CN118735923B - An intelligent evaluation method for the assembly quality of router housing - Google Patents
An intelligent evaluation method for the assembly quality of router housing Download PDFInfo
- Publication number
- CN118735923B CN118735923B CN202411230794.0A CN202411230794A CN118735923B CN 118735923 B CN118735923 B CN 118735923B CN 202411230794 A CN202411230794 A CN 202411230794A CN 118735923 B CN118735923 B CN 118735923B
- Authority
- CN
- China
- Prior art keywords
- area
- radiating hole
- areas
- sub
- crack
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 18
- 230000017525 heat dissipation Effects 0.000 claims abstract description 114
- 238000000034 method Methods 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 32
- 230000004660 morphological change Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 9
- 238000001816 cooling Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 206010057175 Mass conditions Diseases 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Image Analysis (AREA)
Abstract
本发明涉及图像分析技术领域，具体涉及一种路由器外壳的装配质量智能化评估方法，包括：获取路由器外壳的边缘图像；获取边缘图像中散热孔区域；根据散热孔子区域中像素点的灰度值和散热孔区域的位置，获取散热孔子区域的裂纹；根据散热孔子区域中裂纹延伸后与相近散热孔区域的接近情况，得到散热孔子区域中每条裂纹的每一端对散热孔区域的潜在影响程度；获取散热孔子区域的质量指数；根据散热孔子区域的质量指数、边缘图像中散热孔区域的面积及边缘图像中裂纹的面积，评估路由器外壳的装配质量。本发明提高了路由器外壳的装配质量评估的准确性。
The present invention relates to the field of image analysis technology, and in particular to an intelligent evaluation method for the assembly quality of a router shell, comprising: obtaining an edge image of the router shell; obtaining a heat dissipation hole area in the edge image; obtaining cracks in the heat dissipation hole sub-area according to the grayscale value of pixels in the heat dissipation hole sub-area and the position of the heat dissipation hole area; obtaining the potential influence of each end of each crack in the heat dissipation hole sub-area on the heat dissipation hole area according to the proximity of the crack in the heat dissipation hole sub-area to the adjacent heat dissipation hole area after extension; obtaining the quality index of the heat dissipation hole sub-area; and evaluating the assembly quality of the router shell according to the quality index of the heat dissipation hole sub-area, the area of the heat dissipation hole area in the edge image, and the area of the crack in the edge image. The present invention improves the accuracy of the evaluation of the assembly quality of the router shell.
Description
Technical Field
The invention relates to the technical field of image analysis, in particular to an intelligent evaluation method for the assembly quality of a router shell.
Background
The router housing assembly quality directly affects the overall quality and performance stability of the router product. Through intelligent evaluation, the crack defect of the router shell can be found in time so as to ensure the quality of router products.
When the assembly quality of the router shell is evaluated by the existing method, the assembly quality of the router shell is evaluated by only analyzing the crack defect area of the surface of the router shell through edge detection. Since the router shell itself may have a heat dissipation hole, and the crack on the surface of the router shell may be connected to the heat dissipation hole, and the crack and the gray level of the heat dissipation hole are similar, so that the crack defect is difficult to detect, and the crack may have a potential influence on the area of the heat dissipation hole, for example, the crack may extend to the heat dissipation hole with the passage of time, if the assembly quality of the router shell is evaluated by only analyzing the crack defect area on the surface of the router shell, the assembly quality evaluation of the router shell may be inaccurate.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent evaluation method for the assembly quality of a router shell.
The intelligent evaluation method for the assembly quality of the router shell adopts the following technical scheme:
An embodiment of the present invention provides a method for intelligently evaluating assembly quality of a router shell, including the steps of:
Acquiring an edge image of a router shell;
Obtaining a plurality of initial radiating hole areas in the edge image according to the morphological change of the edge in the edge image;
dividing the edge image according to the radiating hole areas to obtain a plurality of radiating hole sub-areas of the edge image, obtaining a plurality of cracks of each radiating hole sub-area according to the gray value of pixel points in the radiating hole sub-areas and the positions of the radiating hole areas, and obtaining the potential influence degree of each end of each crack in each radiating hole sub-area on the radiating hole areas according to the approaching condition of the crack in the radiating hole sub-areas to the similar radiating hole areas after the crack extends;
The quality index of each radiating hole sub-area is obtained according to the number and the area of the cracks in the radiating hole sub-area and the potential influence degree of each end of each crack on the radiating hole area, the assembly quality parameter of the router shell is obtained according to the quality index of the radiating hole sub-area, the area of the radiating hole area in the edge image and the area of the crack in the edge image, and the assembly quality of the router shell is evaluated according to the size of the assembly quality parameter.
Further, according to the morphological change of the edge in the edge image, a plurality of initial heat dissipation hole areas in the edge image are obtained, and the method comprises the following specific steps:
For any edge in the edge image of the router shell, acquiring an original chain code of the edge, taking the absolute value of the difference value between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and making the change value of the direction symbol belong to The method comprises the steps of obtaining corresponding pixel points serving as radiating hole edge pixel points, obtaining edges formed by continuous radiating hole edge pixel points and recording the edges as initial radiating hole edges, taking a closed area as an initial radiating hole area if any one initial radiating hole edge forms a closed area, and fitting the pixel points on the initial radiating hole edge if any one initial radiating hole edge does not form the closed area to obtain a closed circular area serving as the initial radiating hole area.
