CN116721102A - Quick traceability method for quality of explosive bead products - Google Patents
Quick traceability method for quality of explosive bead products Download PDFInfo
- Publication number
- CN116721102A CN116721102A CN202310999986.7A CN202310999986A CN116721102A CN 116721102 A CN116721102 A CN 116721102A CN 202310999986 A CN202310999986 A CN 202310999986A CN 116721102 A CN116721102 A CN 116721102A
- Authority
- CN
- China
- Prior art keywords
- bead
- explosion
- quality
- edge
- explosive
- 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.)
- Granted
Links
- 239000011324 bead Substances 0.000 title claims abstract description 322
- 239000002360 explosive Substances 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004880 explosion Methods 0.000 claims abstract description 148
- 238000004891 communication Methods 0.000 claims abstract description 76
- 230000009172 bursting Effects 0.000 claims abstract description 40
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000009826 distribution Methods 0.000 claims abstract description 10
- 230000007547 defect Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 230000002950 deficient Effects 0.000 claims description 6
- 238000005422 blasting Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 239000003086 colorant Substances 0.000 description 5
- 235000019640 taste Nutrition 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000005336 cracking Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 108010010803 Gelatin Proteins 0.000 description 3
- 229920000159 gelatin Polymers 0.000 description 3
- 239000008273 gelatin Substances 0.000 description 3
- 235000019322 gelatine Nutrition 0.000 description 3
- 235000011852 gelatine desserts Nutrition 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 235000014653 Carica parviflora Nutrition 0.000 description 2
- 241000243321 Cnidaria Species 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 239000000945 filler Substances 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 241000220317 Rosa Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000007788 liquid Substances 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
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The application belongs to the technical field of image processing, and provides a quick traceability method for the quality of a bead explosion product, which comprises the following steps: acquiring and processing a bursting bead image to obtain a bursting bead edge contour and a bursting bead communication area; analyzing the distribution characteristics of pixel points and edge angle points on the edge profile of the explosion bead to obtain the edge excellent degree of the explosion bead communication area; analyzing the gray value change condition of the pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication area; analyzing the change condition of the color of the explosive beads in the explosive bead RGB image to obtain the distance value of the color of the explosive beads; obtaining the quality of the explosion beads based on the edge quality, the gray level uniformity and the explosion bead color distance value; and according to the quality excellence of the explosion beads, combining a quality problem data table, and rapidly tracing the quality of the explosion bead products. The application adopts the technical method of image processing, can carry out batch and quick quality tracing, has good effect and high efficiency, does not need repeated debugging, and is convenient to use.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a quick tracing method for the quality of a bead explosion product.
Background
The bursting bead product is a soft candy food which is made of gelatin as a main component, and when the bursting beads are chewed in the mouth, the bursting beads are extruded by teeth and can instantaneously release a large amount of liquid or granular internal filling materials, so that the bursting feeling in the mouth is generated; different types of the explosion beads have different tastes due to different fillers.
This class of confectionery products has been popular in the marketplace because it has heretofore been less and at the same time provides a very interesting mouthfeel and a different experience.
At present, the automation demand of food processing production is higher and higher, and the quality control of the product is more important. The quality problem of the pop-up product is usually manifested in appearance, such as irregular shape, cracking, bubbles in the pop-up product, etc.; in the prior art, when the proportion of defective products is obviously increased, the fault position can be found only by maintenance personnel in a one-to-one maintenance or even shutdown maintenance mode, and the production efficiency of the bead explosion product is obviously reduced by the method.
Therefore, a quick tracing method for quality of the explosive bead product is needed, so that links causing quality problems of the explosive bead product can be quickly found.
Disclosure of Invention
In order to solve the technical problems, the application provides a quick tracing method for the quality of a bead explosion product.
The provided quick traceability method for the quality of the explosion bead product comprises the following steps:
collecting an explosive bead RGB image, and preprocessing the explosive bead RGB image to obtain an explosive bead gray level image;
performing edge contour detection and processing on the burst bead gray level image by adopting a Canny operator to obtain a burst bead edge contour and a burst bead communication area in the burst bead gray level image;
analyzing the distribution characteristics of pixel points and edge angle points on the burst edge contour to obtain the edge excellence of the burst communication area;
analyzing the gray value change condition of pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication area;
analyzing the change condition of the color of the explosive beads in the explosive bead RGB image to obtain the distance value of the color of the explosive beads;
based on the edge quality, the gray level identity and the bead bursting color distance value, the bead bursting quality is obtained;
and according to the quality excellence of the explosion beads, combining a quality problem data table, and rapidly tracing the quality of the explosion bead products.
