LU504273B1 - Method for Detecting Integrity of Switch Interface - Google Patents
Method for Detecting Integrity of Switch Interface Download PDFInfo
- Publication number
- LU504273B1 LU504273B1 LU504273A LU504273A LU504273B1 LU 504273 B1 LU504273 B1 LU 504273B1 LU 504273 A LU504273 A LU 504273A LU 504273 A LU504273 A LU 504273A LU 504273 B1 LU504273 B1 LU 504273B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- image
- gray level
- network interface
- sampling
- new
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005070 sampling Methods 0.000 claims abstract description 67
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000001186 cumulative effect Effects 0.000 claims description 15
- 238000005315 distribution function Methods 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 abstract description 12
- 238000011179 visual inspection Methods 0.000 abstract description 12
- 238000001514 detection method Methods 0.000 description 14
- 208000003464 asthenopia Diseases 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 3
- 229910052802 copper Inorganic materials 0.000 description 3
- 239000010949 copper Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011016 integrity testing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
Disclosed is a method for detecting integrity of switch interface, relating to the field of machine vision, mainly including: a gray image of a switch image containing a network interface is obtained, and bilinear interpolation is carried out on the gray image to obtain an up-sampling image; histogram equalization is carried out on the up-sampling image to obtain an enhanced image, a gray level after mapping of each new gray level is determined respectively according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image in the histogram equalization process. With the embodiments of the application, all network interfaces contained in a target image may be tested simultaneously without carrying out visual inspection in sequence, so that the time required for inspection is shortened.
Description
METHOD FOR DETECTING INTEGRITY OF SWITCH INTERFACE LU504273
The application relates to the field of machine vision, in particular to a method for detecting integrity of a switch interface.
A network interface of a switch may be damaged to some extent due to bumps during transportation of the switch, and as a result, the contact of the network interface may be bad and subsequent use may be affected.
Therefore, after the batch of switches is transported to a point of sale or a point of inventory, the relevant personnel need to extract a certain proportion of switches therefrom to perform a visual inspection, and check the integrity of each network interface one by one during the visual inspection to determine that there is no abnormal network interface in the inspected batch.
However, since the network interface is small in size, in order to ensure the accuracy of the detection result, an inspector tends to invest a lot of time to perform the inspection, even then, it may be difficult to ensure the inspection accuracy, and meanwhile, the visual inspection is prone to cause visual fatigue to further reduce the inspection efficiency and accuracy.
Aiming at the above technical problem, the application provides a method for detecting integrity of a switch interface, in which graying and bilinear interpolation are carried out on a front image of a switch containing a network interface to obtain an up-sampling image, a gray level after mapping is determined respectively for a new gray level and a gray level except the new gray level in the up-sampling image to obtain a target image containing more details, and finally, integrity detection of the network interface in the switch is realized in a template matching mode. All network interfaces contained in the target image may be tested simultaneously without carrying out visual inspection in sequence, so that the time required for inspection is shortened, meanwhile, the visual fatigue caused by manual visual inspection 1s effectively avoided, and therefore, the accuracy and the efficiency of the integrity inspection of the network interfaces of the switch are improved.
Embodiments of the application provide a method for detecting integrity of switch interface, which includes the following operations.
A front image of a switch containing a network interface is collected, graying is carried out to obtain a gray image, and up-sampling is carried out on the gray image through bilinear LU504273 interpolation to obtain an up-sampling image.
Histogram equalization is carried out on the up-sampling image to obtain an enhanced image, a gray level after mapping is determined respectively for each new gray level and a gray level except the new gray level in the up-sampling image in the histogram equalization process, the gray level after mapping of each new gray level is respectively determined according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image, and the new gray level is a gray level existing in the up-sampling image but not existing in the gray image.
Template matching is carried out on the enhanced image by using a template corresponding to a standard network interface, whether an abnormal network interface exists in the enhanced image or not is judged according to a matching result, and the abnormal network interface is located under the condition that the abnormal network interface exists.
Furthermore, in the method for detecting integrity of a switch interface, the operation that the gray level after mapping of each new gray level is respectively determined according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image includes the following operations.
A mapped value of a cumulative distribution function of each new gray level is determined according to the frequency occupancy ratio of each new gray level in the up-sampling image and the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, the larger the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, the smaller the mapped value of a cumulative distribution function of each new gray level.