Further, according to the distance change and the area change between the initial heat dissipation hole areas, a plurality of heat dissipation hole areas in the edge image are obtained, and the method comprises the following specific steps:
For any initial radiating hole area in the edge image of the router shell, acquiring the shortest distance between the initial radiating hole area and other initial radiating hole areas; obtaining the difference value of the area of the initial radiating hole area and the average area of all the initial radiating hole areas, multiplying the inverse of the difference value of the shortest distance and the average shortest distance, the inverse of the difference value of the area of the initial radiating hole area and the average area of all the initial radiating hole areas, and normalizing to obtain the probability that the initial radiating hole area belongs to the radiating hole area in the edge image of the router shell;
and screening out a plurality of radiating hole areas according to the probability that the initial radiating hole area belongs to the radiating hole area.
Further, the step of screening out a plurality of heat dissipation hole areas according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area comprises the following specific steps:
and taking the initial radiating hole area with the probability of the initial radiating hole area belonging to the radiating hole area being larger than a preset first threshold value as the radiating hole area in the edge image of the router shell, wherein the first threshold value is 0.7.
Further, the dividing the edge image according to the heat dissipation hole area to obtain a plurality of heat dissipation hole sub-areas of the edge image comprises the following specific steps:
The minimum bounding rectangle determined every four adjacent louver areas is taken as the louver sub-areas of the edge image of the router housing, in order from left to right and top to bottom, starting from the upper left corner of the edge image of the router housing.
Further, the method for obtaining a plurality of cracks of each heat dissipation hole sub-area according to the gray value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area comprises the following specific steps:
And for any one of the radiating hole sub-areas, acquiring pixel points with the gray value of 0 in the radiating hole sub-area, and if the pixel points with the gray value of 0 do not belong to the radiating hole area in the radiating hole sub-area, taking the pixel points as crack pixel points of the radiating hole sub-area, acquiring all crack pixel points of the radiating hole sub-area, and acquiring a plurality of cracks of the radiating hole sub-area according to the continuous crack pixel points in the radiating hole sub-area.
Further, the step of obtaining the potential influence degree of each end of each crack in each heat dissipation hole subarea on the heat dissipation hole area according to the approaching condition of the crack in the heat dissipation hole subarea and the similar heat dissipation hole area after the crack extends comprises the following specific steps:
The method comprises the steps of obtaining the shortest distance between a crack and the nearest radiating hole area in the extending direction of the end, marking the shortest distance as a first shortest distance, obtaining the included angle value between the extending direction of the crack and the horizontal right direction, wherein the included angle value is obtained by taking the horizontal right direction as 0 DEG, and the anticlockwise direction as the positive direction, obtaining the first included angle value between the extending direction of the crack and the nearest radiating hole area, and the specific obtaining method of the first included angle value comprises the steps of obtaining the tangent line of the last pixel point of the crack and the nearest radiating hole area in the extending direction of the end, taking the minimum included angle value between the extending direction of the crack and the tangent line as the first included angle value, multiplying the reciprocal of the first shortest distance, the reciprocal of the difference value of the included angle value and the first included angle value, and normalizing to obtain the potential influence degree of the crack in the radiating hole area on the radiating hole area.
Further, the method for obtaining the quality index of each heat dissipation hole sub-area according to the number and the area of the cracks in the heat dissipation hole sub-area and the potential influence degree of each end of each crack on the heat dissipation hole area comprises the following specific steps:
For any one radiating hole sub-area, obtaining the average potential influence degree of the two ends of each crack of the radiating hole sub-area on the radiating hole area, taking the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area as the weighted potential influence degree of the crack on the radiating hole area, and taking the product of the accumulated value of the weighted potential influence degree of all cracks in the radiating hole sub-area on the radiating hole area and the reciprocal of the crack number in the radiating hole sub-area as the quality index of the radiating hole sub-area.
Further, the assembling quality parameters of the router shell are obtained according to the quality indexes of the sub-areas of the radiating holes, the areas of the radiating hole areas in the edge images and the areas of the cracks in the edge images, and the assembling quality parameters comprise the following specific steps:
And multiplying and normalizing the average value of the quality indexes of all the radiating hole sub-areas, the area ratio of the areas of all the radiating hole areas to the edge image and the reciprocal of the areas of all the cracks in the edge image to obtain the assembly quality parameter of the router shell.
Further, the step of evaluating the assembly quality of the router shell according to the magnitude of the assembly quality parameter comprises the following specific steps:
If the assembly quality parameter of the router shell is smaller than a preset second threshold value, the assembly quality of the router shell is unqualified, and if the assembly quality parameter of the router shell is larger than or equal to the preset second threshold value, the assembly quality of the router shell is qualified, wherein the second threshold value is 0.8.
