CN115861320A - Intelligent detection method for automobile part machining information - Google Patents
Intelligent detection method for automobile part machining information Download PDFInfo
- Publication number
- CN115861320A CN115861320A CN202310171997.6A CN202310171997A CN115861320A CN 115861320 A CN115861320 A CN 115861320A CN 202310171997 A CN202310171997 A CN 202310171997A CN 115861320 A CN115861320 A CN 115861320A
- Authority
- CN
- China
- Prior art keywords
- area
- target
- pixel points
- gray
- suspected defect
- 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
Images
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
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an intelligent detection method for automobile part processing information. The method obtains a gray image of the surface of the bearing after fluorescent magnetic powder injection; obtaining a suspected defect area in the gray level image through a watershed algorithm; acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, clustering the pixel points in each suspected defect area, and taking the area of a cluster where the target pixel points are located as a target area; acquiring the aggregation degree of the fluorescent magnetic powder of each target area according to the area of a suspected defect area corresponding to the target area and the position distribution and gradient distribution of pixel points in the target area; acquiring a gray difference between a target area and a gray image as a target difference; obtaining the similarity between the target area and the background area according to the difference between the fluorescent magnetic powder aggregation degree and the target; and determining a defect area in the gray-scale image according to the similarity. The efficiency of detecting the defective area is improved.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent detection method for automobile part processing information.
Background
The bearing is a very critical part in automobile parts, and the quality of the bearing is related to the running safety of an automobile. During the production and processing of the bearing, defects are generated due to overhigh forging heating temperature or overlong heat preservation time, and the grain boundary is oxidized or even melted when the defects are serious. The over-sintered bearing is forged under the defect state, and the defect part is torn to form larger defects by forging, punching and rolling of a heavy hammer.
In the prior art, a fluorescent magnetic powder method is usually adopted to detect defects on the surface of a bearing, fluorescent magnetic powder is attached to a defect area on the surface of the bearing to form a fluorescent area, and the fluorescent area can be segmented through a watershed algorithm commonly used in the field of image segmentation. However, the fine fluorescent magnetic powder is attached to the uneven part of the bearing surface to form a fluorescent region, so that when the segmentation is performed through a watershed algorithm, the area of a suspected defect region reserved after flooding is large due to the large fluorescent region, the suspected defect region not only comprises part of the uneven region without defects but also comprises a defect region, the segmented defect region is inaccurate, the identification of the defect region is interfered, and the detection of the defect region is not facilitated.
Disclosure of Invention
In order to solve the technical problem that the detection of a defect area is inaccurate due to the interference of an uneven area of a bearing on the defect area, the invention aims to provide an intelligent detection method for automobile part processing information, and the adopted technical scheme is as follows:
the embodiment of the invention provides an intelligent detection method for automobile part processing information, which comprises the following steps:
obtaining a gray image of the surface of the bearing after the fluorescent magnetic powder is sprayed;
obtaining a suspected defect area in the gray level image through a watershed algorithm; acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, clustering the pixel points in each suspected defect area, and taking the area of a cluster where the target pixel points are located as a target area;
acquiring the fluorescent magnetic powder aggregation degree of each target region according to the area of the suspected defect region corresponding to the target region and the position distribution and gradient distribution of pixel points in the target region;
acquiring a gray difference between the target area and the gray image as a target difference; obtaining the similarity between the target area and a background area according to the difference between the aggregation degree of the fluorescent magnetic powder and the target;
and combining the suspected defect area corresponding to the target area with the background area according to the similarity, and determining a defect area in the gray image.
Further, the method for obtaining the aggregation degree of the fluorescent magnetic powder comprises the following steps:
acquiring coordinates of pixel points corresponding to the maximum gray value in the target area as first coordinates, calculating the distance between the coordinates corresponding to each pixel point in the target area and the first coordinates, and acquiring the average distance between the pixel points in the target area; carrying out negative correlation mapping and normalization on the average distance, and taking the obtained result as a first result;
acquiring a gradient mean value of edge pixel points in the target area as an average gradient;
acquiring the number of pixel points in a suspected defect area corresponding to the target area, namely the area of the suspected defect area, as a first area;
calculating the product of the first result, the average gradient and the first area as the aggregation degree of the fluorescent magnetic powder in the target area.
Further, the method for acquiring the target difference comprises the following steps:
calculating an average gray value in the target region as a first value;
calculating an average gray value in the gray image as a second value;
and taking the difference value of the first value and the second value as the target difference between the target area and the gray scale image.
Further, the method for acquiring the similarity includes:
and performing negative correlation mapping on the product of the aggregation degree of the fluorescent magnetic powder and the target difference, and normalizing the result to be used as the similarity between the target area and the background area.