The gray level after mapping of each new gray level is determined according to the mapped value of a cumulative distribution function of each new gray level.
Furthermore, in the method for detecting integrity of a switch interface, the operation that template matching is carried out on the enhanced image by using a template corresponding to a standard network interface, and whether an abnormal network interface exists in the enhanced image or not is judged according to a matching result includes the following operations.
The similarity between the template corresponding to the standard network interface and an area to be detected in the enhanced image is acquired, and the area to be detected is an area in the enhanced image, which is as large as the template.
Under the condition that the similarity is greater than a preset first threshold value, it is judged that the area to be detected is the area where a normal network interface is located. LU504273
Under the condition that the similarity is not greater than the preset first threshold value, whether the similarity is greater than a preset second threshold value or not is judged, if the judgment result is yes, the area to be detected is judged as the area where an abnormal interface is located, and the preset second threshold value is smaller than the preset first threshold value.
Furthermore, in the method for detecting integrity of a switch interface, the similarity refers to Structural Similarity Index Measure (SSIM).
Furthermore, in the method for detecting integrity of a switch interface, the similarity refers to Pearson Correlation Coefficient (PCCs).
Furthermore, the method for detecting integrity of a switch interface, before a front image of a switch containing a network interface is collected, further includes: parallel light is disposed to illuminate the switch containing the network interface.
Furthermore, the method for detecting integrity of a switch interface, after histogram equalization is carried out on the up-sampling image to obtain an enhanced image, further includes: edge detection is carried out on the enhanced image, and an edge detection result is taken as a new enhanced image.
Furthermore, the method for detecting integrity of a switch interface, an operator used in edge detection is any one of Roberts operator, Prewitt operator, Sobel operator and Canny operator.
Furthermore, the method for detecting integrity of a switch interface further includes: an abnormal network interface is located under the condition that it exists.
The embodiments of the application provide a method for detecting integrity of an switch interface, compared with the relevant art, the embodiments of the application have the beneficial effects that: all network interfaces contained in the target image may be tested simultaneously without carrying out visual inspection in sequence, so that the time required for inspection is shortened, meanwhile, the visual fatigue caused by manual visual inspection is effectively avoided, and therefore, the accuracy and the efficiency of the integrity inspection of the network interfaces of the switch are improved.
In order to describe the technical solutions in the embodiments of the application or the relevant art more clearly, the drawings required to be used in descriptions about the embodiments or the relevant art will be simply introduced below, obviously, the drawings described below are only some embodiments of the application, and other drawings can further be obtained by those of ordinary skill in the art according to the drawings without LU504273 creative work.
Fig. 1 is a flow diagram of a method for detecting integrity of a switch interface provided by an embodiment of the application.
In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described below in combination with the drawings and embodiments. It is to be understood that the specific embodiments described herein are for the purpose of explaining the application only and are not intended to limit the application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the application without creative efforts shall fall within the protection scope of the application.
Specific details such as the specific system structure, technology, etc. are given in the following description for the purpose of illustration rather than limitation to enable a thorough understanding of the embodiments of the application. However, it will be understood by the skilled in the art that the application may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, apparatuses, circuits and methods are omitted so as not to prejudice the description of the application with unnecessary details.
Terms “first” and “second” are only adopted for description and should not be understood to indicate or imply relative importance or implicitly indicate the number of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of these features; and in the description of the embodiment, unless otherwise specified, "multiple" means two or more.
Embodiments of the application provide a method for detecting integrity of switch interface, as shown in Fig. 1, which includes the following operations.
In S101, a front image of a switch containing a network interface is collected, graying is carried out to obtain a gray image, and up-sampling is carried out on the gray image through bilinear interpolation to obtain an up-sampling image.
In S102, histogram equalization is carried out on the up-sampling image to obtain an enhanced image, a gray level after mapping is determined respectively for each new gray level and a gray level except the new gray level in the up-sampling image in the histogram equalization process, and the new gray level is a gray level existing in the up-sampling image but not existing in the gray image.
The gray level after mapping of each new gray level is respectively determined LU504273 according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image.