The method has the advantages that after the edge image of the router shell is obtained, a more accurate radiating hole area is obtained through analysis of the shape change of the edge in the edge image and the distance change and the area change between the radiating hole areas, the fact that the accurate radiating hole area is difficult to determine due to connection of cracks and the radiating holes is reduced, the cracks of radiating hole sub-areas are further obtained more accurately, the accuracy of crack detection is improved, meanwhile, the potential influence degree of each end of each crack in each radiating hole sub-area on the radiating hole area is obtained through analysis of the approaching condition of the crack after the crack extends to the similar radiating hole area, the assembly quality of the router shell is evaluated more reasonably, and finally the assembly quality parameter of the router shell is obtained through the quality index of the radiating hole sub-areas, the area of the radiating hole areas in the edge image and the area of the crack in the edge image, the assembly quality of the router shell is evaluated, and the assembly quality of the router shell is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for intelligently evaluating the assembly quality of a router shell according to an embodiment of the present invention;
Fig. 2 is a flowchart for obtaining quality parameters of assembly of a router shell according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to the specific implementation, structure, characteristics and effects of an intelligent evaluation method for the assembly quality of a router shell according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the intelligent evaluation method for the assembly quality of the router shell provided by the invention with reference to the accompanying drawings.
Referring to fig. 1 and 2, a flowchart of steps of a method for intelligently evaluating assembly quality of a router shell and a flowchart for obtaining assembly quality parameters of the router shell according to an embodiment of the present invention are shown, where the method includes the following steps:
and S001, acquiring an edge image of the router shell.
It should be noted that, the main purpose of this embodiment is to obtain the quality index of the sub-area of the heat dissipation hole by analyzing the potential influence of the crack on the router shell on the heat dissipation hole area, and comprehensively obtain the assembly quality parameters of the router shell by combining the performance of the crack on the router shell. Before starting the analysis, the required image is acquired.
Specifically, an edge image of the router shell is obtained, specifically as follows:
And carrying out overlooking shooting on the surface of the assembled router shell by using a camera to obtain an RGB image of the surface of the router shell, carrying out graying and histogram equalization processing on the RGB image to obtain a gray image of the router shell, and carrying out edge detection on the gray image of the router shell by using a Canny operator to obtain an edge image of the router shell.
Since the surface of the router case is white, the photographing background needs to be set to white at the time of photographing in order to perform quality evaluation later.
Thus, an edge image of the router housing is acquired.
Step S002, obtaining a plurality of initial radiating hole areas in the edge image according to the shape change of the edge in the edge image, and obtaining a plurality of radiating hole areas in the edge image according to the distance change and the area change between the initial radiating hole areas.
In order to better analyze the potential influence of the crack on the router shell on the heat dissipation hole area, the heat dissipation hole area needs to be determined first, and the edge image of the router shell is obtained, and the heat dissipation hole on the router shell is mainly circular, so that the edge of the heat dissipation hole can be in a circular shape. Therefore, a plurality of initial radiating hole areas are obtained through morphological changes of edges in the edge image.
Specifically, according to the morphological change of the edge in the edge image, a plurality of initial radiating hole areas in the edge image are obtained, specifically as follows:
For any edge in the edge image of the router shell, acquiring an original chain code of the edge, taking the absolute value of the difference value between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and making the change value of the direction symbol belong to The method comprises the steps of obtaining corresponding pixel points serving as radiating hole edge pixel points, obtaining edges formed by continuous radiating hole edge pixel points and recording the edges as initial radiating hole edges, taking a closed area as an initial radiating hole area if any one initial radiating hole edge forms a closed area, and fitting the pixel points on the initial radiating hole edge if any one initial radiating hole edge does not form the closed area to obtain a closed circular area serving as the initial radiating hole area. In this embodiment, the circle fitting is performed on the pixel points on the edge of the initial heat dissipation hole where a closed region is not formed by the least square method, and the specific fitting is the existing method, which is not described in detail in this embodiment.
It should be noted that, since the heat dissipation hole is mainly circular, the edge of the heat dissipation hole will be in a circular shape, the change reflected as a direction symbol in the original chain code of the edge is moderate, so the edge of the initial heat dissipation hole is screened by analyzing the change value of the direction symbol in the original chain code of the edge, meanwhile, the situation that the crack may be connected with the heat dissipation hole to cause the edge of the heat dissipation hole to be poorly determined is considered, the pixel points which show a shape close to the circular shape are fitted, so the initial heat dissipation hole area is obtained, and the shape of part of the crack may be close to the heat dissipation hole, so the initial heat dissipation hole area is obtained, and further analysis is needed.
It should be noted that, since the initial hole area is obtained as described above, the shape of a part of the crack may be similar to the hole, which may interfere with determining the actual hole area, and thus the actual hole area needs to be obtained by combining the change in distance and the change in area between the initial hole areas. Because the distances among the radiating hole areas are approximately equal and the areas are relatively similar, a plurality of radiating hole areas in the edge image are obtained through the distance change and the area change.
Specifically, according to the distance change and the area change between the initial heat dissipation hole areas, a plurality of heat dissipation hole areas in the edge image are obtained, and the method comprises the following steps:
First, according to the distance change and the area change between the initial radiating hole areas, the probability that each initial radiating hole area belongs to the radiating hole area in the edge image of the router shell is obtained.
Secondly, a plurality of radiating hole areas are screened out according to the probability that the initial radiating hole area belongs to the radiating hole area.