Further, the method for determining the defect area in the gray image according to the similarity comprises the following steps:
setting a similarity threshold, and merging the suspected defect area and the background area when the similarity is greater than the similarity threshold and the suspected defect area where the corresponding target area is located has no defect; the uncombined area is a defective area, and the defective area is checked.
Further, the method for clustering the pixel points in each suspected defect area includes:
and clustering the pixel points in the suspected defect area according to the positions and the gray values of the pixel points by using a DBSCAN density clustering algorithm.
The invention has the following beneficial effects:
a suspected defect area in the gray-scale image of the bearing surface is obtained through a watershed algorithm, and then only the suspected defect area is analyzed, so that the efficiency of detecting the defect area is improved; acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, so that the specific characteristics of the suspected defect areas can be conveniently analyzed subsequently; therefore, the pixel points in each suspected defect area are clustered, the area of the cluster where the target pixel points are located is used as the target area, the pixel points in the target area are the pixel points with a large gray value peak in the suspected defect area, and the attachment condition of the fluorescent magnetic powder in the corresponding suspected defect area can be reflected, so that the fluorescent magnetic powder aggregation degree of each target area is obtained according to the area of the suspected defect area corresponding to the target area and the position distribution and gradient distribution of the pixel points in the target area, and the defect area is preliminarily judged; in order to further determine the defect area, acquiring the gray difference between the target area and the gray image as the target difference, and indirectly determining the difference degree between the suspected defect area where the target area is located and the background area; and then the similarity between the target area and the background area is obtained according to the difference between the aggregation degree of the fluorescent magnetic powder and the target, the suspected defect area corresponding to the target area is merged with the background area according to the similarity, the interference on the detection of the defect area caused by the unevenness of the bearing surface is eliminated, the over-segmentation area caused by a watershed algorithm is eliminated, the defect area in the gray level image is determined, and the accuracy of the detection of the defect area is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of an intelligent detection method for processing information of an automobile part according to an embodiment of the present invention;
FIG. 2 is a graph showing gray scale values in a suspected defect area according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined object, the following detailed description of the method for intelligently detecting the machining information of the automobile parts, the specific implementation manner, the structure, the characteristics and the effects thereof according to the present invention are provided with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 describes a specific scheme of the intelligent detection method for the automobile part processing information provided by the invention in detail with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of an intelligent detection method for automobile part machining information according to an embodiment of the present invention is shown, where the method includes the following steps:
step S1: and obtaining a gray image of the surface of the bearing after the fluorescent magnetic powder is sprayed.
Specifically, the embodiment of the invention aims to detect the defects on the surface of the bearing by a fluorescent magnetic powder method, and the method comprises the steps of firstly spraying a certain amount of fluorescent magnetic powder on the surface of the bearing by using a seifu flaw detector, then collecting an image of the surface of the bearing after spraying the fluorescent magnetic powder by using a high-definition camera, and denoising the obtained image.
The mean filtering algorithm and the graying process are both in the prior art, and are not described herein again.
Step S2: obtaining a suspected defect area in the gray level image through a watershed algorithm; and acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, clustering the pixel points in each suspected defect area, and taking the area of the clustering cluster where the target pixel points are located as a target area.
Specifically, the surface of the bearing is marked by a fluorescent magnetic powder method, different bright and dark areas can be formed by different planeness of the surface of the bearing, for example, when the concave-convex degree of the surface of the bearing is large, fine fluorescent magnetic powder can be attached to the uneven part of the surface of the bearing to form an integral fluorescent area; the defect on the surface of the bearing is that the metal grain boundary of the lower surface layer is oxidized and cracked to present a sharp angle under microscopic observation, if the segregation of the internal components of the metal is serious, the grain boundary also begins to melt, a sharp-angle-shaped cave can be formed when the segregation is serious, fluorescent magnetic powder can be adsorbed in a defect area, and an integral fluorescent area is also formed. The fluorescence area in the bearing surface is analyzed, and when the fluorescence area is larger and brighter, the fluorescence area is more likely to be a larger uneven area or a defect area in the bearing surface. The gray value corresponding to the fluorescence area in the gray image is large, the gray value corresponding to the background area except the fluorescence area is small, and the initial segmentation area in the gray image, namely the suspected defect area, is obtained through a watershed algorithm. The watershed algorithm finds a minimum value in the gray-scale image, then starts to expand, and if too many minimum regions exist in the gray-scale image and many small catchment basins are generated, the gray-scale image is over-segmented. Therefore, when segmentation is performed through a watershed algorithm, the area of a suspected defect area reserved after flooding is large due to the fact that the fluorescence area is large, the suspected defect area comprises an uneven area without defects and a defect area, and the segmented defect area is inaccurate. Therefore, the obtained suspected defect area needs to be processed to remove the suspected defect area without the defect, and then the remaining suspected defect area is identified to determine the defect area. According to the embodiment of the invention, the water logging position of the watershed algorithm is optimized according to the characteristics of the defect area, the optimal water logging position is obtained, and the interference of the uneven area without defects, which is caused by marking fluorescent magnetic powder, is removed, so that the reserved suspected defect area is the defect area.
