect of claim 5, wherein,
the characteristic region extraction is carried out based on the surface texture, the reflection degree and the region area of the macroscopic image, and the edge region, the gold band region and the ferrite region are obtained
Extracting an outer contour of the macroscopic image, and shrinking the outer contour inwards to form a new contour, wherein a region between the outer contour and the new contour is an edge region;
extracting a region with gray values in the new contour being greater than 150% of the average value of the gray values of the macroscopic image and the area being greater than or equal to 20% of the area of the macroscopic image as a gold band region;
and extracting the areas except the gold band area in the new outline as ferrite areas.
7. The method for visual inspection of a microstrip circulator defect of claim 6, wherein,
the edge region edge breakage defect detection comprises
Threshold segmentation and edge breakage region extraction are carried out on the edge region;
calculating the centrality and the rectangularity of the edge-breaking area, wherein when the centrality of the edge-breaking area is more than or equal to 0.7 and the rectangularity of the edge-breaking area is more than or equal to 0.7, the edge-breaking area has edge-breaking defects.
8. The method for visual inspection of a microstrip circulator defect of claim 7, wherein,
the screening according to the result of the macro defect detection comprises
Judging whether the defect size of the edge breakage defect is larger than 2% of the area of the microstrip circulator to be detected, and if not, detecting the foaming defect.
9. The method for visual inspection of a microstrip circulator defect of claim 8, wherein,
the screening according to the macro defect detection result further comprises
Judging whether the position of the gold belt scratch defect is in a port bonding area or not;
and if not, carrying out macroscopic detection of the crack defect.
10. A visual inspection system for microstrip circulator defects, the system comprising
The first acquisition module is used for acquiring a macroscopic image of the microstrip circulator to be detected;
the feature extraction module is used for extracting feature areas based on the surface texture, the reflection degree and the area of the macroscopic image to obtain an edge area, a gold zone area and a ferrite area;
the macroscopic detection module is used for detecting macroscopic defects based on the edge area, the gold band area and the ferrite area, screening according to the macroscopic defect detection result and marking and recording the positions of the areas with suspected crack defects on the macroscopic image;
the second acquisition module is used for acquiring microscopic images of the positions corresponding to the marks and the position records in the microstrip circulator to be detected or traversing and acquiring microscopic images of all the positions of the microstrip circulator to be detected;
the microscopic detection module is used for performing microscopic detection on the crack defects based on the microscopic image;
and the judging module is used for judging whether cracks exist at the positions corresponding to the marks and the position records or the positions of the microstrip circulator to be detected which are acquired currently in the microstrip circulator to be detected according to the microscopic detection result of the crack defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311089840.5A CN117191792A (en) | 2023-08-28 | 2023-08-28 | Visual detection method and system for defect of microstrip circulator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311089840.5A CN117191792A (en) | 2023-08-28 | 2023-08-28 | Visual detection method and system for defect of microstrip circulator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117191792A true CN117191792A (en) | 2023-12-08 |
Family
ID=88986189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311089840.5A Pending CN117191792A (en) | 2023-08-28 | 2023-08-28 | Visual detection method and system for defect of microstrip circulator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117191792A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689659A (en) * | 2024-02-02 | 2024-03-12 | 深圳市未尔科技有限公司 | Production quality monitoring method based on flat electronic product |
-
2023
- 2023-08-28 CN CN202311089840.5A patent/CN117191792A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689659A (en) * | 2024-02-02 | 2024-03-12 | 深圳市未尔科技有限公司 | Production quality monitoring method based on flat electronic product |
| CN117689659B (en) * | 2024-02-02 | 2024-04-19 | 深圳市未尔科技有限公司 | Production quality monitoring method based on flat electronic product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080622B (en) | Neural network training method, workpiece surface defect classification and detection method and device | |
| CN108355987B (en) | A kind of screen printing of battery quality determining method based on piecemeal template matching | |
| CN109255787B (en) | System and method for detecting scratch of silk ingot based on deep learning and image processing technology | |
| CN108355981A (en) | A kind of battery connector quality determining method based on machine vision | |
| CN103913468A (en) | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line | |
| JP2001509618A (en) | Maskless semiconductor and liquid crystal display inspection method and apparatus | |
| CN117191792A (en) | Visual detection method and system for defect of microstrip circulator | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111681213A (en) | Light guide plate line scratch defect detection method based on deep learning | |
| CN109816627B (en) | Method for detecting weak and small defect target in ink area of plane glass element | |
| CN110335233A (en) | Express-way guard-rail plates defect detecting system and method based on image processing techniques | |
| CN112233059A (en) | Light guide plate defect detection method based on segmentation and decision-making two-stage residual error attention network | |
| JP2000200356A (en) | Method and device for defect classification | |
| CN111415330A (en) | Copper foil appearance defect detection method based on deep learning | |
| CN113421230A (en) | Vehicle-mounted liquid crystal display light guide plate defect visual detection method based on target detection network | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN114972230A (en) | Method and system for detecting defects of circuit board on production line | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN110533660B (en) | Method for detecting silk-screen defect of electronic product shell | |
| CN115661148A (en) | Wafer crystal grain arrangement detection method and system | |
| CN114549493A (en) | Magnetic core defect detection system and method based on deep learning | |
| CN113962929A (en) | Photovoltaic cell assembly defect detection method and system and photovoltaic cell assembly production line | |
| CN115731228B (en) | Gold-plated chip defect detection system and method | |
| CN112991259A (en) | Method and system for detecting defects of semiconductor manufacturing process | |
| CN109886912B (en) | Method for detecting surface defects of thrust bearing retainer |
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 |