Preferably, in one embodiment of the present invention, the probability that each initial louvre area belongs to a louvre area in the edge image of the router casing is obtained according to the distance change and the area change between the initial louvre areas, which is specifically as follows:
The method comprises the steps of obtaining the shortest distance between an initial radiating hole area and other initial radiating hole areas in an edge image of a router shell, obtaining the difference value between the shortest distance and an average shortest distance, which is the average value of the shortest distances between all initial radiating hole areas and other initial radiating hole areas, obtaining the difference value between the area of the initial radiating hole area and the average area of all initial radiating hole areas, multiplying the inverse of the difference value between the shortest distance and the average shortest distance, the inverse of the difference value between the area of the initial radiating hole area and the average area of all initial radiating hole areas, and normalizing to obtain the probability that the initial radiating hole area belongs to the radiating hole area in the edge image of the router shell.
As a specific example, the specific acquisition method of the probability that the initial louvre region belongs to the louvre region is as follows:
in the formula, Edge image for router shellShortest distance between each initial radiating hole area and other initial radiating hole areas; the average value of the shortest distance between all initial radiating hole areas and other initial radiating hole areas in the edge image of the router shell; Taking an absolute value; Edge image for router shell The number of pixel points in the initial heat dissipation hole areas; the average value of the number of pixel points in all initial radiating hole areas in the edge image of the router shell; is a linear normalization function; Edge image for router shell Probability that the initial louvre region belongs to the louvre region.
It should be noted that, because the distances between the heat dissipation hole areas are approximately equal and the areas are relatively similar, the above formula obtains the probability that each initial heat dissipation hole area belongs to the heat dissipation hole area in the edge image of the router shell by analyzing the distance change and the area change between the initial heat dissipation hole areas.The smaller, the description of the firstThe shortest distance between each initial radiating hole area and other initial radiating hole areas has smaller change compared with the whole average distance, the distance between the initial radiating hole areas is more regular, the firstThe higher the probability that the initial louvre region belongs to the louvre region; The smaller, the description of the first The initial heat dissipation hole areas have smaller area change than the whole area, the more regular the area of the initial heat dissipation hole areas is, the firstThe probability that each initial heat dissipation hole area belongs to the heat dissipation hole area is higher, and the purpose of adding 1 to the denominator is to prevent the occurrence of the situation that the denominator is 0 and cannot be calculated.
It should be noted that, the probability that each initial louvre area belongs to a louvre area in the edge image of the router housing is obtained, and a plurality of louvre areas are screened out by setting a proper threshold.
Specifically, a plurality of heat dissipation hole areas are screened out according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area, and the specific steps are as follows:
and taking the initial radiating hole area with the probability of the initial radiating hole area belonging to the radiating hole area being larger than a preset first threshold value as the radiating hole area in the edge image of the router shell, wherein the first threshold value is 0.7.
So far, a plurality of radiating hole areas in the edge image are obtained.
The method comprises the steps of S003, dividing an edge image according to a radiating hole area to obtain a plurality of radiating hole sub-areas of the edge image, obtaining a plurality of cracks of each radiating hole sub-area according to gray values of pixel points in the radiating hole sub-areas and positions of the radiating hole areas, and obtaining potential influence degree of each end of each crack in each radiating hole sub-area on the radiating hole area according to the approaching condition of the crack in the radiating hole sub-area after the crack extends to the similar radiating hole area.
It should be noted that, since the cracks of the router shell are mainly distributed between the heat dissipation hole areas, for better analysis, the edge image needs to be divided according to the heat dissipation hole areas to obtain heat dissipation hole sub-areas.
Specifically, the edge image is divided according to the heat dissipation hole areas, and a plurality of heat dissipation hole sub-areas of the edge image are obtained, specifically as follows:
The minimum bounding rectangle determined every four adjacent louver areas is taken as the louver sub-areas of the edge image of the router housing, in order from left to right and top to bottom, starting from the upper left corner of the edge image of the router housing. If the number of the remaining heat dissipating hole areas is not enough to constitute four heat dissipating hole areas adjacent to each other, analysis is not performed.
It should be noted that, when the heat dissipating hole sub-area is reached, the cracks are mainly distributed between the heat dissipating hole areas in the heat dissipating hole sub-area, and in order to better determine the potential influence of the cracks on the heat dissipating hole area, it is first required to determine the cracks in the heat dissipating hole sub-area. Since the gray level of the crack is similar to the gray level of the radiating hole area, the crack is determined in the radiating hole area through the gray level of the pixel in the radiating hole sub-area and the position of the radiating hole area.
Specifically, according to the gray value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area, a plurality of cracks of each heat dissipation hole sub-area are obtained, specifically as follows:
And for any one of the radiating hole sub-areas, acquiring pixel points with the gray value of 0 in the radiating hole sub-area, and if the pixel points with the gray value of 0 do not belong to the radiating hole area in the radiating hole sub-area, taking the pixel points as crack pixel points of the radiating hole sub-area, acquiring all crack pixel points of the radiating hole sub-area, and acquiring a plurality of cracks of the radiating hole sub-area according to the continuous crack pixel points in the radiating hole sub-area.