The watershed algorithm is a well-known technique, and will not be described in detail here.
The suspected defect areas obtained by the watershed algorithm are directly judged according to a threshold value, and which suspected defect areas are uneven areas and defect areas cannot be distinguished, so that specific characteristics of each suspected defect area need to be analyzed to combine the suspected defect areas, the suspected defect areas belonging to normal uneven areas are combined with a background area, that is, when the suspected defect areas are segmented by the watershed algorithm, not only a 'flooding' process but also the suspected defect areas need to be judged, and the suspected defect areas belonging to normal uneven areas also become 'flooded' objects.
Analyzing the specific characteristics of the suspected defect areas, wherein a target area in each suspected defect area needs to be acquired first, and the specific operation of acquiring the target area is as follows:
and obtaining the pixel point corresponding to the maximum gray value in each suspected defect area as a target pixel point, and if at least two pixel points corresponding to the maximum gray value in one suspected defect area are obtained, randomly selecting one pixel point corresponding to the maximum gray value as the target pixel point. And clustering the pixel points in the suspected defect area according to the positions and the gray values of the pixel points by using a DBSCAN density clustering algorithm, wherein the DBSCAN density clustering algorithm is used for clustering according to the positions of the pixel points, and selecting which pixel points are clustering objects according to the gray values. And acquiring the region of the clustering cluster where the target pixel point is located as a target region. The embodiment of the invention sets the neighborhood radius in the DBSCAN density clustering algorithm to be 3, sets the minimum neighborhood pixel number to be 3, and sets the threshold value to be an empirical threshold value, so that an implementer can set the threshold value according to different implementation environments. The DBSCAN density clustering algorithm is a known technology, and will not be described in detail here.
The reason for taking the region of the cluster where the target pixel point is located as the target region is as follows:
the fluorescent magnetic powder attached to the defect area is more and uniform, so that the whole gray value of the defect area is larger and the gray level fluctuation is larger; the gray values of the pixels in the defect region are distributed as in a region B in fig. 2, and the height of each peak in the region B is the gray value of the corresponding pixel in the defect region; the rough area of the bearing surface has a background area between suspected defect areas formed by attaching fluorescent magnetic powder, so that the distance between peaks in corresponding gray distribution is large, the gray value peaks in the suspected defect areas corresponding to the rough area are uneven, and the gray fluctuation of pixel points is large or small, such as the area a in fig. 2, wherein each peak value in the area a is the gray value of the corresponding pixel point in the corresponding suspected defect area. According to fig. 2, it can be found that the distribution characteristics of peaks between the suspected defect region and the defect region corresponding to the uneven region are greatly different, the distance between the peaks in the region a is large, and the peak value has a high value or a low value; the peaks in the region B are dense and large, after the watershed algorithm is carried out, partial peaks in the region A are smaller than a threshold value and cannot be segmented, the peaks in the region B are larger than a segmentation threshold value and can be segmented, and the fluorescent magnetic powder aggregation degree of the peaks in the region B is large. Therefore, the suspected defect region having a larger degree of aggregation of the fluorescent magnetic powder is more likely to be a defect region. The cluster where the target pixel points are located can sufficiently reflect the distribution of high gray value peaks in the corresponding suspected defect area, so that the area of the cluster where the target pixel points are located is selected as a target area, and the target area is analyzed. Because the distribution of the gray value peaks in the area A and the area B is different, the number of the pixels in the target area corresponding to each suspected defect area after clustering is different, and the distribution of the pixels is also different, so that the fluorescent magnetic powder aggregation degree of each target area is obtained according to the number and the distribution of the pixels in the target area.
And step S3: and acquiring the fluorescent magnetic powder aggregation degree of each target area according to the area of the suspected defect area corresponding to the target area and the position distribution and gradient distribution of the pixel points in the target area.
Specifically, the fluorescent regions generated by the uneven regions of the bearing surface interfere with the identification of the defective regions, and the fluorescent regions and the defective regions without defects cannot be accurately distinguished only by means of gray scale distribution. However, since there is a possibility that a defect exists in a region marked with a fluorescence, a suspected defect region is obtained by dividing the fluorescence region in the gray-scale image, and then the suspected defect region is analyzed to obtain an accurate defect region.