In some embodiments of the present application, analyzing the distribution characteristics of the pixel points and the edge angle points on the bead explosion edge contour to obtain the edge quality of the bead explosion communication area includes:
performing Hough circle transformation on the bead explosion edge contour to obtain a Hough circle;
counting the number of pixels overlapped with the corresponding Hough circle on the burst edge contour;
obtaining a circular fitting factor of the explosion communication area according to the number of the coincident pixel points and the total number of the pixel points on the Hough circle;
according to the circular fitting factor, combining the difference value between the Euclidean distance between the pixel point on the explosion bead edge contour and the centroid point of the corresponding explosion bead communication area and the radius of the Hough circle to obtain the roundness of the explosion bead communication area;
performing corner detection on the bead explosion edge profile to obtain an edge corner point on the bead explosion edge profile;
clustering the edge corner points to obtain clustering clusters;
counting the number of edge corner points outside the cluster;
and according to the roundness, combining the number of the clusters and the number of edge corner points outside the clusters to obtain the edge excellent degree of the explosion communication area.
In some embodiments of the present application, the circle fit factor is a ratio of the number of overlapping pixels to the total number of pixels on the hough circle.
In some embodiments of the present application, the roundness-like calculation method is as follows:
；
in the method, in the process of the application,indicating the roundness-like of the bead-blasted communication region,a circular fitting factor representing the bead communication region,representing the Euclidean distance between the pixel point on the burst edge contour and the centroid point of the corresponding burst communication area,the radius of the hough circle is indicated,representing the number of all pixel points on the outline of the burst edge,a constant is used to avoid zero denominator,expressed in terms ofAs an exponential function of the base, to similar roundnessNormalized, normalized roundness is recorded as。
In some embodiments of the application, the edge goodness is the product of the normalized circularity-like degree and the inverse cluster parameter, wherein the inverse cluster parameter is the inverse of the product of the number of clusters plus one and the number of edge corner points outside the clusters plus one.
In some embodiments of the present application, the gray level is represented as the inverse of the sum of gray value differences, where the sum of gray value differences is represented as the sum of gray values of all pixels of the bead-blasted communication area and the average of gray values of all pixels of the bead-blasted communication area, respectively, then squared, then summing the squares of all the differences, and then adding the adjustment parameter.
In some embodiments of the present application, analyzing the variation of the color of the pop in the RGB image of the pop to obtain a distance value of the color of the pop, including:
analyzing a bursting bead RGB image without any defect bursting beads, obtaining a bursting bead standard color, and converting the bursting bead standard color into an HSV color space to obtain a standard color HSV value;
converting the bead explosion RGB image into an HSV color space to obtain an HSV value of each pixel point;
according to the HSV value of each pixel point, an HSV average value of the bead explosion RGB image is obtained;
and obtaining the explosion bead color distance value based on the standard color HSV value and the HSV average value.
In some embodiments of the application, the pop color distance value is a euclidean distance value of a standard color HSV value and an HSV mean of the pop RGB image.
In some embodiments of the application, the bead burst quality merit is the product of the edge merit and the gray scale, and then is a ratio of one to the bead burst color distance value.
In some embodiments of the present application, the quality problem data table obtaining method includes: and determining the reason by manually detecting the defective product, forming a corresponding relation between the determined defect reason and the quality excellence of the explosion beads, and constructing a quality problem data table.
The embodiment of the application provides a quick traceability method for the quality of the explosive bead product, which has the following beneficial effects:
according to the application, the explosive bead RGB image is collected, and the explosive bead RGB image is preprocessed to obtain the explosive bead gray level image; performing edge contour detection and processing on the burst bead gray level image by adopting a Canny operator to obtain a burst bead edge contour and a burst bead communication area in the burst bead gray level image; analyzing the distribution characteristics of pixel points and edge angle points on the burst edge contour to obtain the edge excellence of the burst communication area; analyzing the gray value change condition of pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication area; analyzing the change condition of the color of the explosive beads in the explosive bead RGB image to obtain the distance value of the color of the explosive beads; based on the edge quality, the gray level identity and the bead bursting color distance value, the bead bursting quality is obtained; and according to the quality excellence of the explosion beads, combining a quality problem data table, and rapidly tracing the quality of the explosion bead products. According to the application, the possible quality problems of the explosive beads are analyzed, the comprehensive quality evaluation is carried out on the explosive beads to be detected according to the edge change on the appearance of the explosive beads, the gray level change in the interior and the distance between the overall color and the standard color, and then the quality of the explosive bead products can be rapidly traced by combining the quality problem data table, so that tracing is rapid and accurate.
The application adopts the technical method of image processing, has simpler calculation, good effect and high efficiency when the mass and rapid quality tracing is needed for the explosive bead products to be detected, does not need repeated debugging, and is convenient to use.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a basic flow diagram of a quick traceability method for quality of a bead explosion product according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a basic method for obtaining edge quality of a bead explosion communication area according to an embodiment of the present application;
fig. 3 is a basic flow chart of a method for obtaining a distance value of a bead burst color according to an embodiment of the present application.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The following describes in detail a quick tracing method for quality of a bead explosion product provided in this embodiment with reference to the accompanying drawings.
Fig. 1 is a basic flow chart of a quick traceability method for quality of a bead explosion product, which is provided by the embodiment of the application, and as shown in fig. 1, the method specifically includes the following steps:
s100: and acquiring an explosive bead RGB image, and preprocessing the explosive bead RGB image to obtain an explosive bead gray level image.