In S103, template matching is carried out on the enhanced image by using a template 5 corresponding to a standard network interface, whether an abnormal network interface exists in the enhanced image or not is judged according to a matching result, and the abnormal network interface is located under the condition that the abnormal network interface exists.
Through the above, all network interfaces contained in the target image may be tested simultaneously without carrying out visual inspection in sequence, so that the time required for inspection is shortened, meanwhile, the visual fatigue caused by manual visual inspection is effectively avoided, and therefore, the accuracy and the efficiency of the integrity inspection of the network interfaces of the switch are improved.
The purpose of the embodiments of the application is: the integrity detection of a rated network interface in the switch is realized by machine vision, image processing and other technical means, the time required for detection is shortened, and the detection accuracy is improved.
Furthermore, In S101, a front image of a switch containing a network interface is collected, graying is carried out to obtain a gray image, and up-sampling is carried out on the gray image through bilinear interpolation to obtain an up-sampling image.
A multi-layer shelf may be disposed for storing switches, the switches are oriented in a unified way, so as to collect images on the side, containing network interfaces, of the switches, the resolution performance of a camera needs to be high enough, and indoor ambient light may be set in advance to ensure that the ambient light is bright enough and even, so that the details of the collected images may be presented more clearly.
As different switches may have different positions on the shelf, visual field blind areas may exist in image acquisition equipment, which may fail to capture a complete front image of the switch containing the network interface, therefore, a plurality of cameras may be disposed in the embodiments of the application, the shooting angle of each camera may be fixed respectively, and each camera only captures switch images within the horizontal perspective of a camera lens.
In the embodiments of the application, it also may be that the image acquisition equipments are disposed on the front of the switch containing the network interface in parallel, the image acquisition equipment is moved and captures images, finally, all the shot images are combined to obtain the front image of the switch, therefore, it may effectively avoid the bad influence of different lens distances from different positions in the switch to the image LU504273 acquisition equipment on the acquired images.
Optionally, before the front image of the switch containing the network interface is collected, parallel light perpendicular to the switch containing the network interface may also be disposed to irradiate the switch, therefore, the details of the switch interface may be better presented in the front image collected, thus improving the subsequent integrity detection accuracy at the network interface.
Conventional graying processing is carried out on the collected images to remove the influence of excess color factors, which may effectively reduce the amount of calculation in the detection process. The graying process includes: the maximum pixel value of a pixel point in the front image of the switch containing the network interface in the three RGB channels is taken as the gray value of the pixel point in the gray image.
The appearance detection of batch of switch interfaces is mainly aimed at the deformation and defect of copper contacts; however, it is difficult to effectively find the deformation or damage that may exist in a short time through visual observation, which limits the efficiency of integrity detection of the network interface of the switch.
In the same image, there are a plurality of network interfaces on the side, containing the network interfaces, of the switch, therefore, if it is processed directly, the corresponding area of each network interface is small, an accurate detection result may not be obtained, therefore, the embodiments of the application expect to obtain an image with higher resolution and process it while retaining the information in the original image, meanwhile, compared with the nearest neighbor interpolation method, bilinear interpolation obtains less sawtooth in the up-sampling image, which may make the information in the original image be retained more complete, therefore, in the embodiments of the application, bilinear interpolation is used to realize the up-sampling processing of the gray image, the up-sampling image with larger size after up-sampling may be obtained respectively, and meanwhile, the bilinear interpolation process in the embodiments of the application adopts the same up-sampling ratio for rows and columns.
It should be noted that the image may be scaled by using bilinear interpolation, the steps of image scaling by using bilinear interpolation are as follows: a scaling factor between a target image and an original image is calculated, and the scaling factor includes the proportions of row direction and column direction respectively; by using the scaling factor, it is pushed back from the pixel position in the target image to the virtual pixel position in the original image; four pixel points adjacent to each other in the direction of width and height are found from the virtual pixel position, and the pixel values in the target image are obtained by LU504273 using bilinear interpolation calculation of the four pixel points. Specifically, each pixel of the image output by the bilinear interpolation algorithm is the result of four pixels (2x2) operation in the original image.
Furthermore, in S102, histogram equalization is carried out on the up-sampling image to obtain an enhanced image, and a gray level after mapping is determined respectively for each new gray level and a gray level except the new gray level in the up-sampling image in the histogram equalization process.