And analyzing the suspected defect area, combining the suspected defect area without the defect with the background area, and taking the finally divided area as the defect area. Step S2 shows that the suspected defect area can be preliminarily analyzed according to the aggregation degree of the fluorescent magnetic powder in the target area.
Preferably, the method for obtaining the aggregation degree of the fluorescent magnetic powder comprises the following steps: acquiring coordinates of pixel points corresponding to the maximum gray value in the target area as first coordinates, calculating the distance between the coordinates corresponding to each pixel point in the target area and the first coordinates, and acquiring the average distance between the pixel points in the target area; carrying out negative correlation mapping and normalization on the average distance, and taking the obtained result as a first result; acquiring a gradient mean value of edge pixel points in a target area as an average gradient; acquiring the number of pixel points in a suspected defect area corresponding to a target area, namely the area of the suspected defect area, as a first area; the product of the first result, the average gradient and the first area is calculated as the degree of aggregation of the fluorescent magnetic powder in the target region.
It should be noted that, a fluorescence region caused by unevenness on the bearing surface is segmented by a watershed algorithm, and then only a region with obvious fluorescence is reserved, and a region with unobvious fluorescence is segmented into a background region; the remaining area of the defect area after being divided by the watershed algorithm is larger, so that the number of pixels with larger gray values in the defect area is larger, the pixels with larger gray values are the peak value points of each peak in the area B in fig. 2, the corresponding pixels in the target area are pixels which are close to the peak value of the maximum peak value point in the corresponding suspected defect area, and the corresponding pixels on the bearing surface are a certain larger defect area. The aggregation degree of the fluorescent magnetic powder in the target area is represented by calculating the average distance of the pixel points in the target area, and the larger the aggregation degree of the fluorescent magnetic powder is, the larger the possible degree that a suspected defect area corresponding to the target area is a defect area is. The gradient change of the edge pixel points is used for correcting the clustering result, the density clustering result not only clusters the pixel points close to the peak value into one type, but also clusters the regions corresponding to the clustering pixel points into one type, the peaks of the defect regions are gathered and the gray value is larger, and the larger the gradient of the edge pixel points is, the more obvious the edge characteristics generated by gathering the fluorescent magnetic powder in the region is, the larger the gathering degree of the fluorescent magnetic powder is. After clustering, different peaks are clustered into a region, namely a target region, so that the larger the area of the target region is, namely the more the number of pixel points in the target region is, the more the fluorescent magnetic powder at the corresponding position of the target region is clustered, the larger the clustering degree of the fluorescent magnetic powder is, and the larger the possible degree of the corresponding suspected defect region being a defect region is.
After the segmentation is carried out through the watershed algorithm, each suspected defect area is equivalent to an isolated area, the number of pixels in the suspected defect area corresponding to the defect area is certainly large, the suspected defect area with the large number of pixels is larger in probability of being the defect area, the suspected defect area which is segmented out due to unevenness and does not have defects is equivalent to scattered points, the number of pixels in the corresponding suspected defect area is small, and the probability that the suspected defect area is the defect area is smaller. Therefore, the number of the pixels in the suspected defect area, namely the area of the suspected defect area, is used as a component for calculating the aggregation degree of the fluorescent magnetic powder.
As an example, taking the target area j as an example, the coordinates of the pixel point corresponding to the maximum gray value in the target area j are obtained as the first coordinates, and if there are at least two pixel points corresponding to the maximum gray value in the target area j, the coordinates of one pixel point are arbitrarily selected as the first coordinates. And obtaining the distance between each pixel point in the target area j and the pixel point corresponding to the first coordinate according to the coordinate of each pixel point in the target area j. By passing
The operator obtains the gradient of each pixel point in the target area j and obtains the gradient of the edge pixel point at the boundary of the area, wherein,
operators are well known technology and will not be described in detail herein. Acquiring the fluorescent magnetic powder aggregation degree of the target region j according to the distance between each pixel point in the target region j and the pixel point corresponding to the first coordinate and the gradient of each pixel point, and acquiring the fluorescent magnetic powder aggregation degree of the target region j
The formula of (1) is:
wherein the content of the first and second substances,
the aggregation degree of the fluorescent magnetic powder in the target area j;
the number of pixel points in the target region j;
the coordinate of the pixel point corresponding to the maximum gray value in the target area j is a first coordinate;
is the number one in the target region j
Coordinates of the individual pixel points;
is the number one in the target region j
The gradient of each edge pixel point;
the area of the suspected defect area where the target area j is located is a first area;
is a natural constant.