It should be noted that, since there are a plurality of sub-areas of the heat dissipation holes, some of the sub-areas of the heat dissipation holes may not have cracks, the main analysis of this embodiment is to analyze the sub-areas of the heat dissipation holes having cracks, but for the normal sub-areas of the heat dissipation holes, there is no problem on its own, and no analysis is performed.
It should be noted that, the main purpose of this embodiment is to obtain the quality index of the sub-area of the heat dissipation hole by analyzing the potential influence of the crack on the router shell on the heat dissipation hole area, and comprehensively obtain the assembly quality parameters of the router shell by combining the performance of the crack on the router shell. The above has resulted in a crack in the louvre region, and then analyzing the potential impact of each end of the crack on the louvre region. If the crack in the radiating hole sub-area is closer to the adjacent radiating hole area after being extended, the crack may be extended to the radiating hole area after a period of time, and the potential influence on the radiating hole area is larger, so that the potential influence degree of each end of the crack on the radiating hole area is obtained by analyzing the approaching condition of the crack after being extended to the adjacent radiating hole area.
Preferably, in one embodiment of the present invention, the potential influence degree of each end of each crack in each heat dissipating hole sub-area on the heat dissipating hole area is obtained according to the proximity condition of the crack in the heat dissipating hole sub-area to the similar heat dissipating hole area after the crack extends, which is specifically as follows:
The method comprises the steps of obtaining the shortest distance between a crack and the nearest radiating hole area in the extending direction of the end, marking the shortest distance as a first shortest distance, obtaining the included angle value between the extending direction of the crack and the horizontal right direction, wherein the included angle value is obtained by taking the horizontal right direction as 0 DEG, and the anticlockwise direction as the positive direction, obtaining the first included angle value between the extending direction of the crack and the nearest radiating hole area, and the specific obtaining method of the first included angle value comprises the steps of obtaining the tangent line of the last pixel point of the crack and the nearest radiating hole area in the extending direction of the end, taking the minimum included angle value between the extending direction of the crack and the tangent line as the first included angle value, multiplying the reciprocal of the first shortest distance, the reciprocal of the difference value of the included angle value and the first included angle value, and normalizing to obtain the potential influence degree of the crack in the radiating hole area on the radiating hole area.
As a specific example, the specific method for obtaining the potential influence degree is as follows:
Any one of the sub-areas of the radiating hole with cracks is marked as a target radiating hole sub-area.
The extending direction of each crack in the target radiating hole sub-area at each end is obtained by the specific obtaining method of the extending direction, namely, for the last two pixel points at any one end of any crack in the target radiating hole sub-area, pointing the next post pixel point in the last two pixel points to the direction of the last pixel point, and taking the direction of the extending direction of the crack at the end as the extending direction of the crack.
In the formula,Is the first in the target heat dissipation hole areaA first shortest distance of the strip crack from the nearest heat dissipation hole area in the extending direction of the 1 st end; Is the first in the target heat dissipation hole area An included angle value between the extending direction of the 1 st end of the strip crack and the horizontal rightward direction is obtained by taking the horizontal rightward direction as 0 DEG and the anticlockwise direction as the positive direction; Is the first in the target heat dissipation hole area The specific acquisition method of the first included angle value between the extension direction of the strip crack at the 1 st end and the nearest radiating hole area comprises the following steps of acquiring the first included angle value in the target radiating hole areaThe strip crack is at the tangent line of the last pixel point of the 1 st end and the nearest radiating hole area in the extending direction of the 1 st end, and the first radiating hole area in the target radiating hole areaThe minimum angle value between the extension direction of the strip crack at the 1 st end and the tangent line is recorded as;Taking an absolute value; is a linear normalization function; Is the first in the target heat dissipation hole area The potential extent of influence of the 1 st end of the strip crack on the heat sink area.
It should be noted that, if the crack in the sub-area of the heat dissipating hole extends to be closer to the adjacent heat dissipating hole area, the crack may extend to the heat dissipating hole area after a period of time, and the potential influence on the heat dissipating hole area is greater.The smaller, the description of the firstThe closer the strip crack is to the nearest radiating hole area in the extending direction of the 1 st end, the greater the potential influence degree on the nearest radiating hole area; The smaller, the description of the first The smaller the included angle between the extending direction of the strip crack at the 1 st end and the tangent line passing through the last pixel point at the 1 st end is, namely the greater the potential influence degree of the crack extending trend on the nearest radiating hole area is, and the potential influence of each end of the crack on the radiating hole area is obtained by combining the distance and the included angle.
Thus, the potential influence degree of each end of each crack in each radiating hole area on the radiating hole area is obtained.
Step S004, obtaining a quality index of each radiating hole sub-area according to the number and the area of cracks in the radiating hole sub-area and the potential influence degree of each end of each crack on the radiating hole area, obtaining an assembly quality parameter of the router shell according to the quality index of the radiating hole sub-area, the area of the radiating hole area in the edge image and the area of the crack in the edge image, and evaluating the assembly quality of the router shell according to the size of the assembly quality parameter.