The gray level after mapping of each new gray level is respectively determined according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image, and the new gray level is a gray level existing in the up-sampling image but not existing in the gray image.
In the embodiments of the application, histogram equalization is used to enhance the contrast of the image so as to improve the clarity of the fuzzy edge contour, however, during histogram equalization, some gray levels with less pixel number distribution may be lost without difference, or these gray levels with less number of pixel points may not be obvious, as a result, copper contacts with a small distribution of pixel points and the gray level of the edge may not be obvious, resulting in the failure to effectively conduct subsequent integrity detection of the network interface.
After bilinear interpolation, the pixel points generated may be in an edge high frequency area or a uniform low frequency area of the up-sampling image, while the edge high frequency area of the gray image is more likely to have a new gray level in the up-sampling image, that is, the gray level that does not exist in the original gray image, because these pixel points are located at the high frequency edge of the gray gradient, in the bilinear interpolation calculation of adjacent pixel points, new gray levels are more likely to appear, on the contrary, in a low frequency area with uniform gray values, the gray values of adjacent pixel points are close to each other, and the gray levels generated after the calculation of bilinear interpolation are gray levels that are close to these adjacent pixel points.
Therefore, in the embodiments of the application, a first gray level histogram corresponding to the up-sampling image and a second gray level histogram corresponding to the gray image may be obtained respectively to screen out each new gray level existing in the first gray level histogram but not in the second gray level histogram.
In the embodiments of the application, the gray level after mapping of each new gray level is respectively determined according to the proportion of the frequency of each new gray level in the first gray level histogram to the frequency of all new gray levels in the first gray LU504273 histogram.
Histogram equalization is a simple and effective image enhancement technique, which changes the gray level of each pixel in the image by changing the histogram of the image, and itis mainly used to enhance the contrast of the image with a small dynamic range. Since the gray distribution in the original image may be concentrated in a narrow range, the image is not clear enough. For example, the gray level of an overexposed image is concentrated in a high brightness range, while under exposure will make the gray level of the image concentrate in a low brightness range
By adopting the histogram equalization, the histogram of the original image may be transformed into a uniform distribution form, which increases the dynamic range of gray value difference between pixels, so as to achieve the effect of enhancing the overall contrast of the image. In other words, the basic principle of histogram equalization is: the gray value with a large number of pixels in the image (that is, the gray value that plays a major role in a picture) is broadened, while the gray value with a small number of pixels (that is, the gray value that does not play a major role in the picture) is merged, so as to increase the contrast, make the image clear, and achieve the purpose of enhancement.
However, for the up-sampling image obtained in the embodiments of the application, there are new gray levels which do not exist in the original gray image, the existence of these new gray levels may enable the details of the network interface in the embodiments of the application to be completely preserved, however, if the up-sampling image is directly equalized by gray histogram, in the enhanced image after histogram equalization, these new gray levels are not obviously reserved in the enhanced image due to their small frequency, which makes it still unable to conduct the integrity detection of the network interface on the basis of the enhanced image.
In the embodiments of the application, the operation that a gray level after mapping is determined respectively for each new gray level and a gray level except the new gray level includes the following operations.
A mapped value of a cumulative distribution function of each new gray level is determined according to the frequency occupancy ratio of each new gray level in the up-sampling image and the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, the larger the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, the smaller the mapped value of a cumulative distribution function of each new gray level; and the gray level after mapping of each new gray level is determined according to the mapped value of a cumulative distribution LU504273 function of each new gray level.
Meanwhile, a mapped value of a cumulative distribution function of a gray level except each new gray level is determined according to the frequency occupancy ratio of the gray level except each new gray level in the up-sampling image.
Specifically, the process of obtaining the mapped value of the cumulative distribution function of each gray level in the up-sampling image includes:
NE SG sp = gl) x {I~ x > WER j=0
Where, Sk is the mapped value of the cumulative distribution function corresponding to the kth gray level, k is an integer in the range of [0, L-I], j is an integer in the range of [0, k],
L is the total gray level in the up-sampling image, G; is the frequency of the jth gray level, and
M and N are the length and width of the image respectively.