It should be noted that the average distance
The smaller the size, the more concentrated the position distribution of the pixel points in the target area j is,
the larger; mean gradient
The larger the gray scale change is, the larger the gray scale change of the edge pixel points in the target region j is, so that the edge characteristics generated by the fluorescent magnetic powder aggregation are more obvious,
the larger;
the larger the area is, the larger the area of the suspected defect area where the target area j is located is, that is, the more the number of the pixel points is, the more the pixel points which meet the clustering condition are, the better the clustering effect is,
the larger; therefore, the temperature of the molten metal is controlled,
the larger the size is, the higher the aggregation degree of the fluorescent magnetic powder of the target region j is, and the more likely the suspected defect region in which the target region j is located is to be a defect region.
And acquiring the aggregation degree of the fluorescent magnetic powder of each target area according to the method for acquiring the aggregation degree of the fluorescent magnetic powder of the target area j. The larger the aggregation degree of the fluorescent magnetic powder in the target region is, the more uneven the target region is, and the more uneven region is marked by a fluorescent magnetic powder method, so that the marking effect is more obvious; the smaller the degree of aggregation of the fluorescent magnetic powder in the target region, the more the target region is a normal region remaining due to the unevenness of the bearing surface. The correlation of the target region is judged to be inaccurate through the position of the pixel point, the clustering result needs to be corrected according to the gradient change between peaks, and whether the corresponding suspected defect region can be merged with the background region is judged according to the aggregation degree of the fluorescent magnetic powder of each target region.
And step S4: acquiring a gray difference between the target area and the gray image as a target difference; and obtaining the similarity between the target area and the background area according to the difference between the fluorescent magnetic powder aggregation degree and the target.
Specifically, in order to determine the optimal water flooding position of the watershed algorithm, a suspected defect area without a defect is merged with a background area to further obtain an accurate defect area, and the similarity between the target area and the background area is obtained according to the fluorescent magnetic powder aggregation degree of the target area.
Preferably, the method for obtaining the similarity between the target area and the background area comprises: calculating an average gray value in the target region as a first value; calculating the average gray value in the gray image as a second value; and taking the difference value of the first value and the second value as the target difference between the target area and the gray scale image. And performing negative correlation mapping on the product of the fluorescent magnetic powder aggregation degree and the target difference and normalizing the result to be used as the similarity between the target area and the background area.
It should be noted that, by calculating the similarity between the suspected defect area and the background area, the suspected defect area with a large similarity is merged with the background area, so as to eliminate part of the suspected defect area which does not have defects but affects the judgment of the defect area. When segmentation is carried out through a watershed algorithm, excessive interference of suspected defect areas without defects is avoided, and the segmentation of the defect areas in the gray-scale image is more accurate.
As an example, taking the target area j in step S3 as an example, according to the gray value of each pixel point in the target area j, obtaining an average gray value of the target area j, that is, a first value; according to the gray value of each pixel point in the gray image, the average gray value of the gray image, namely the second value, is obtained, because the pixel points in the target area j are all the pixel points marked by the fluorescent magnetic powder, the gray value is larger, namely the first value is larger, and the pixel points in the gray image also comprise the pixel points in the background area, therefore, the second value is smaller than the first value, and the difference value between the first value and the second value, namely the target difference, is a positive number. Obtaining the target difference of the target area j
The formula of (1) is:
wherein the content of the first and second substances,
the target difference between the target area j and the gray level image;
the average gray value of the target area j is a first value;
the number of pixel points in the gray level image is calculated;
is the first in a gray scale image
The gray value of each pixel point.
It should be noted that, in the following description,
the larger the difference between the average gradation value of the target region j and the average gradation value of the gradation image is; marking by a fluorescent magnetic powder method, wherein the gray value of the defect area is larger than that of the normal area, and the larger the gray value is, the more obvious the defect is; therefore, the temperature of the molten metal is controlled,
the larger the difference between the target region j and the background region is.
According to the aggregation degree of fluorescent magnetic powder
Difference from target
Obtaining the similarity between the target area j and the background area
The formula of (1) is:
wherein the content of the first and second substances,
similarity of the target area j and the background area is obtained;
the aggregation degree of the fluorescent magnetic powder in the target region j;
is the target difference for target region j;
are natural constants.
It should be noted that, in the following description,
the larger the size, the more likely the suspected defect area in which the target area j is located is to be a defect area,
the smaller;
the larger the difference between the gray value in the target region j and the gray value in the background region, the more dissimilar the target region j and the background region, the more likely the target region j is a defective region,
the smaller; therefore, the temperature of the molten metal is controlled,
the smaller the size, the less similar the target area j is to the background area, and the more likely the suspected defect area in which the target area j is located is to be a defect area.
And according to the method for acquiring the similarity between the target area j and the background area, acquiring the similarity between each target area and the background area. And setting a proper segmentation threshold value in the watershed algorithm according to the similarity, so that the final segmentation region is a defect region.
Step S5: and combining the suspected defect area corresponding to the target area with the background area according to the similarity, and determining the defect area in the gray image.