The quality of each bead explosion product is detected, and an image of the bead explosion product needs to be acquired first. As the explosive beads are crystal clear and have stronger light transmission and reflection, the application adopts the form of LED lamp backlight to reduce reflection, and adopts the CMOS camera to shoot the explosive beads to be detected in overlooking angle, thus ensuring that all the explosive beads to be detected are shot. The obtained burst bead images are all RGB images, and the burst bead RGB images are converted into burst bead gray images. And then median filtering processing is carried out on the burst gray level image to prevent noise in the image from influencing subsequent processing of the image, and meanwhile, sharpening operation is carried out on the burst gray level image by using a Laplacian operator, so that the edge contour of the image is clearer, and subsequent operation is conveniently carried out.
S200: and detecting and processing the edge contour of the bursting bead gray level image by adopting a Canny operator to obtain the bursting bead edge contour and the bursting bead communication area in the bursting bead gray level image.
The explosive bead product mainly comprises gelatin and transparent internal filler, so that on the image of the explosive bead product without defects, the explosive bead is a crystal clear, transparent, large and full sphere. The color of the pop-up product is related to the taste of the pop-up product, the pop-up products with different tastes have different colors, and the color of the pop-up product is light pink or light coral color, which is usually quite different from the background color of an image, and a certain interval exists between each pop-up product and is not connected with each other. Therefore, for the explosive bead gray level image sharpened by the Laplacian operator, the Canny operator is adopted for edge detection to obtain the edge of each explosive bead, at the moment, the 8-direction chain code method is adopted to determine the communication area where the explosive bead is located, each explosive bead corresponds to one explosive bead communication area, each explosive bead communication area is provided with an edge contour, and the contour is the explosive bead edge contour.
S300: and analyzing the distribution characteristics of the pixel points and the edge angle points on the edge contour of the explosion bead to obtain the edge excellent degree of the explosion bead communication area.
Each complete bead edge profile corresponds to one bead product. The quality is better, the appearance is comparatively complete explodes the pearl, and the grain is big full, and is a comparatively regular sphericity, adopts overlook the angle to shoot, obtains single explodes pearl gray scale image and is a very regular circular, explodes the pearl edge profile and is a circular promptly. Once the pop-up product has some problems in the production process, the appearance of the pop-up product is changed, for example, the filling in a certain pop-up product is less likely to cause the pop-up to be shrunken, and the gelatin component is not well configured to cause the pop-up to be broken, etc. The edge profile of the normal and large full pop bead product is regular round, and the pop bead product has the defects of shriveling, cracking and the like, so that the appearance of the pop bead product is deformed, the profile is not regular round any more, and the edge profile of the pop bead is obviously deformed and cracked. In addition, the normal bursting bead images are uniform in color, the difference among the colors of the whole bursting beads is very small, the bursting bead products are shriveled, broken and the like, more edge corner points can appear at the edge outline part of the bursting beads, and most of the edge corner points are closer in distance and denser.
In conclusion, the distribution of the pixel points and the edge corner points on the edge profile of the bursting bead can be changed when the bursting bead product is deformed such as shrunken, broken and the like, so that the quality of the bursting bead product can be judged by analyzing the distribution characteristics of the pixel points and the edge corner points on the edge profile of the bursting bead.
Fig. 2 is a basic flow chart of a method for obtaining edge quality of a bead-blasting communication area according to an embodiment of the present application, as shown in fig. 2, in some embodiments of the present application, distribution characteristics of pixel points and edge corner points on a bead-blasting edge contour are analyzed to obtain edge quality of the bead-blasting communication area, including steps S301 to S308.
S301: and carrying out Hough circle transformation on the edge contours of the explosion beads to obtain Hough circles.
In order to calculate the roundness of the bursting beads, the application carries out Hough circle transformation on the edge contour of each bursting bead in the bursting bead gray level image, and the number of all pixel points on a certain bursting bead edge contour is recorded as1, the total number of pixel points on the Hough circle corresponding to the burst edge outline is recorded asThe radius of the circle isIf the burst edge contour does not have a corresponding Hough circle, thenFor a larger value, the application is set to 100000,and similarly set to 1000.
S302: and counting the number of the pixels overlapped with the corresponding Hough circle on the edge outline of the explosion bead.
The normal burst edge contour is more regular and presents a circle, so that partial pixel points exist, namely the pixel points on the burst edge contour, are also the pixel points on the circle after Hough circle transformation, the number of the pixel points which are overlapped with the circle after Hough circle transformation on the burst edge contour is counted, and the number of the overlapped pixel points is recorded as follows。
S303: and obtaining a circular fitting factor of the explosion communication area according to the number of the coincident pixel points and the total number of the pixel points on the Hough circle.