It should be noted that the potential influence degree of each end of each crack in each heat dissipation hole sub-area on the heat dissipation hole area is obtained, and then the quality condition of each heat dissipation hole sub-area is analyzed, so that the assembly quality of the router shell is better evaluated. The quality condition of the radiating hole sub-area is related to the number and the area of cracks in the radiating hole sub-area and the potential influence degree of two ends of each crack in the radiating hole sub-area on the radiating hole area, when the number, the area and the potential influence degree of the cracks in the radiating hole sub-area are larger, the quality condition of the radiating hole sub-area is indicated to be poorer, and therefore the quality index of the radiating hole sub-area is obtained by analyzing the number and the area of the cracks in the radiating hole sub-area and the potential influence degree of two ends of each crack in the radiating hole sub-area on the radiating hole area.
Preferably, in one embodiment of the present invention, the quality index of each sub-area of the heat dissipation hole is obtained according to the number and the area of the cracks in the sub-area of the heat dissipation hole and the potential influence degree of each end of each crack on the heat dissipation hole area, which is specifically as follows:
For any one radiating hole sub-area, obtaining the average potential influence degree of the two ends of each crack of the radiating hole sub-area on the radiating hole area, taking the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area as the weighted potential influence degree of the crack on the radiating hole area, and taking the product of the accumulated value of the weighted potential influence degree of all cracks in the radiating hole sub-area on the radiating hole area and the reciprocal of the crack number in the radiating hole sub-area as the quality index of the radiating hole sub-area.
As a specific example, the specific method for obtaining the quality index is as follows:
in the formula, The number of cracks in the target heat dissipation hole subarea is the number of cracks; Is the first in the target heat dissipation hole area Area of the strip crack; Is the first in the target heat dissipation hole area The potential influence degree of the 1 st end of the strip crack on the radiating hole area; Is the first in the target heat dissipation hole area The potential influence degree of the 2 nd end of the strip crack on the radiating hole area; Is the quality index of the target heat dissipation hole sub-area.
It should be noted that, since the mass condition of the sub-areas of the heat dissipating holes is related to the number and the area of the cracks in the sub-areas of the heat dissipating holes and the potential influence degree of the two ends of each crack in the sub-areas of the heat dissipating holes on the areas of the heat dissipating holes, when the number, the area and the potential influence degree of the cracks in the sub-areas of the heat dissipating holes are larger, that is、、The larger the mass of the sub-area of the heat dissipation hole is, the worse the mass condition of the sub-area of the heat dissipation hole is, so that the mass index of the sub-area of the heat dissipation hole is obtained through reciprocal analysis.
It should be noted that, the quality index of each cooling hole sub-area is obtained, and by combining the quality index of the cooling hole sub-area, the area of the cooling hole area and the area of the crack, the assembly quality parameter of the router shell is more reasonably evaluated, and when the quality index of the cooling hole sub-area is larger, the area of the cooling hole area is larger and the area of the crack is smaller, the assembly quality of the router shell is higher, namely, the assembly quality parameter of the router shell is larger.
Preferably, in one embodiment of the present invention, the assembly quality parameter of the router shell is obtained according to the quality index of the sub-area of the heat dissipation hole, the area of the heat dissipation hole area in the edge image, and the area of the crack in the edge image, and specifically includes the following steps:
And multiplying and normalizing the average value of the quality indexes of all the radiating hole sub-areas, the area ratio of the areas of all the radiating hole areas to the edge image and the reciprocal of the areas of all the cracks in the edge image to obtain the assembly quality parameter of the router shell.
As a specific example, the specific acquisition method of the assembly quality parameter is as follows:
in the formula, The average value of the quality indexes of all the radiating hole sub-areas is obtained; the areas of all the radiating hole areas in the edge image; Is the area of the edge image; the area of all cracks in the edge image; is a linear normalization function; is an assembly quality parameter of the router housing.
It is to be noted that,The larger the overall mass of the sub-area of the radiating hole is, the higher the assembly quality of the corresponding router shell is; The larger the area of the radiating hole area is, the higher the assembly quality of the router shell is; smaller indicates smaller cracks on the surface of the router housing and higher assembly quality of the router housing.
The above-mentioned quality parameters of the router shell are obtained, and the quality of the router shell is evaluated by setting a suitable threshold.
Specifically, the assembly quality of the router shell is evaluated according to the magnitude of the assembly quality parameter, and the assembly quality is specifically as follows:
If the assembly quality parameter of the router shell is smaller than a preset second threshold, the assembly quality of the router shell is unqualified, and if the assembly quality parameter of the router shell is larger than or equal to the preset second threshold, the assembly quality of the router shell is qualified, and the embodiment is described with the second threshold being 0.8.
Through the steps, the intelligent evaluation method for the assembly quality of the router shell is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An intelligent evaluation method for the assembly quality of a router shell is characterized by comprising the following steps:
Acquiring an edge image of a router shell;
Obtaining a plurality of initial radiating hole areas in the edge image according to the morphological change of the edge in the edge image;
dividing the edge image according to the radiating hole areas to obtain a plurality of radiating hole sub-areas of the edge image, obtaining a plurality of cracks of each radiating hole sub-area according to the gray value of pixel points in the radiating hole sub-areas and the positions of the radiating hole areas, and obtaining the potential influence degree of each end of each crack in each radiating hole sub-area on the radiating hole areas according to the approaching condition of the crack in the radiating hole sub-areas to the similar radiating hole areas after the crack extends;
The quality index of each radiating hole sub-area is obtained according to the number and the area of the cracks in the radiating hole sub-area and the potential influence degree of each end of each crack on the radiating hole area, the assembly quality parameter of the router shell is obtained according to the quality index of the radiating hole sub-area, the area of the radiating hole area in the edge image and the area of the crack in the edge image, and the assembly quality of the router shell is evaluated according to the size of the assembly quality parameter.