Setting a similarity threshold, and merging the suspected defect area and the background area when the similarity is greater than the similarity threshold and the suspected defect area where the corresponding target area is located has no defect; the uncombined area is a defective area, and the defective area is checked.
The embodiment of the invention sets the similarity threshold value to be 0.32, and an implementer can adjust the similarity according to different actual conditions. When the similarity is larger than the similarity threshold, the similarity between the target area and the background area is high, the suspected defect area where the target area is located has no defect, the suspected defect area and the background area are merged, and the suspected defect area cannot be segmented when the gray level image is segmented through a watershed algorithm.
After the suspected defect areas are combined, the suspected defect areas without defects are eliminated, the remaining unconjugated suspected defect areas are the defect areas, the defect areas are marked, manual verification of the defect areas is facilitated, and the defect detection efficiency is improved.
The present embodiment is thus completed.
In summary, the embodiment of the invention obtains the gray image of the bearing surface after the fluorescent magnetic powder is sprayed; obtaining a suspected defect area in the gray level image through a watershed algorithm; acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, clustering the pixel points in each suspected defect area, and taking the area of a cluster where the target pixel points are located as a target area; acquiring the aggregation degree of the fluorescent magnetic powder of each target area according to the area of a suspected defect area corresponding to the target area and the position distribution and gradient distribution of pixel points in the target area; acquiring a gray difference between a target area and a gray image as a target difference; acquiring the similarity between a target area and a background area according to the difference between the fluorescent magnetic powder aggregation degree and the target; and determining a defect area in the gray-scale image according to the similarity. The efficiency of detecting the defective area is improved.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
Claims (6)
1. An intelligent detection method for automobile part machining information is characterized by comprising the following steps:
obtaining a gray image of the surface of the bearing after the fluorescent magnetic powder is sprayed;
obtaining a suspected defect area in the gray image through a watershed algorithm; acquiring pixel points corresponding to the maximum gray value in each suspected defect area as target pixel points, clustering the pixel points in each suspected defect area, and taking the area of a cluster where the target pixel points are located as a target area;
acquiring the fluorescent magnetic powder aggregation degree of each target region according to the area of the suspected defect region corresponding to the target region and the position distribution and gradient distribution of pixel points in the target region;
acquiring a gray difference between the target area and the gray image as a target difference; obtaining the similarity between the target area and a background area according to the difference between the aggregation degree of the fluorescent magnetic powder and the target;
and combining the suspected defect area corresponding to the target area with the background area according to the similarity, and determining a defect area in the gray image.
2. The method for intelligently detecting the machining information of the automobile parts according to claim 1, wherein the method for acquiring the aggregation degree of the fluorescent magnetic powder comprises the following steps:
acquiring coordinates of pixel points corresponding to the maximum gray value in the target area as first coordinates, calculating the distance between the coordinates corresponding to each pixel point in the target area and the first coordinates, and acquiring the average distance between the pixel points in the target area; carrying out negative correlation mapping and normalization on the average distance, and taking the obtained result as a first result;
acquiring a gradient mean value of edge pixel points in the target area as an average gradient;
acquiring the number of pixel points in a suspected defect area corresponding to the target area, namely the area of the suspected defect area, as a first area;
calculating the product of the first result, the average gradient and the first area as the aggregation degree of the fluorescent magnetic powder in the target area.
3. The intelligent detection method for the automobile part machining information as claimed in claim 1, wherein the method for acquiring the target difference comprises the following steps:
calculating an average gray value in the target region as a first value;
calculating an average gray value in the gray image as a second value;
and taking the difference value of the first value and the second value as the target difference between the target area and the gray scale image.
4. The intelligent detection method for the automobile part machining information as claimed in claim 1, wherein the method for obtaining the similarity comprises the following steps:
and performing negative correlation mapping on the product of the fluorescent magnetic powder aggregation degree and the target difference and normalizing the result to be used as the similarity between the target area and the background area.
5. The method for intelligently detecting the machining information of the automobile parts as claimed in claim 1, wherein the method for determining the defect area in the gray image according to the similarity comprises the following steps:
setting a similarity threshold, and merging the suspected defect area and the background area when the similarity is greater than the similarity threshold and the suspected defect area where the corresponding target area is located has no defect; the non-merged area is a defective area, and the defective area is verified.