Meanwhile, when the kth gray level is the new gray level, the value of g(k) is the reciprocal of the frequency occupancy ratio of the new gray level in all new gray level, it should be noted that the frequency of the new gray level refers to the number of pixel points of the new gray level in the up-sampling image; thus, the mapped value of the cumulative distribution function of each gray level in the up-sampling image is obtained respectively.
Finally, after the mapped values of the cumulative distribution function of all gray levels are determined, the mapped values of the cumulative distribution function of all gray levels are normalized to the range [0, 255], so as to obtain the gray level after histogram equalization corresponding to each gray level in the up-sampling image.
In this way, the resolution of the image is improved, the enhancement of the image is realized, and less detailed information distributed in the image is retained as much as possible, and the detailed information refers to the tiny damage in the image or the edge information of the copper contacts.
Optionally, after obtaining the enhanced image after histogram equalization, edge detection may be carried out on the enhanced image, and the edge detection result may be taken as a new enhanced image, so as to reduce the amount of calculation in the subsequent template matching process.
The edge of an image is the most basic feature of the image, and the so-called edge refers to the discontinuity of local features of the image. Abrupt changes in information such as gray LU504273 or structure are called edges. For example, the abrupt change of gray level, the abrupt change of color and the abrupt change of texture structure. Edge is the end of one area, but also the beginning of another area, which may be used to segment an image. The edge of an image has two properties: direction and amplitude. Edge may usually be detected by a first derivative or a second derivative. The first derivative takes the maximum value as the position of the corresponding edge and the second derivative takes the zero crossing as the position of the corresponding edge.
The process of edge detection of the edge operator of the first derivative includes: the template serves as the kernel to do convolution and operation with each pixel point of an image, and then an appropriate threshold value is selected to extract the edge of the image.
The common edge operators of the first derivative are: Roberts operator, Prewitt operator,
Sobel operator, Canny operator, etc. The process of edge detection by the second derivative is based on the property of zero crossing of the second derivative, and the common edge operator of the second derivative is Laplacian operator.
In the embodiments of the application, in the process of edge detection, an operator used in edge detection is any one of Roberts operator, Prewitt operator, Sobel operator and Canny operator.
Optionally, for the enhanced image, there are both rich image details and clear contrast, at the same time, Canny operator has the advantage of double threshold value detection, so it can be preferred to use Canny operator for edge detection.
Furthermore, in S103, template matching is carried out on the enhanced image by using a template corresponding to a standard network interface, whether an abnormal network interface exists in the enhanced image or not is judged according to a matching result, and the abnormal network interface is located under the condition that the abnormal network interface exists.
Template matching is a process of traversing the enhanced image by using a template, in the process of traversing, if an area to be detected is an area where a normal network interface, namely, a network interface without defects is located, the similarity between the area to be detected and the template will be greater than a first preset threshold value; otherwise, if the similarity between the area to be detected and the template is not greater than the preset threshold value, the area to be detected may be an area where the network interface with defects is located, or the area to be detected may not be the area where the network interface is located, however, there is a certain similarity between the area where the network interface with defects is located and the template, when the similarity between the template and the LU504273 area to be detected is greater than a preset second threshold value, the area to be detected is determined as the area where the abnormal network interface is located, in this way, the possible abnormal network interface may be located while the integrity testing of the network interface is realized.
Specifically, the similarity in the embodiments of the application may be SSIM, PCCs, or other characteristic values used to calculate the similarity between images.
SSIM is a measure of similarity of two images, from the perspective of image composition, it defines structural information as an attribute that is independent of brightness and contrast and reflect the structure of objects in a scene, and models distortion as a combination of brightness, contrast and structure, a mean value is used as the estimate of brightness, standard deviation as the estimate of contrast, and covariance as the measure of
SSIM.
In statistics, PCCs is also known as PPMCC, which may be applied to calculate the similarity between two images.
In conclusion, the embodiments of the application provide a method for detecting integrity of a switch interface, in which graying and bilinear interpolation are carried out on the front image of the switch containing the network interface to obtain the up-sampling image, the gray level after mapping is determined respectively for the new gray level and the gray level except the new gray level in the up-sampling image to obtain the target image containing more details, and finally, integrity detection of the network interface in the switch is realized in a template matching mode.