2. The intelligent evaluation method for the assembly quality of the router shell according to claim 1, wherein the obtaining of the plurality of initial heat dissipation hole areas in the edge image according to the morphological change of the edge in the edge image comprises the following specific steps:
For any edge in the edge image of the router shell, acquiring an original chain code of the edge, taking the absolute value of the difference value between each direction symbol in the original chain code and the next direction symbol as the change value of each direction symbol in the original chain code, and making the change value of the direction symbol belong to The method comprises the steps of obtaining corresponding pixel points serving as radiating hole edge pixel points, obtaining edges formed by continuous radiating hole edge pixel points and recording the edges as initial radiating hole edges, taking a closed area as an initial radiating hole area if any one initial radiating hole edge forms a closed area, and fitting the pixel points on the initial radiating hole edge if any one initial radiating hole edge does not form the closed area to obtain a closed circular area serving as the initial radiating hole area.
3. The method for intelligently evaluating the assembly quality of a router shell according to claim 1, wherein the obtaining a plurality of radiating hole areas in an edge image according to the distance change and the area change between the initial radiating hole areas comprises the following specific steps:
For any initial radiating hole area in the edge image of the router shell, acquiring the shortest distance between the initial radiating hole area and other initial radiating hole areas; obtaining the difference value of the area of the initial radiating hole area and the average area of all the initial radiating hole areas, multiplying the inverse of the difference value of the shortest distance and the average shortest distance, the inverse of the difference value of the area of the initial radiating hole area and the average area of all the initial radiating hole areas, and normalizing to obtain the probability that the initial radiating hole area belongs to the radiating hole area in the edge image of the router shell;
and screening out a plurality of radiating hole areas according to the probability that the initial radiating hole area belongs to the radiating hole area.
4. The intelligent evaluation method for the assembly quality of the router shell according to claim 3, wherein the step of screening out a plurality of heat dissipation hole areas according to the probability that the initial heat dissipation hole area belongs to the heat dissipation hole area comprises the following specific steps:
and taking the initial radiating hole area with the probability of the initial radiating hole area belonging to the radiating hole area being larger than a preset first threshold value as the radiating hole area in the edge image of the router shell, wherein the first threshold value is 0.7.
5. The intelligent evaluation method for the assembly quality of the router shell according to claim 1, wherein the dividing the edge image according to the heat dissipation hole areas to obtain a plurality of heat dissipation hole sub-areas of the edge image comprises the following specific steps:
The minimum bounding rectangle determined every four adjacent louver areas is taken as the louver sub-areas of the edge image of the router housing, in order from left to right and top to bottom, starting from the upper left corner of the edge image of the router housing.
6. The method for intelligently evaluating the assembly quality of a router shell according to claim 1, wherein the steps of obtaining a plurality of cracks of each heat dissipation hole sub-area according to the gray value of the pixel point in the heat dissipation hole sub-area and the position of the heat dissipation hole area comprise the following specific steps:
And for any one of the radiating hole sub-areas, acquiring pixel points with the gray value of 0 in the radiating hole sub-area, and if the pixel points with the gray value of 0 do not belong to the radiating hole area in the radiating hole sub-area, taking the pixel points as crack pixel points of the radiating hole sub-area, acquiring all crack pixel points of the radiating hole sub-area, and acquiring a plurality of cracks of the radiating hole sub-area according to the continuous crack pixel points in the radiating hole sub-area.
7. The method for intelligently evaluating the assembly quality of a router shell according to claim 1, wherein the step of obtaining the potential influence degree of each end of each crack in each heat dissipation hole subarea on the heat dissipation hole area according to the approaching condition of the crack in the heat dissipation hole subarea to the similar heat dissipation hole area after the crack extends comprises the following specific steps:
The method comprises the steps of obtaining the shortest distance between a crack and the nearest radiating hole area in the extending direction of the end, marking the shortest distance as a first shortest distance, obtaining the included angle value between the extending direction of the crack and the horizontal right direction, wherein the included angle value is obtained by taking the horizontal right direction as 0 DEG, and the anticlockwise direction as the positive direction, obtaining the first included angle value between the extending direction of the crack and the nearest radiating hole area, and the specific obtaining method of the first included angle value comprises the steps of obtaining the tangent line of the last pixel point of the crack and the nearest radiating hole area in the extending direction of the end, taking the minimum included angle value between the extending direction of the crack and the tangent line as the first included angle value, multiplying the reciprocal of the first shortest distance, the reciprocal of the difference value of the included angle value and the first included angle value, and normalizing to obtain the potential influence degree of the crack in the radiating hole area on the radiating hole area.