6. The method for intelligently detecting the machining information of the automobile parts as claimed in claim 1, wherein the method for clustering the pixel points in each suspected defect area comprises the following steps:
and clustering the pixel points in the suspected defect area according to the positions and the gray values of the pixel points by using a DBSCAN density clustering algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310171997.6A CN115861320B (en) | 2023-02-28 | 2023-02-28 | Intelligent detection method for automobile part machining information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310171997.6A CN115861320B (en) | 2023-02-28 | 2023-02-28 | Intelligent detection method for automobile part machining information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115861320A true CN115861320A (en) | 2023-03-28 |
| CN115861320B CN115861320B (en) | 2023-05-12 |
Family
ID=85659149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310171997.6A Active CN115861320B (en) | 2023-02-28 | 2023-02-28 | Intelligent detection method for automobile part machining information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861320B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116091499A (en) * | 2023-04-07 | 2023-05-09 | 山东中胜涂料有限公司 | Abnormal paint production identification system |
| CN116630815A (en) * | 2023-07-25 | 2023-08-22 | 济南玖通志恒信息技术有限公司 | Intelligent agricultural pest detection method |
| CN116990993A (en) * | 2023-09-26 | 2023-11-03 | 深圳市柯达科电子科技有限公司 | LCD display panel quality detection method |
| CN117291937A (en) * | 2023-11-27 | 2023-12-26 | 山东嘉达装配式建筑科技有限责任公司 | Automatic plastering effect visual detection system based on image feature analysis |
| CN118115499A (en) * | 2024-04-29 | 2024-05-31 | 深圳市金利源绝缘材料有限公司 | Visual detection method for production quality of electric power copper bar |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101168474A (en) * | 2006-10-27 | 2008-04-30 | 群康科技(深圳)有限公司 | Method for manufacturing polycrystalline silicon thin film at low temperature |
| CN103955913A (en) * | 2014-02-18 | 2014-07-30 | 西安电子科技大学 | SAR image segmentation method based on line segment co-occurrence matrix characteristics and regional maps |
| CN107145896A (en) * | 2017-03-14 | 2017-09-08 | 西南科技大学 | Dysnusia identifying system based on fluorescentmagnetic particle(powder) |
| CN107292882A (en) * | 2017-08-02 | 2017-10-24 | 国网电力科学研究院武汉南瑞有限责任公司 | One kind is based on the adaptive electrical equipment malfunction detection methods of Meanshift |
| CN108595596A (en) * | 2018-04-19 | 2018-09-28 | 厦门启尚科技有限公司 | A kind of image similarity search method |
| CN108629783A (en) * | 2018-05-02 | 2018-10-09 | 山东师范大学 | Image partition method, system and medium based on the search of characteristics of image density peaks |
| CN109215020A (en) * | 2018-08-30 | 2019-01-15 | 国网黑龙江省电力有限公司佳木斯供电公司 | Ultra-high-tension power transmission line fault recognition method based on computer vision |
| CN110177532A (en) * | 2017-01-22 | 2019-08-27 | 四川金瑞麒智能科学技术有限公司 | A kind of intelligent wheelchair system based on big data and artificial intelligence |
| CN110706236A (en) * | 2019-09-03 | 2020-01-17 | 西人马帝言(北京)科技有限公司 | Three-dimensional reconstruction method and device of blood vessel image |
| CN112131924A (en) * | 2020-07-10 | 2020-12-25 | 国网河北省电力有限公司雄安新区供电公司 | Transformer substation equipment image identification method based on density cluster analysis |
| CN112906550A (en) * | 2021-02-09 | 2021-06-04 | 哈尔滨理工大学 | Static gesture recognition method based on watershed transformation |
| CN113642631A (en) * | 2021-08-10 | 2021-11-12 | 沭阳协润电子有限公司 | Dangerous area electronic fence generation method and system based on artificial intelligence |
| CN114581692A (en) * | 2022-03-06 | 2022-06-03 | 扬州孚泰电气有限公司 | Vibration damper fault detection method and system based on intelligent pattern recognition |
| CN115100212A (en) * | 2022-08-29 | 2022-09-23 | 卡松科技股份有限公司 | Method for detecting pollution degree of lubricating oil |
| CN115351598A (en) * | 2022-10-17 | 2022-11-18 | 南通钜德智能科技有限公司 | Numerical control machine tool bearing detection method |
-
2023
- 2023-02-28 CN CN202310171997.6A patent/CN115861320B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101168474A (en) * | 2006-10-27 | 2008-04-30 | 群康科技(深圳)有限公司 | Method for manufacturing polycrystalline silicon thin film at low temperature |
| CN103955913A (en) * | 2014-02-18 | 2014-07-30 | 西安电子科技大学 | SAR image segmentation method based on line segment co-occurrence matrix characteristics and regional maps |
| CN110177532A (en) * | 2017-01-22 | 2019-08-27 | 四川金瑞麒智能科学技术有限公司 | A kind of intelligent wheelchair system based on big data and artificial intelligence |
| CN107145896A (en) * | 2017-03-14 | 2017-09-08 | 西南科技大学 | Dysnusia identifying system based on fluorescentmagnetic particle(powder) |