The closer the bead burst edge contour is to a circle, the more the pixel points on the Hough circle obtained by carrying out Hough circle transformation on the bead burst edge contour are overlapped with the pixel points on the bead burst edge contour, namelyThe larger the round fitting factor of the explosion communication area is, the round fitting factor of the explosion communication area can be obtainedCircle fitting factorFor the number of coincident pixel pointsTotal number of pixels on Hough circleIs a ratio of (2). Namely:
；
in the method, in the process of the application,a circular fitting factor representing the bead communication region,representing the number of pixels on the contour of the burst edge, which coincides with the corresponding Hough circle,representing the total number of pixels on the hough circle.
Wherein, the number of the overlapped pixel pointsThe more the explosion bead edge outline is similar to the corresponding Hough circle, the more the coincident pixel points occupy the proportion of the Hough circle pointsThe larger the bead edge profile is, the more the bead edge profile can be fitted to a circle, the circle fitting factorThe larger the bead edge profile, the closer to circular.
S304: and according to the circular fitting factor, combining the difference value between the Euclidean distance between the pixel point on the explosion bead edge contour and the centroid point of the corresponding explosion bead communication area and the radius of the Hough circle to obtain the roundness-like of the explosion bead communication area.
In the bead edge profiles, each bead edge profile corresponds to a centroidAt the same time, the radius of the Hough circle corresponding to the edge contour of the burst bead isEach pixel point and corresponding mass center on the edge contour of the explosion beadIs recorded as the Euclidean distance of (2)Pixel point and mass center on each burst edge contourThe closer the Euclidean distance of (a) is to the radius of the Hough circleThe closer the bead edge profile is to a circle, the less the bead is defective in its appearance shape, and the better the quality of the bead. Therefore, according to the circular fitting factor, combining the difference value of the Euclidean distance between the pixel point on the explosion bead edge contour and the centroid point of the corresponding explosion bead communication area and the radius of the Hough circle to obtain the roundness of the explosion bead communication areaRoundness-likeThe calculation method of (1) is as follows:
；
in the method, in the process of the application,indicating the roundness-like of the bead-blasted communication region,a circular fitting factor representing the bead communication region,representing the Euclidean distance between the pixel point on the burst edge contour and the centroid point of the corresponding burst communication area,the radius of the hough circle is indicated,representing the number of all pixel points on the outline of the burst edge,a constant is used to avoid zero denominator,the checked value may be taken to be 0.001,expressed in terms ofAs an exponential function of the base, to similar roundnessNormalized, normalized roundness is recorded as。
If the explosion bead is a normal explosion bead, the explosion bead is in a regular spherical shape, and the centroid of the corresponding explosion bead edge outline is the center of the explosion bead Hough circle. The closer the Euclidean distance from the pixel point on the edge contour of each explosion bead to the centroid of each explosion bead is to the radius of the Hough circleI.e.The smaller the bead edge profile, the closer to a circle, roundnessThe larger; at the same time, the more the number of all pixel points on the edge contour of the burst bead is, namelyThe bigger the roundnessThe larger; circle fitting factorThe larger the bead edge profile, the closer to a circle, roundnessThe larger. Roundness of the bead-exploded regionNormalizing to obtain a value range of (0, 1)]Normalized roundnessIs marked as。
S305: and (3) carrying out corner detection on the edge profile of the explosion bead to obtain an edge corner point on the edge profile of the explosion bead.
In the burst gray level image, the color of the normal burst image is uniform and consistent, and the difference between the colors of the whole burst is very small. If the detonating bead product has the defects of shrinkage, breakage and the like, the detonating bead edge outline part of the detonating bead can be deformed and broken more, more edge corner points exist, and most of the edge corner points are closer in distance and denser. Therefore, harris edge corner detection is carried out on the bead edge contour, and a plurality of edge corner points on the bead edge contour are obtained.
S306: and clustering the edge corner points to obtain a cluster.
DBSCAN clustering is carried out on edge corner points, and neighborhood radius in DBSCAN clustering algorithm is carried outSetting the empirical value to be 4, setting the minimum neighborhood point number MinPts to be 6, and finally outputting to obtain DBSCAN clusters so as to divide edge corner points on the edge contour of the explosive beads intoAnd clustering clusters.
S307: and counting the number of edge corner points outside the cluster.
Based on the cluster obtained in step S306, the number of edge corner points outside the cluster is counted, i.e. the statistics is no longer performedThe number of edge corner points in each cluster is recorded as。
S308: and according to the roundness, combining the number of the clusters and the number of edge corner points outside the clusters to obtain the edge excellent degree of the explosion bead communication area.
The normal explosive bead edge profile is a very regular circle, each pixel point is smooth in transition and does not generate more severe change, edge corner points are few, but once the explosive bead has the defects of being shrunken, broken and the like, the explosive bead edge profile is deformed and broken, more edge corner points appear, and the edge corner points are more concentrated in a deformation area, so that the explosive bead edge profile can obtain more edge corner points and generally corresponds to a clustered cluster after clustering. Therefore, the edge quality of the explosion communication area can be obtained by combining the number of clusters and the number of edge corner points outside the clusters according to the roundness. Edge dominance degreeTo normalize the roundnessProduct of cluster parameter reciprocal, wherein cluster parameter reciprocal is number of clustersAdding one to the number of edge corner points outside the clusterThe inverse of the product of plus one, namely:
；
in the method, in the process of the application,represents the edge excellent degree of the explosion bead communication area,indicating the communication area of the explosion beadsThe roundness-like degree is normalized and the degree of freedom,representing the number of clusters obtained by DBSCAN clustering,representing the number of edge corner points outside the cluster.