All network interfaces contained in the target image may be tested simultaneously without carrying out visual inspection in sequence, so that the time required for inspection is shortened, meanwhile, the visual fatigue caused by manual visual inspection is effectively avoided, and therefore, the accuracy and the efficiency of the integrity inspection of the network interfaces of the switch are improved.
In the application, the terms such as "include", "comprise", "have", etc., are open terms, meaning "including but not limited to", and may be used interchangeably with it. The term "or" used here means the term "and/or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The term "such" used here means the term "such as but not limited to" and can be used interchangeably with it.
It should also be noted that in the method and system of the application, the components or steps can be broken down and/or recombined. These decomposition and/or recombination shall be deemed to be the equivalent solutions of the application. LU504273
The above-described embodiments are merely examples made for clarity of illustration and do not constitute limits on the scope of protection of the application. For those of ordinary skill in the art, other variations or modifications in different forms may be made on the basis of the above description, and it is unnecessary and impossible to exhaust all the embodiments here. All the same or similar designs of the application are within the scope of protection of the application.
Claims (9)
1. À method for detecting integrity of a switch interface, comprising: collecting a front image of a switch containing a network interface, carrving out graying to obtain a gray image, and carrving out up-sampling n the gray image through bilinear interpolation to obtain an up-sampling image; carrying out histogram equalization on the up-sampling image to obtain an enhanced image, determining a gray level after mapping for each new gray level and a gray level except the new gray level in the up-sampling image in the histogram equalization process, wherein the gray level after mapping of each new gray level is respectively determined according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image, and the new gray level is a gray level existing in the up-sampling image but not existing in the gray image; and carrying out template matching on the enhanced image by using a template corresponding to a standard network interface, and judging whether an abnormal network interface exists in the enhanced image or not according to a matching result.
2. The method for detecting integrity of a switch interface as claimed in claim 1, wherein that determining the gray level after mapping of each new gray level according to its frequency occupancy ratio in the up-sampling image and its frequency occupancy ratio to all new gray levels in the up-sampling image comprises: determining a mapped value of a cumulative distribution function of each new gray level according to the frequency occupancy ratio of each new gray level in the up-sampling image and the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, wherein the larger the frequency occupancy ratio of each new gray level to all new gray levels in the up-sampling image, the smaller the mapped value of a cumulative distribution function of each new gray level; and determining the gray level after mapping of each new gray level according to the mapped value of a cumulative distribution function of each new gray level.
3. The method for detecting integrity of a switch interface as claimed in claim 1, wherein that carrying out template matching on the enhanced image by using a template corresponding to a standard network interface, and judging whether an abnormal network interface exists in the enhanced image or not according to a matching result comprises: acquiring the similarity between the template corresponding to the standard network interface and an area to be detected in the enhanced image, and the area to be detected is an area in the enhanced image, which is as large as the template;
under the condition that the similarity is greater than a preset first threshold value, LU504273 judging that the area to be detected is the area where a normal network interface is located; and under the condition that the similarity is not greater than the preset first threshold value, judging whether the similarity is greater than a preset second threshold value or not, if the judgment result is yes, judging the area to be detected as the area where an abnormal interface is located, wherein the preset second threshold value is smaller than the preset first threshold value.
4. The method for detecting integrity of a switch interface as claimed in claim 3, wherein the similarity refers to Structural Similarity Index Measure (SSIM).
5. The method for detecting integrity of a switch interface as claimed in claim 3, wherein the similarity refers to Pearson Correlation Coefficient (PCCs).
6. The method for detecting integrity of a switch interface as claimed in claim 1, before collecting a front image of a switch containing a network interface, further comprising: disposing parallel light to illuminate the switch containing the network interface.
7. The method for detecting integrity of a switch interface as claimed in claim 1, after carrying out histogram equalization on the up-sampling image to obtain an enhanced image, further comprising: carrying out edge detection on the enhanced image, and taking an edge detection result as a new enhanced image.
8. The method for detecting integrity of a switch interface as claimed in claim 7, wherein an operator used in edge detection is any one of Roberts operator, Prewitt operator, Sobel operator and Canny operator.