8. The intelligent evaluation method for the assembly quality of the router shell according to claim 1, wherein the obtaining the quality index of each heat dissipation hole sub-area according to the number and the area of the cracks in the heat dissipation hole sub-area and the potential influence degree of each end of each crack on the heat dissipation hole area comprises the following specific steps:
For any one radiating hole sub-area, obtaining the average potential influence degree of the two ends of each crack of the radiating hole sub-area on the radiating hole area, taking the product of the reciprocal of the average potential influence degree and the reciprocal of the corresponding crack area as the weighted potential influence degree of the crack on the radiating hole area, and taking the product of the accumulated value of the weighted potential influence degree of all cracks in the radiating hole sub-area on the radiating hole area and the reciprocal of the crack number in the radiating hole sub-area as the quality index of the radiating hole sub-area.
9. The method for intelligently evaluating the assembly quality of the router shell according to claim 1, wherein the method for obtaining the assembly quality parameters of the router shell according to the quality index of the sub-areas of the radiating holes, the areas of the radiating holes in the edge image and the areas of the cracks in the edge image comprises the following specific steps:
And multiplying and normalizing the average value of the quality indexes of all the radiating hole sub-areas, the area ratio of the areas of all the radiating hole areas to the edge image and the reciprocal of the areas of all the cracks in the edge image to obtain the assembly quality parameter of the router shell.
10. The intelligent evaluation method for the assembly quality of the router shell according to claim 1, wherein the evaluation of the assembly quality of the router shell according to the magnitude of the assembly quality parameter comprises the following specific steps:
If the assembly quality parameter of the router shell is smaller than a preset second threshold value, the assembly quality of the router shell is unqualified, and if the assembly quality parameter of the router shell is larger than or equal to the preset second threshold value, the assembly quality of the router shell is qualified, wherein the second threshold value is 0.8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411230794.0A CN118735923B (en) | 2024-09-04 | 2024-09-04 | An intelligent evaluation method for the assembly quality of router housing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411230794.0A CN118735923B (en) | 2024-09-04 | 2024-09-04 | An intelligent evaluation method for the assembly quality of router housing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118735923A CN118735923A (en) | 2024-10-01 |
| CN118735923B true CN118735923B (en) | 2025-01-03 |
Family
ID=92849561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411230794.0A Active CN118735923B (en) | 2024-09-04 | 2024-09-04 | An intelligent evaluation method for the assembly quality of router housing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118735923B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197138A (en) * | 2023-11-07 | 2023-12-08 | 深圳市极摩客科技有限公司 | Computer host shell scratch detection method based on image characteristics |
| CN118014935A (en) * | 2024-01-04 | 2024-05-10 | 东莞市江霖五金实业有限公司 | Router shell production quality inspection method based on artificial intelligence |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7146057B2 (en) * | 2002-07-10 | 2006-12-05 | Northrop Grumman Corporation | System and method for image analysis using a chaincode |
| CN115880304B (en) * | 2023-03-08 | 2023-05-09 | 曲阜市巨力铁路轨道工程股份有限公司 | Pillow defect identification method based on complex scene |
-
2024
- 2024-09-04 CN CN202411230794.0A patent/CN118735923B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117197138A (en) * | 2023-11-07 | 2023-12-08 | 深圳市极摩客科技有限公司 | Computer host shell scratch detection method based on image characteristics |
| CN118014935A (en) * | 2024-01-04 | 2024-05-10 | 东莞市江霖五金实业有限公司 | Router shell production quality inspection method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118735923A (en) | 2024-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741356B (en) | Subpixel edge detection method and system | |
| CN110276284A (en) | Flame identification method, device, equipment and storage medium based on video quality assessment | |
| CN102799862A (en) | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image | |
| CN105469384B (en) | The integrated evaluating method of license plate image quality | |
| CN102306307B (en) | Positioning method of fixed point noise in color microscopic image sequence | |
| CN117197138B (en) | Computer host shell scratch detection method based on image characteristics | |
| JP4901229B2 (en) | Red-eye detection method, apparatus, and program | |
| CN116664567B (en) | Solid insulation switch cabinet quality assessment method and system | |
| CN111160477A (en) | Image template matching method based on feature point detection | |
| CN118735923B (en) | An intelligent evaluation method for the assembly quality of router housing | |
| CN113920065B (en) | Imaging quality evaluation method for visual detection system of industrial site | |
| CN118212478A (en) | Construction engineering quality detection method based on image processing | |
| CN118250445A (en) | Projector angle correction method and system | |
| CN108549889B (en) | A Simple Method of Printed Number Recognition | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| US9129356B2 (en) | Shotspot system | |
| US10958899B2 (en) | Evaluation of dynamic ranges of imaging devices | |
| CN115937263B (en) | Vision-based target tracking method, system, electronic device and storage medium | |
| CN119274002B (en) | Method for generating large-scale target detection data sample | |
| CN117152151B (en) | Motor shell quality detection method based on machine vision | |
| CN118823024B (en) | A method for identifying machining defects of air-cooled radiators | |
| CN114881911B (en) | Cigarette box detection method and system | |
| CN116681695B (en) | Quality detection method for anti-deformation template end face | |
| CN102810203A (en) | System and method for detecting unknown objects and events based on high-definition video surveillance images | |
| CN118172296B (en) | A fire source accurate positioning method based on image processing |
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 |