Wherein the closer the bead edge profile is to a circle, the normalized roundness of the bead-blasted regionThe larger the explosion bead is, the more normal the explosion bead is, the larger and full the explosion bead is, the better the explosion bead quality is judged from the explosion bead edge outline, and the edge excellent degree corresponding to the explosion bead isThe larger; clustering number of clustered edge corner points of explosive beadsThe more the edge deformation and the more the fracture parts are indicated, the more the non-clustered edge angular points exist in the explosive beads, the more severe and unsmooth changes of other edges of the explosive beads are indicated, the coarser the edge profile of the explosive beads is, the worse the quality of the explosive beads is judged from the edge profile of the explosive beads, and the edge quality degree corresponding to the explosive beads is determinedThe smaller.
S400: and analyzing the gray value change condition of the pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication area.
For the inner part of the explosive bead, the color is generally consistent and transparent, but when the explosive bead product is manufactured, air can remain in the explosive bead, and the residual air can form bubbles, and if the tightness of the explosive bead is low, air can enter the explosive bead to form bubbles. In addition, due to the action of external force, the defects such as dry cracking and cracking can be caused at the non-edge part of the explosion bead. Whether the bubble or the crack belongs to the quality problem of the explosive bead product, so that the detection of the quality problem inside the explosive bead is extremely important.
Normal bursting beads are transparent, the colors are consistent, the gray level change is small, and the gray level value is small; and once the explosion beads have abnormal defects such as bubbles, cracks and the like, the gray level change of the defective parts is larger, and the gray level value is larger. Based on the analysis, the application can analyze the gray value of each pixel point of the burst bead, and the gray value of the normal burst bead part and the gray value of the abnormal defect part have larger difference. Calculating the gray average value of the burst connected region, and recording asBecause the normal part in the burst gray level image occupies a larger proportion of the whole burst, the burst gray level image is provided with a larger proportion of the whole burstThe gray value of the glass is very close to that of normal bursting beads, and the glass has larger difference with that of defects such as bubbles, cracks and the like.
Analyzing the gray value change condition of the pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication areaGray level is the same degreeThe gray value difference sum is expressed as the reciprocal of the gray value difference sum, wherein the gray value difference sum is expressed as the difference between the gray values of all the pixel points of the explosion communication area and the gray value mean value of all the pixel points of the explosion communication area, and then the squares is carried out, and then the squares of all the difference values are summed, and then the adjusting parameters are added, namely:
；
in the method, in the process of the application,the gray scale of the explosion bead communication area is identical,a first step of indicating a bead-explosion communication areaThe number of pixels in a pixel is one,the gray value average value of all pixel points in the explosion bead communication area is represented,the number of the pixel points of the explosion bead communication area is represented,the presentation constant is used to avoid zero denominator,the checked value can be taken to be 0.001.
Wherein, the firstThe larger the difference between the gray value of each pixel point and the gray average value of the explosion bead communication area is, the more likely the pixel point is an abnormal defect point, the larger the gray difference in the comprehensive explosion bead communication area is, the more suspected abnormal defect points in the explosion bead communication area are, the more likely the explosion bead product quality is problematic, the larger the gray value difference is, and the explosion bead gray identity isThe smaller.
S500: and analyzing the change condition of the color of the explosive beads in the explosive bead RGB image to obtain the distance value of the color of the explosive beads.
In the burst gray level image, each burst has a corresponding burst communication area, and the burst communication area corresponds to an RGB area. The color of the pop-up product is related to the taste of the product, and products with different tastes have different colors, and the application takes 'encounter rose' in the product as an example, and the color presents light pink or light coral color.
Fig. 3 is a basic flow chart of a method for obtaining a bead burst color distance value according to an embodiment of the present application, as shown in fig. 3, the method includes steps S501 to S504, where the bead burst color distance value is obtained by analyzing the variation of the bead burst color in an RGB image of the bead burst.
S501: analyzing the burst bead RGB image without any defect burst bead, obtaining the burst bead standard color, and converting the burst bead standard color into an HSV color space to obtain a standard color HSV value.
The normal explosive bead RGB image without any defect is obtained, the environment is ensured to be the same as the explosive bead environment to be detected, so that the standard color of the explosive bead is obtained, and is converted into an HSV color space, wherein the standard color is%,,）。
S502: and converting the burst RGB image into an HSV color space to obtain an HSV value of each pixel point.
The bead explosion area to be detected is also converted from the bead explosion RGB image into an HSV color space to obtain an HSV value of each pixel point, and the third step is thatThe pixel points of each explosion bead are marked as%,,）。
S503: and obtaining the HSV average value of the bead explosion RGB image according to the HSV value of each pixel point.