| CN107292882A (en) * | 2017-08-02 | 2017-10-24 | 国网电力科学研究院武汉南瑞有限责任公司 | One kind is based on the adaptive electrical equipment malfunction detection methods of Meanshift |
| CN108595596A (en) * | 2018-04-19 | 2018-09-28 | 厦门启尚科技有限公司 | A kind of image similarity search method |
| CN108629783A (en) * | 2018-05-02 | 2018-10-09 | 山东师范大学 | Image partition method, system and medium based on the search of characteristics of image density peaks |
| CN109215020A (en) * | 2018-08-30 | 2019-01-15 | 国网黑龙江省电力有限公司佳木斯供电公司 | Ultra-high-tension power transmission line fault recognition method based on computer vision |
| CN110706236A (en) * | 2019-09-03 | 2020-01-17 | 西人马帝言(北京)科技有限公司 | Three-dimensional reconstruction method and device of blood vessel image |
| CN112131924A (en) * | 2020-07-10 | 2020-12-25 | 国网河北省电力有限公司雄安新区供电公司 | Transformer substation equipment image identification method based on density cluster analysis |
| CN112906550A (en) * | 2021-02-09 | 2021-06-04 | 哈尔滨理工大学 | Static gesture recognition method based on watershed transformation |
| CN113642631A (en) * | 2021-08-10 | 2021-11-12 | 沭阳协润电子有限公司 | Dangerous area electronic fence generation method and system based on artificial intelligence |
| CN114581692A (en) * | 2022-03-06 | 2022-06-03 | 扬州孚泰电气有限公司 | Vibration damper fault detection method and system based on intelligent pattern recognition |
| CN115100212A (en) * | 2022-08-29 | 2022-09-23 | 卡松科技股份有限公司 | Method for detecting pollution degree of lubricating oil |
| CN115351598A (en) * | 2022-10-17 | 2022-11-18 | 南通钜德智能科技有限公司 | Numerical control machine tool bearing detection method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116091499A (en) * | 2023-04-07 | 2023-05-09 | 山东中胜涂料有限公司 | Abnormal paint production identification system |
| CN116630815A (en) * | 2023-07-25 | 2023-08-22 | 济南玖通志恒信息技术有限公司 | Intelligent agricultural pest detection method |
| CN116630815B (en) * | 2023-07-25 | 2023-09-22 | 济南玖通志恒信息技术有限公司 | Intelligent agricultural pest detection method |
| CN116990993A (en) * | 2023-09-26 | 2023-11-03 | 深圳市柯达科电子科技有限公司 | LCD display panel quality detection method |
| CN116990993B (en) * | 2023-09-26 | 2023-12-22 | 深圳市柯达科电子科技有限公司 | LCD display panel quality detection method |
| CN117291937A (en) * | 2023-11-27 | 2023-12-26 | 山东嘉达装配式建筑科技有限责任公司 | Automatic plastering effect visual detection system based on image feature analysis |
| CN117291937B (en) * | 2023-11-27 | 2024-03-05 | 山东嘉达装配式建筑科技有限责任公司 | Automatic plastering effect visual detection system based on image feature analysis |
| CN118115499A (en) * | 2024-04-29 | 2024-05-31 | 深圳市金利源绝缘材料有限公司 | Visual detection method for production quality of electric power copper bar |
| CN118115499B (en) * | 2024-04-29 | 2024-07-12 | 深圳市金利源绝缘材料有限公司 | Visual detection method for production quality of electric power copper bar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115861320B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115861320A (en) | Intelligent detection method for automobile part machining information | |
| CN115311292B (en) | Strip steel surface defect detection method and system based on image processing | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN114723701B (en) | Gear defect detection method and system based on computer vision | |
| CN107437243B (en) | Tire impurity detection method and device based on X-ray image | |
| CN115601367A (en) | LED lamp wick defect detection method | |
| CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN115984284B (en) | X-ray ship body weld image detection method for ship maintenance | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| CN115829883A (en) | Surface image denoising method for dissimilar metal structural member | |
| CN115294159B (en) | Method for dividing corroded area of metal fastener | |
| CN115272321B (en) | Textile defect detection method based on machine vision | |
| CN115690108A (en) | Aluminum alloy rod production quality evaluation method based on image processing | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN115294140A (en) | Hardware part defect detection method and system | |
| CN115082466B (en) | PCB surface welding spot defect detection method and system | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
| CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
| CN1702684A (en) | Strong noise image characteristic points automatic extraction method | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN115274486B (en) | Semiconductor surface defect identification method | |
| CN115049651B (en) | Metal plate stamping abnormity detection method | |
| CN107516315B (en) | Tunneling machine slag tapping monitoring method based on machine vision |
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 |