9. The method for detecting integrity of a switch interface as claimed in claim 1, further comprising: locating an abnormal network interface under the condition that it exists.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211190970.3A CN115471486A (en) | 2022-09-28 | 2022-09-28 | Switch interface integrity detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU504273B1 true LU504273B1 (en) | 2023-07-31 |
Family
ID=84334398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU504273A LU504273B1 (en) | 2022-09-28 | 2023-04-05 | Method for Detecting Integrity of Switch Interface |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN115471486A (en) |
| LU (1) | LU504273B1 (en) |
| WO (1) | WO2023126030A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471486A (en) * | 2022-09-28 | 2022-12-13 | 探长信息技术(苏州)有限公司 | Switch interface integrity detection method |
| CN116681696B (en) * | 2023-07-27 | 2023-10-20 | 东莞雅达高精密塑胶模具有限公司 | Mold quality monitoring method for automatic production equipment |
| CN116703912B (en) * | 2023-08-07 | 2023-11-24 | 深圳市鑫赛科科技发展有限公司 | Mini-host network port integrity visual detection method |
| CN117078679B (en) * | 2023-10-16 | 2023-12-15 | 东莞百舜机器人技术有限公司 | Automatic assembly line production detection method for cooling fan based on machine vision |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5481619A (en) * | 1992-07-07 | 1996-01-02 | Schwartz; Nira | Inspection method using templates images, unique histogram analysis, and multiple gray levels correlated to addresses of template images |
| US20100278423A1 (en) * | 2009-04-30 | 2010-11-04 | Yuji Itoh | Methods and systems for contrast enhancement |
| CN113034452B (en) * | 2021-03-15 | 2022-09-27 | 南京理工大学 | Weldment contour detection method |
| CN114494256B (en) * | 2022-04-14 | 2022-06-14 | 武汉金龙电线电缆有限公司 | Electric wire production defect detection method based on image processing |
| CN115471486A (en) * | 2022-09-28 | 2022-12-13 | 探长信息技术(苏州)有限公司 | Switch interface integrity detection method |
-
2022
- 2022-09-28 CN CN202211190970.3A patent/CN115471486A/en not_active Withdrawn
-
2023
- 2023-04-05 LU LU504273A patent/LU504273B1/en active IP Right Grant
- 2023-04-05 WO PCT/CN2023/086364 patent/WO2023126030A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| CN115471486A (en) | 2022-12-13 |
| WO2023126030A1 (en) | 2023-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| LU504273B1 (en) | Method for Detecting Integrity of Switch Interface | |
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| Lin et al. | Vehicle speed detection from a single motion blurred image | |
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| US20080075385A1 (en) | Detection and Correction of Flash Artifacts from Airborne Particulates | |
| US10467731B2 (en) | Automatic defective digital motion picture pixel detection | |
| CN111612725B (en) | Image fusion method based on contrast enhancement of visible light image | |
| CN109712127B (en) | Power transmission line fault detection method for machine inspection video stream | |
| CN111031311B (en) | Imaging quality detection method and device, electronic equipment and readable storage medium | |
| CN109859160A (en) | Almag internal defect in cast image-recognizing method based on machine vision | |
| CN107515227A (en) | Based on the lossless method for compressing image of defect and defects of display panel detecting system | |
| CN114972575A (en) | Linear fitting algorithm based on contour edge | |
| CN115494193B (en) | Machine vision-based flame transverse propagation detection method and system for single body combustion test | |
| CN110007493A (en) | Broken bright spot detection method in liquid crystal display | |
| CN112488998A (en) | Apple stem and calyx detection method based on stripe projection | |
| Chen et al. | Image registration between visible and infrared images for electrical equipment inspection robots based on quadrilateral features | |
| CN117274113B (en) | Broken silicon wafer cleaning effect visual detection method based on image enhancement | |
| US20120039531A1 (en) | Method, system and computer program product for object color correction | |
| JP3324699B2 (en) | Method and apparatus for measuring fiber diameter distribution | |
| KR20050022320A (en) | Defect inspecting method and apparatus | |
| CN112833821A (en) | Differential geometric three-dimensional micro-vision detection system and method for high-density IC welding spots | |
| CN116758425A (en) | Automatic acceptance checking method and device for large-base photovoltaic power station | |
| CN112837285B (en) | Edge detection method and device for panel image | |
| CN111415365A (en) | Image detection method and device | |
| CN114125435A (en) | Intelligent image defect detection method for network camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20230731 |