Obtaining HSV average value of the bead explosion RGB image according to the HSV value of each pixel point, and marking as @，，）。
S504: and obtaining the burst color distance value based on the standard color HSV value and the HSV average value.
Based on the standard color HSV value and the HSV average value, the burst color distance value is the Euclidean distance value of the standard color HSV value and the HSV average value of the burst RGB image, namely:
；
in the method, in the process of the application,the distance value of the color of the explosion beads is shown, and the HSV value of the standard color is%,,) HSV average value of the bead explosion RGB image is%，，）。
The smaller the difference between the color of the explosive bead to be detected and the standard color of the normal explosive bead, namely the closer the color of the explosive bead to be detected is to the standard color, the color distanceThe smaller the size, the more normal the burst bead to be detected, and no quality problem.
S600: and obtaining the bead explosion quality degree based on the edge degree of excellence, the gray level degree of identity and the bead explosion color distance value.
Based on the edge quality, the gray level uniformity and the burst color distance value, the burst quality is obtained, and is the product of the edge quality and the gray level uniformity, and then the ratio of the burst quality to the burst color distance value is one, namely:
；
in the method, in the process of the application,the quality of the explosion beads is expressed,represents the edge excellent degree of the explosion bead communication area,the gray scale of the explosion bead communication area is identical,indicating the distance value of the color of the explosion beads.
Wherein, the closer the contour of the edge of the explosion bead is to the round shape, the less the possibility of deformation and fracture of the edge of the explosion bead, the better the quality of the explosion bead is judged from the edge of the explosion bead, and the quality of the explosion bead is excellentThe larger; for the gray level variation of the interior of each explosion bead, the explosion bead gray level identityThe larger the explosion bead is, the lower the possibility of bubbles and cracks appear in the explosion bead, the better the quality of the explosion bead is, and the excellent quality of the explosion bead isThe larger; the color of the burst bead is closer to the standard color of the normal burst bead, and the color distance is as followsThe smaller the size, the better the quality of the explosion bead, and the explosionBead qualityThe larger.
S700: and according to the quality excellence of the explosion beads, combining a quality problem data table, and rapidly tracing the quality of the explosion bead products.
The quality of the explosion beads in each explosion bead communication area to be detected can be obtained by the step S600. First, the factory can determine the reason by manually detecting the defective products and has excellent quality with the explosion beadsAnd forming a corresponding relation, and constructing a quality problem data table. And then through a factory-built quality problem data table in which each of the explosion beads has a quality degree of excellenceAnd the interval corresponds to the reason that the quality of one product appears, so that the quick tracing of the quality of the bead explosion product can be performed. Such as the quality of the bursting beadsSearching the quality problem data table for 0.615, wherein the value corresponds to the quality degree of the explosion beads in the quality problem data tableThe interval (0.600,0.700) corresponds to the quality problem that the explosive beads are too little in the internal filling during production, so that the explosive beads are shrunken. The specific case implementers can be adjusted according to the specific case.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
It should be noted that unless otherwise specified and limited, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a circuit structure, 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 article or apparatus. Without further limitation, the statement "comprises one … …" does not exclude that an additional identical element is present in an article or device that comprises the element. In addition, the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The quick traceability method for the quality of the explosion bead product is characterized by comprising the following steps of:
collecting an explosive bead RGB image, and preprocessing the explosive bead RGB image to obtain an explosive bead gray level image;
performing edge contour detection and processing on the burst bead gray level image by adopting a Canny operator to obtain a burst bead edge contour and a burst bead communication area in the burst bead gray level image;
analyzing the distribution characteristics of pixel points and edge angle points on the burst edge contour to obtain the edge excellence of the burst communication area;
analyzing the gray value change condition of pixel points in the explosion bead communication area to obtain the gray level uniformity of the explosion bead communication area;
analyzing the change condition of the color of the explosive beads in the explosive bead RGB image to obtain the distance value of the color of the explosive beads;
based on the edge quality, the gray level identity and the bead bursting color distance value, the bead bursting quality is obtained;
and according to the quality excellence of the explosion beads, combining a quality problem data table, and rapidly tracing the quality of the explosion bead products.
2. The quick traceability method for the quality of the explosive bead product according to claim 1, wherein analyzing the distribution characteristics of the pixel points and the edge angle points on the explosive bead edge contour to obtain the edge quality of the explosive bead communication area comprises the following steps:
performing Hough circle transformation on the bead explosion edge contour to obtain a Hough circle;
counting the number of pixels overlapped with the corresponding Hough circle on the burst edge contour;
obtaining a circular fitting factor of the explosion communication area according to the number of the coincident pixel points and the total number of the pixel points on the Hough circle;
according to the circular fitting factor, combining the difference value between the Euclidean distance between the pixel point on the explosion bead edge contour and the centroid point of the corresponding explosion bead communication area and the radius of the Hough circle to obtain the roundness of the explosion bead communication area;
performing corner detection on the bead explosion edge profile to obtain an edge corner point on the bead explosion edge profile;
clustering the edge corner points to obtain clustering clusters;
counting the number of edge corner points outside the cluster;
and according to the roundness, combining the number of the clusters and the number of edge corner points outside the clusters to obtain the edge excellent degree of the explosion communication area.
3. The quick traceability method of bead blasting product quality according to claim 2, wherein the circular fitting factor is a ratio of the number of the coincident pixels to the total number of the pixels on the hough circle.
4. The quick traceability method of the quality of the explosion bead product according to claim 2, wherein the roundness-like calculation method is as follows:
；
in the method, in the process of the application,indicative of the roundness of the bead-like communication region, +.>A circular fitting factor representing the bead-blasted connected region, < >>Representing the Euclidean distance between the pixel point on the burst edge contour and the centroid point of the corresponding burst communication area, < >>Representing the radius of a hough circle, +.>Indicating the number of all pixel points on the edge outline of the explosion bead, < +.>Constant is used to avoid zero denominator, < >>Expressed as +.>An exponential function as a base, for a roundness +.>Normalizing, and recording the normalized roundness as +.>。
5. The quick traceability method of bead blasting product quality according to claim 4, wherein the edge-like degree is a product of the normalized roundness and a reciprocal of a cluster parameter, wherein the reciprocal of the cluster parameter is a reciprocal of a product of one more than the number of clusters and one more than the number of edge points outside the clusters.
6. The quick tracing method for the quality of the explosive bead product according to claim 1, wherein the gray level is represented as the inverse of a gray level difference sum, wherein the gray level difference sum is represented as the difference between gray values of all pixel points of the explosive bead communication area and gray value average values of all pixel points of the explosive bead communication area respectively, and then the sum of squares of all the differences is carried out, and then the adjusting parameter is added.
7. The quick traceability method of quality of a pop-up product according to claim 1, wherein analyzing the change condition of the pop-up color in the pop-up RGB image to obtain the pop-up color distance value comprises:
analyzing a bursting bead RGB image without any defect bursting beads, obtaining a bursting bead standard color, and converting the bursting bead standard color into an HSV color space to obtain a standard color HSV value;
converting the bead explosion RGB image into an HSV color space to obtain an HSV value of each pixel point;
according to the HSV value of each pixel point, an HSV average value of the bead explosion RGB image is obtained;
and obtaining the explosion bead color distance value based on the standard color HSV value and the HSV average value.
8. The quick tracing method for the quality of the pop-up product according to claim 7, wherein the pop-up color distance value is a Euclidean distance value of an HSV value of a standard color and an HSV average value of an RGB image of the pop-up.
9. The quick traceability method for the quality of the explosion bead product according to claim 1, wherein the explosion bead quality excellence is a product of the edge excellence and the gray level, and then a ratio of one to the explosion bead color distance value is added.
10. The quick quality tracing method for the explosive bead product according to claim 1, wherein the quality problem data table obtaining method is as follows: and determining the reason by manually detecting the defective product, forming a corresponding relation between the determined defect reason and the quality excellence of the explosion beads, and constructing a quality problem data table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310999986.7A CN116721102B (en) | 2023-08-10 | 2023-08-10 | Quick traceability method for quality of explosive bead products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310999986.7A CN116721102B (en) | 2023-08-10 | 2023-08-10 | Quick traceability method for quality of explosive bead products |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116721102A true CN116721102A (en) | 2023-09-08 |
| CN116721102B CN116721102B (en) | 2023-10-20 |
Family
ID=87870078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310999986.7A Active CN116721102B (en) | 2023-08-10 | 2023-08-10 | Quick traceability method for quality of explosive bead products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116721102B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117333489A (en) * | 2023-12-01 | 2024-01-02 | 苏州普洛泰科精密工业有限公司 | Film damage detection device and detection system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019066767A1 (en) * | 2017-09-26 | 2019-04-04 | Siemens Product Lifecycle Management Software Inc. | System and method for providing variation in bead size to improve geometrical accuracy of deposited layers in an additive manufacturing process |
| CN109781735A (en) * | 2018-12-26 | 2019-05-21 | 中电科信息产业有限公司 | A kind of quick-fried pearl on-line measuring device and detection method |
| US20190206043A1 (en) * | 2017-12-29 | 2019-07-04 | Huizhou China Star Optoelectronics Technology Co., Ltd. | Method and system for detection of in-panel mura based on hough transform and gaussian fitting |
| US20190285476A1 (en) * | 2016-11-11 | 2019-09-19 | Henkel Ag & Co. Kgaa | Method and device for determining the color homogeneity of hair |
| CN112033313A (en) * | 2020-10-10 | 2020-12-04 | 成都瑞拓科技股份有限公司 | Eccentricity detection method for wet blasting bead |
| US20210166358A1 (en) * | 2019-12-02 | 2021-06-03 | Aizo Systems LLC | Artificial intelligence based image quality assessment system |
| CN115049653A (en) * | 2022-08-15 | 2022-09-13 | 凤芯微电子科技(聊城)有限公司 | Integrated circuit board quality detection system based on computer vision |
| CN115836744A (en) * | 2022-11-30 | 2023-03-24 | 红云红河烟草(集团)有限责任公司 | Cigarette circumference detection method |
| CN116030034A (en) * | 2023-02-21 | 2023-04-28 | 青岛精锐机械制造有限公司 | Visual identification method for valve surface defects |
-
2023
- 2023-08-10 CN CN202310999986.7A patent/CN116721102B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190285476A1 (en) * | 2016-11-11 | 2019-09-19 | Henkel Ag & Co. Kgaa | Method and device for determining the color homogeneity of hair |
| WO2019066767A1 (en) * | 2017-09-26 | 2019-04-04 | Siemens Product Lifecycle Management Software Inc. | System and method for providing variation in bead size to improve geometrical accuracy of deposited layers in an additive manufacturing process |
| US20190206043A1 (en) * | 2017-12-29 | 2019-07-04 | Huizhou China Star Optoelectronics Technology Co., Ltd. | Method and system for detection of in-panel mura based on hough transform and gaussian fitting |
| CN109781735A (en) * | 2018-12-26 | 2019-05-21 | 中电科信息产业有限公司 | A kind of quick-fried pearl on-line measuring device and detection method |
| US20210166358A1 (en) * | 2019-12-02 | 2021-06-03 | Aizo Systems LLC | Artificial intelligence based image quality assessment system |
| CN112033313A (en) * | 2020-10-10 | 2020-12-04 | 成都瑞拓科技股份有限公司 | Eccentricity detection method for wet blasting bead |
| CN115049653A (en) * | 2022-08-15 | 2022-09-13 | 凤芯微电子科技(聊城)有限公司 | Integrated circuit board quality detection system based on computer vision |
| CN115836744A (en) * | 2022-11-30 | 2023-03-24 | 红云红河烟草(集团)有限责任公司 | Cigarette circumference detection method |
| CN116030034A (en) * | 2023-02-21 | 2023-04-28 | 青岛精锐机械制造有限公司 | Visual identification method for valve surface defects |
Non-Patent Citations (4)
| Title |
|---|
| YAN, GAOYUAN等: "Quantitative description of shale pore structure using image analysis and determination of controls on shape, size and orientation complexity", 《ARABIAN JOURNAL OF GEOSCIENCES》 * |
| 李巧灵;黄胜翰;张廷贵;施建在;余玉梅;姚小元;陈昆焱;***;黄华发;张国建;黄朝章;庄锦标;徐建荣;戴丽君;: "爆珠滴制在线视觉检测设备的设计及应用", 烟草科技, no. 07 * |
| 杨光远;王闻;彭三文;刘强;李立新;李哲铭;邓少鹏;: "爆珠滤棒在线视觉检测***的研究与开发", 轻工科技, no. 04 * |
| 林生佑, 石教英: "基于HVS的彩色图像边缘检测算子", 中国图象图形学报, no. 01 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117333489A (en) * | 2023-12-01 | 2024-01-02 | 苏州普洛泰科精密工业有限公司 | Film damage detection device and detection system |
| CN117333489B (en) * | 2023-12-01 | 2024-02-02 | 苏州普洛泰科精密工业有限公司 | Film damage detection device and detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116721102B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116721102B (en) | Quick traceability method for quality of explosive bead products | |
| CN104871175B (en) | Food quality is scored and is controlled | |
| US20060081135A1 (en) | Industrial overline imaging system and method | |
| CN114387273B (en) | Environmental dust concentration detection method and system based on computer image recognition | |
| CN113610850B (en) | Decorative paper texture abnormity detection method based on image processing | |
| Ni et al. | Corn kernel crown shape identification using image processing | |
| CN110310275B (en) | Chain conveyor belt defect detection method based on image processing | |
| CN111122590B (en) | Ceramic surface defect detection device and detection method | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN112669394A (en) | Automatic calibration method for vision detection system | |
| CN115330791A (en) | Part burr detection method | |
| CN116958125B (en) | Electronic contest host power supply element defect visual detection method based on image processing | |
| van Zwanenberg et al. | Edge detection techniques for quantifying spatial imaging system performance and image quality | |
| CN108889635B (en) | Online visual inspection method for manufacturing defects of ring-pull cans | |
| CN116703889B (en) | Flexible circuit board patch abnormality detection method | |
| CN115953627A (en) | Image recognition system capable of classifying grades of peppers | |
| CN109540892A (en) | Duck variety discriminating method and system | |
| CN115545383A (en) | Binocular stereoscopic vision detection method for crisp appearance quality of strawberries | |
| CN113570578A (en) | Lens ghost phenomenon detection method and device | |
| Thong et al. | Mango sorting mechanical system combines image processing | |
| CN116797575A (en) | Intelligent detection method for broken rice rate based on machine vision | |
| CN116485801A (en) | Rubber tube quality online detection method and system based on computer vision | |
| Thinh et al. | Sorting and classification of mangoes based on artificial intelligence | |
| Yin et al. | Image processing techniques for internal texture evaluation of French fries | |
| CN114088714B (en) | Method for detecting surface regularity of grain particles |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |