CN111462074A - Bearing appearance detection method, device and system, computer equipment and storage medium - Google Patents
Bearing appearance detection method, device and system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111462074A CN111462074A CN202010241842.1A CN202010241842A CN111462074A CN 111462074 A CN111462074 A CN 111462074A CN 202010241842 A CN202010241842 A CN 202010241842A CN 111462074 A CN111462074 A CN 111462074A
- Authority
- CN
- China
- Prior art keywords
- gray
- bearing
- image
- preset
- appearance
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 152
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 239000000463 material Substances 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000007689 inspection Methods 0.000 claims abstract description 28
- 238000005520 cutting process Methods 0.000 claims abstract description 25
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 27
- 238000005086 pumping Methods 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 5
- 230000002411 adverse Effects 0.000 abstract description 6
- 230000002950 deficient Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000012856 packing Methods 0.000 description 5
- 239000003086 colorant Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011324 bead Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Images
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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The application relates to a bearing appearance detection method, a device, a system, computer equipment and a storage medium, which realize the appearance gray level image acquisition operation of a bearing according to an image acquisition device, and then analyze whether the bearing is provided with materials according to the appearance gray level image, namely, detect whether the bearing is provided with balls. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
Description
Technical Field
The present disclosure relates to the field of automatic detection technologies, and in particular, to a method, an apparatus, a system, a computer device, and a storage medium for detecting an appearance of a bearing.
Background
The bearing is an important part for supporting a mechanical rotating body, and is widely applied to mechanical equipment. The bearing machine is equipment for assembling and processing the bearing, and when the bearing machine is used, if the ball assembly of the bearing is abnormal, the subsequent station cannot be carried out, and the bearing machine is easy to abnormally stop frequently. Therefore, the normal assembly of the balls is particularly important in the use process of the bearing machine.
In the use of the bearing machine, whether the ball is normally assembled or not is normally detected by a worker, so that the normal operation of a subsequent station can be ensured. A large amount of human resources can be wasted in a traditional bearing appearance detection mode, and the error rate of manual detection is high. Therefore, the traditional bearing appearance detection mode has the defect of low detection reliability.
Disclosure of Invention
In view of the above, it is necessary to provide a bearing appearance detection method, device, system, computer device, and storage medium for solving the problem of low detection reliability of the conventional bearing appearance detection method.
A bearing appearance detection method comprises the following steps: analyzing whether the bearing is provided with materials or not according to an appearance gray image of the bearing, wherein the appearance gray image is obtained by carrying out image acquisition on the bearing through an image acquisition device; when the bearing is filled with materials, cutting the corresponding position of the appearance gray image according to a preset rectangular area to obtain a gray image of an interested area; and segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
A bearing appearance inspection device, comprising: the material analysis module is used for analyzing whether the bearing is provided with materials or not according to an appearance gray level image of the bearing, and the appearance gray level image is obtained by carrying out image acquisition on the bearing through an image acquisition device; the interested region obtaining module is used for cutting the corresponding position of the appearance gray image according to a preset rectangular region when the bearing is filled with materials to obtain an interested region gray image; and the detection analysis module is used for segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
The bearing appearance detection system comprises an image acquisition device and a bearing detector, wherein the image acquisition device is connected with the bearing detector, the image acquisition device is used for carrying out image acquisition on a bearing to obtain a corresponding appearance gray-scale image, and the bearing detector is used for carrying out bearing appearance detection according to the method.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the bearing appearance detection method, the bearing appearance detection device, the bearing appearance detection system, the computer equipment and the storage medium, the appearance gray level image acquisition operation of the bearing is realized according to the image acquisition device, and then whether the bearing is filled or not is analyzed according to the appearance gray level image, namely whether the bearing is filled with balls or not is detected. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, can remove the manual detection in later stage to realize the unmanned automated production of the whole flow of equipment packing. This scheme is disposable to detect multiple bad to definite classification, the problem of the analysis equipment of being convenient for, detection efficiency is high simultaneously, and the beat is less than 0.2S/piece, and the outward appearance that can compatible different kinds of ball detects, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for detecting the appearance of a bearing according to an embodiment;
FIG. 2 is a diagram illustrating an image acquisition method according to an embodiment;
FIG. 3 is a schematic view of a material free ash level of a bearing according to an embodiment;
FIG. 4 is a schematic view of the bearing material ash level in one embodiment;
FIG. 5 is a schematic diagram illustrating a gray scale of a region of interest in an embodiment;
FIG. 6 is a schematic diagram illustrating the divided gray scales in an embodiment;
FIG. 7 is a schematic view of a bearing appearance inspection method according to another embodiment;
FIG. 8 is a schematic view of a bearing appearance inspection method according to yet another embodiment;
FIG. 9 is a flow diagram illustrating a post-segmentation image analysis process according to an embodiment;
FIG. 10 is a flowchart illustrating an exemplary bearing appearance inspection process;
FIG. 11 is a schematic view of an embodiment of a ball bearing assembly;
FIG. 12 is a schematic view of an embodiment of a ball assembly;
FIG. 13 is a schematic view of a ball bearing in an embodiment of the present invention;
FIG. 14 is a schematic view of an embodiment of a ball loader without pumping oil;
FIG. 15 is a schematic diagram of ball reverse oiling in one embodiment;
FIG. 16 is a schematic diagram illustrating that each inspection of the balls is acceptable in one embodiment;
FIG. 17 is a schematic diagram illustrating a post-segmentation image analysis process in another embodiment;
FIG. 18 is a flow diagram illustrating a connected component analysis process according to an embodiment;
FIG. 19 is a schematic view of an embodiment of a bearing appearance inspection device;
FIG. 20 is a schematic diagram of a bearing appearance inspection system in accordance with an embodiment;
FIG. 21 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present application are illustrated in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Referring to fig. 1, a bearing appearance detecting method includes steps S100, S200, and S400.
And S100, analyzing whether the bearing is filled according to the appearance gray level image of the bearing.
Specifically, the appearance gray level image is obtained by image acquisition of the bearing through an image acquisition device. A grayscale image is a grayscale digital image, which is an image with only one sample color per pixel. Such images are typically displayed in gray scale from darkest black to brightest white, although in theory this sampling could be of different shades of any color and even different colors at different brightnesses. The gray image is different from the black and white image, the black and white image only has two colors of black and white in the field of computer image, the gray image has a plurality of levels of color depth between black and white, and the white and the black can be divided into 256 levels according to a logarithmic relation. The gray processing is to perform graying on the color image, and specifically, a component method, a maximum value method, an average value method, a weighted average method and the like may be adopted, the appearance gray image is an image obtained after performing gray processing on the appearance image of the bearing, the image acquisition device may acquire a general image (i.e., a color image) of the bearing first, and then perform gray processing, so as to obtain a corresponding appearance gray image, and send the appearance gray image obtained after the gray processing to a corresponding bearing detector for analysis operation.
It should be noted that the image capturing device may be a device that directly captures the appearance gray scale image of the bearing, and in this case, the bearing detector may directly analyze the received appearance gray scale image. In another embodiment, the image acquisition device may acquire a color image of the bearing and send the color image to the bearing detector, and the bearing detector performs gray processing to obtain a corresponding appearance gray image. In one embodiment, the image acquisition device comprises a camera and a light source, and a positive shooting mode is adopted when the appearance gray scale map of the bearing is acquired. Referring to fig. 2, the light source is a red ring light with a diameter of 75mm, and the light emitting direction of the lamp bead forms an angle of 45 degrees with the direction perpendicular to the camera lens, so as to ensure the clarity of image acquisition. It will be appreciated that in other embodiments, the camera, the light source and the bearing may be arranged in other ways as long as a clear and complete bearing appearance image can be acquired.
It is understood that in one embodiment, the original image acquired by the image acquisition device may be used as the image for detecting the appearance of the bearing in the bearing detector. In another embodiment, the original image acquired by the image acquisition device may be subjected to a certain cropping, and then the cropped image is used as the image for bearing appearance detection in the bearing detector. Whether the bearing body needs to be cut or not can be selected according to the actually shot image, and the image finally used for bearing appearance detection only needs to be ensured to contain the image of the whole bearing body.
Referring to fig. 3 and 4, in the gray scale of the appearance of the bearing, the difference between the material and the material (i.e. the material and the ball) is very large, and referring to fig. 3, in the case of no material, the position of the gray scale of the appearance where the ball should be present will appear white, and the gray scale of the corresponding area will be very large, close to 255. Referring to fig. 4, in the presence of material, the position of the appearance gray scale where the ball should be located will appear black, and the gray scale value of the corresponding area will be very small and close to 0. Therefore, according to the inconsistency of the appearance gray level images in the presence and absence of the material, the detection operation of whether the bearing is material or not can be carried out.
And S200, when the bearing is filled, cutting the corresponding position of the appearance gray image according to a preset rectangular area to obtain a gray image of the region of interest.
Specifically, in the absence of material in the bearing, there is no ball in the bearing and no need to perform further analysis of the ball condition. Therefore, in this embodiment, the ball state detection operation is further performed when the analysis result indicates that the bearing is in a material state. At the moment, the bearing detector cuts the appearance gray image according to the preset rectangular area to obtain the gray image of the region of interest matched with the rectangular area. The Region Of Interest (ROI) is a Region to be processed in a frame, a circle, an ellipse, an irregular polygon, or the like from a processed image in machine vision and image processing.
In the actual bearing appearance detection operation, because the positions of the image acquisition device and the bearing are fixed, the sizes of the corresponding acquired appearance gray-scale images are basically consistent. Therefore, the bearing appearance detector is provided with a rectangular region having a fixed size and a fixed position with respect to the appearance gray scale image by an algorithm, so that the fixed position of the appearance gray scale image can be cut when the cutting is performed, the size of the image obtained by cutting each time is consistent, and the image of the region of interest obtained by cutting can be further analyzed. For example, in an embodiment, please refer to fig. 3 and fig. 4 in combination, the position of the preset rectangular region is shown as the rectangular position in the figure, and in the appearance detection operation of each bearing, the position is cut according to the preset rectangular region, and a gray scale map of the region of interest is obtained as shown in fig. 5. It is understood that in other embodiments, rectangular regions with other sizes may be set to cut the appearance grayscale image, as long as the cut image can reasonably reflect the rolling ball state.
And S400, segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
Specifically, the size of the preset segmentation threshold is not unique, as long as the ball part and the background part can be reasonably distinguished, and the preset segmentation threshold may be set differently by a user according to actual conditions. When the foreground part and the background part are distinguished, an image formed by a part with a gray value higher than a preset division threshold value is used as a foreground gray image, and an image formed by a part with a gray value lower than the preset division threshold value is used as a background gray image. In one embodiment, the foreground grayscale image and the background grayscale image obtained by segmenting the grayscale image of the region of interest according to the preset segmentation threshold are shown in fig. 6, where the ring-like portion is the foreground grayscale image and the rest is the background grayscale image.
Referring to fig. 7, in one embodiment, step S100 includes step S110 and step S120.
Step S110, carrying out gray level analysis according to the appearance gray level image of the bearing to obtain a first gray level average value of the appearance gray level image. And step S120, if the first gray average value is smaller than a first preset gray threshold value, the bearing is charged.
Specifically, as described in the above embodiments, in the case of material and material absence, the gray values of the material portions in the appearance gray-scale map are greatly different, and due to the difference between the gray values of the material portions and the material absence, there is a substantial difference between the gray values of the material portions in the appearance gray-scale map and the material absence in the end. Therefore, in this embodiment, a manner of gray-scale mean analysis is adopted to determine whether the bearing corresponding to the appearance gray-scale map is material. Specifically, a first gray average value of the appearance gray image is obtained by analyzing and calculating the gray value corresponding to each pixel in the appearance gray image, and then the gray average value is compared with a corresponding first preset gray threshold value for analysis. And under the condition that the first gray average value is smaller than a first preset gray threshold value, indicating that materials exist in an original material area, so that the whole appearance gray image is biased to be black, and correspondingly obtaining an analysis conclusion that the bearing is material at the moment when the calculated first gray average value is smaller.
It should be noted that the size of the first preset grayscale threshold is not unique, and for different types of bearings, the first preset grayscale threshold with different sizes may be set specifically, as long as the difference between the material existence and the material nonexistence can be reasonably represented. For example, in one embodiment, the first preset gray level threshold is 80, that is, when the first gray level average value is less than 80, it indicates that the bearing is material, and when the first gray level average value is greater than or equal to 80, it indicates that the bearing is material-free.
Referring to fig. 8, in an embodiment, after step S100, the method further includes step S300.
And step S300, when the bearing is free of materials, obtaining a detection result of the absence of the materials of the bearing.
Specifically, when the bearing is empty, it means that the ball is not installed in the bearing at this time, and it is not necessary to continue the ball state detection at this time. Therefore, when the bearing is empty, the bearing detector directly obtains the detection result of the bearing without material, and the bearing appearance detection operation is directly finished.
Referring to fig. 9, in an embodiment, the step of analyzing the foreground grayscale image and the background grayscale image to obtain the ball state detection result of the bearing includes steps S410, S430, S450, and S470.
Referring to fig. 10, in step S410, the background gray image is clipped according to the preset circular area, and a second gray average of the clipped circular gray image is calculated.
Specifically, the preset circular area is similar to the preset rectangular area, and the preset circular area is also an area which is realized by an algorithm in the bearing detector and is fixed in position and size relative to the area to be cut. For example, in one embodiment, referring to fig. 11 and 12, the circular region fixes the center position of the gray-scale map of the region of interest to be cropped.
And step S430, when the second gray average value is less than or equal to a second preset gray threshold value, clipping the foreground gray image according to the preset ring area, and calculating the pixel area of the clipped ring gray image.
Specifically, each pixel in the gray image has a corresponding gray value, and after the gray image of the region of interest is cut by using the preset circular region to obtain the circular region, the bearing detector calculates according to the gray value corresponding to each pixel point to obtain an average value of the gray values of each pixel point, which is the second gray average value. At this time, the bearing detector compares the calculated second gray level average value with a preset second gray level threshold value, and different detection operations are realized according to the magnitude relation between the second gray level average value and the second preset gray level threshold value. Further, when the second gray level mean value is less than or equal to the second gray level threshold, a more accurate detection result cannot be obtained, and therefore, an additional analysis operation needs to be performed on the combined foreground gray level image. It should be noted that the size of the second preset gray threshold is not exclusive, for example, in one embodiment, the second preset gray threshold is 10, that is, in the case that the second gray average value is less than or equal to the second preset gray threshold, the subsequent analysis operation of the foreground gray image is continued.
The preset circular ring regions are similar to the preset circular region and the preset rectangular region, and are circular ring regions which are pre-stored by the bearing detector, fixed in position relative to the foreground gray-scale image and fixed in size, and in each bearing appearance detection operation, the bearings of the same model are cut according to the same preset circular ring regions, so that corresponding circular ring gray-scale images are obtained, and specifically, refer to fig. 13 to fig. 16. After the bearing detector cuts the foreground gray image according to the preset ring area to obtain a ring area gray image, the size of the pixel area in the area is counted, the pixel area corresponding to each pixel is 1, and the bearing detector can obtain the corresponding pixel area only by counting the number of the pixels.
Step S450, when the pixel area is smaller than the preset pixel area, calculating a third gray average value of the ring gray image.
Specifically, a preset pixel area is prestored in the bearing detector, after the pixel area is obtained through statistics, comparison analysis is performed according to the pixel area and the preset pixel area, and under the condition that the pixel area is smaller than the preset pixel area, an average value (i.e., a third gray average value) of gray values of all pixel points in the circular ring region is further analyzed. At this time, the bearing detector counts the gray value corresponding to each pixel point, and then calculates according to the number of the pixel points and the sum of the gray values of each pixel point to obtain a corresponding third gray average value.
And step S470, obtaining a qualified detection result of the bearing when the third gray average value is greater than a third preset gray threshold value.
Specifically, referring to fig. 16, the third predetermined grayscale threshold is greater than the second predetermined grayscale threshold, and the first predetermined grayscale threshold is greater than the third predetermined grayscale threshold. And when the third gray average value is obtained through calculation, the bearing detector further analyzes and operates the third gray average value and a third preset gray value, and when the third gray average value is greater than or equal to a third gray threshold value, the bearing detector obtains a qualified final detection result of the bearing. It should be noted that the size of the third preset grayscale threshold is not unique, for example, in an embodiment, the third preset grayscale threshold is 65, that is, in a case that the third grayscale mean value corresponding to the ring grayscale image obtained by cutting the preset ring region is greater than 65, the bearing detector will obtain a qualified final detection result of the bearing, and complete a bearing appearance detection operation.
Referring to fig. 17, in an embodiment, after step S410, the method further includes step S420.
And step S420, when the second gray average value is larger than a second preset gray threshold value, obtaining a detection result that the balls are loaded askew.
Referring to fig. 10 and 11, when the bearing detector obtains the second gray average value through analysis and performs comparative analysis according to the second gray average value and the second preset gray threshold value, a situation that the second gray average value is greater than the second preset gray threshold value may also occur, which indicates that the ball is in a wrong collision state, and the bearing detector directly obtains a detection result that the ball is in a wrong collision state, thereby ending the operation of detecting the appearance of the bearing.
Referring to fig. 17, in an embodiment, after the step S430, the method further includes a step S440.
Step S440, when the pixel area is larger than or equal to the preset pixel area, obtaining the detection result that the ball is loaded normally but not oiled.
Referring to fig. 10 and 14, similarly, after the bearing detector cuts the preset circular ring region to obtain the gray image of the circular ring region and calculates the pixel area of the region, when the pixel area is compared with the preset pixel area, the pixel area may be larger than or equal to the preset pixel area. And the corresponding bearing controller obtains the detection result that the ball is loaded correctly but not oiled, and the corresponding bearing appearance detection operation is finished. It should be noted that the size of the predetermined pixel area is not exclusive, for example, in one embodiment, the predetermined pixel area is 16000.
Referring to fig. 17, in an embodiment, after step S450, the method further includes step S460.
And step S460, when the third gray average value is smaller than a third preset gray threshold value, obtaining a detection result of ball reverse loading but oil pumping.
Referring to fig. 10 and fig. 15, similarly, when the bearing detector performs a comparison analysis according to the third gray level average value of the annular region and the preset third gray level threshold, a situation that the third gray level average value is smaller than the third preset gray level threshold may also occur. At this time, the bearing detector will obtain the detection result of the ball being reversely loaded but being oiled, and end the corresponding bearing appearance detection operation.
Referring to fig. 18, in one embodiment, step S430 includes step S431, including step S431, step S432, and step S433.
And step S431, when the second gray average value is less than or equal to a second preset gray threshold value, removing a connected domain of which the pixel area is less than the preset connected pixel area in the foreground gray image. And step S432, counting the number of the residual connected domains in the foreground gray-scale image. And step S433, when the number of the residual connected domains is not zero, cutting the foreground gray image according to a preset ring area, and calculating the pixel area of the cut ring gray image.
Specifically, referring to fig. 10, connected domains are connected small domains without disconnection, specifically, some connected pixels obtained according to the gray value. After the gray level image of the region of interest is segmented according to the preset segmentation threshold, the image can be converted into a binary image, the pixel values corresponding to the background gray level image are all 0, the pixel values of the foreground gray level image are all 1, and the bearing controller only needs to find the region with the pixel value of 1 as the corresponding connected domain. Then the bearing detector respectively calculates the pixel areas corresponding to the connected domains, namely the number of pixel points, the connected domains with pixel areas (namely the pixel points) smaller than the preset connected pixel areas are removed, and the bearing detector counts the number of the residual connected domains. When the number of the residual connected domains is not zero, it indicates that at least one pixel region with the pixel area larger than 8 exists, and at this time, the foreground image is continuously analyzed. It should be noted that the size of the preset connected pixel area is not unique, and different sizes of the preset connected pixel area can be set according to the type of the bearing to be monitored and the user requirements. For example, in one embodiment, the size of the area of the connected pixels is set to 8.
Referring to fig. 18, in an embodiment, after step S432, the method further includes step S434.
And step S434, when the number of the residual connected domains is zero, obtaining the detection result of missing or reverse installation of the ball bearings.
Specifically, referring to fig. 10, fig. 13 and fig. 15 in combination, after the connected component is screened according to the preset connected pixel area, the number of the remaining connected components is zero. At this time, the bearing detector will obtain the detection result of the missing or reverse installation of the ball, and the corresponding bearing appearance detection operation is finished. Through the bearing appearance detection operation, the complex detection of staff can be replaced by automatic detection;
according to the bearing appearance detection method, the appearance gray level image acquisition operation of the bearing is realized according to the image acquisition device, and then whether the bearing is filled or not is analyzed according to the appearance gray level image, namely whether the bearing is filled with balls or not is detected. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, can remove the manual detection in later stage to realize the unmanned automated production of the whole flow of equipment packing. This scheme is disposable to detect multiple bad to definite classification, the problem of the analysis equipment of being convenient for, detection efficiency is high simultaneously, and the beat is less than 0.2S/piece, and the outward appearance that can compatible different kinds of ball detects, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
Referring to fig. 19, an apparatus for detecting an appearance of a bearing includes: a material analysis module 100, a region of interest acquisition module 200, and a detection analysis module 300.
The material analysis module 100 is used for analyzing whether the bearing is filled according to the appearance gray level image of the bearing; the region-of-interest obtaining module 200 is configured to, when the bearing is filled with a material, cut the corresponding position of the appearance gray image according to the preset rectangular region to obtain a gray image of the region of interest; the detection analysis module 300 is configured to segment the grayscale image of the region of interest according to a preset segmentation threshold to obtain a foreground grayscale image and a background grayscale image, and analyze the foreground grayscale image and the background grayscale image to obtain a ball state detection result of the bearing.
In one embodiment, the material analysis module 100 is further configured to perform gray scale analysis according to the appearance gray scale image of the bearing, so as to obtain a first gray scale average value of the appearance gray scale image; if the first gray average value is smaller than a first preset gray threshold value, the bearing is charged; and when the first gray average value is greater than or equal to a first preset gray threshold value, obtaining a detection result of the material absence of the bearing.
In one embodiment, the detection analysis module 300 is further configured to crop the background grayscale image according to a preset circular region, and calculate a second grayscale mean of the cropped circular grayscale image; when the second gray average value is smaller than or equal to a second preset gray threshold value, the foreground gray image is cut according to the preset ring area, and the pixel area of the cut ring gray image is calculated; when the area of the pixel is smaller than the area of the preset pixel, calculating a third gray average value of the ring gray image; and when the third gray average value is larger than a third preset gray threshold value, obtaining a qualified detection result of the bearing.
In one embodiment, the detection analysis module 300 is further configured to obtain a detection result that the balls are loaded askew when the second gray level average value is greater than a second preset gray level threshold value.
In one embodiment, the detection analysis module 300 is further configured to obtain a detection result that the ball is loaded but not oiled when the pixel area is greater than or equal to the preset pixel area.
In one embodiment, the detection analysis module 300 is further configured to obtain a detection result of ball reverse loading but oil pumping when the third gray average value is smaller than a third preset gray threshold value.
In one embodiment, the detection analysis module 300 is further configured to remove a connected domain in the foreground grayscale image, where the pixel area of the connected domain is smaller than the preset connected pixel area, when the second grayscale mean is smaller than or equal to a second preset grayscale threshold; counting the number of the residual connected domains in the foreground gray level image; and when the number of the residual connected domains is not zero, cutting the foreground gray-scale image according to a preset ring area, and calculating the pixel area of the cut ring gray-scale image.
In one embodiment, the detection analysis module 300 is further configured to obtain a detection result of missing or reverse loading of the ball when the number of the remaining connected domains is zero.
For specific limitations of the bearing appearance detection device, reference may be made to the above limitations of the bearing appearance detection method, and details are not repeated here. Each module in the bearing appearance detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The bearing appearance detection device realizes the appearance gray level image acquisition operation of the bearing according to the image acquisition device, and then analyzes whether the bearing is filled according to the appearance gray level image, namely, detects whether the bearing has a ball. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, can remove the manual detection in later stage to realize the unmanned automated production of the whole flow of equipment packing. This scheme is disposable to detect multiple bad to definite classification, the problem of the analysis equipment of being convenient for, detection efficiency is high simultaneously, and the beat is less than 0.2S/piece, and the outward appearance that can compatible different kinds of ball detects, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
Referring to fig. 20, a bearing appearance detecting system includes an image capturing device 10 and a bearing detector 20, the image capturing device 10 is connected to the bearing detector 20, the image capturing device 10 is used for capturing an image of a bearing to obtain a corresponding appearance gray scale, and the bearing detector 20 is used for detecting the appearance of the bearing according to the above method.
Specifically, the appearance grayscale image is obtained by image-capturing the bearing by the image-capturing device 10. A grayscale image is a grayscale digital image, which is an image with only one sample color per pixel. Such images are typically displayed in gray scale from darkest black to brightest white, although in theory this sampling could be of different shades of any color and even different colors at different brightnesses. The gray image is different from the black and white image, the black and white image only has two colors of black and white in the field of computer image, the gray image has a plurality of levels of color depth between black and white, and the white and the black can be divided into 256 levels according to a logarithmic relation. The grayscale processing is to perform graying on the color image, and specifically, a component method, a maximum value method, an average value method, a weighted average method, and the like may be adopted, where the appearance grayscale image is an image obtained after performing grayscale processing on the appearance image of the bearing, and the image acquisition device 10 may first acquire a general image (i.e., a color image) of the bearing, then perform grayscale processing, and obtain a corresponding appearance grayscale image, and send the appearance grayscale image obtained after the grayscale processing to the corresponding bearing detector 20 for analysis.
Further, in one embodiment, the image capturing device 10 includes a camera and a light source, and takes a positive photograph when capturing the appearance gray scale of the bearing. Referring to fig. 2, the workpiece is a bearing, and the switching between the stations is electrically controlled, and when the workpiece flows to the corresponding station, the electric circuit triggers the camera to take a picture. The light source adopts red annular light with the diameter of 75mm, and the light-emitting direction of the lamp bead and the direction vertical to the camera lens form an angle of 45 degrees so as to ensure the image acquisition definition. It will be appreciated that in other embodiments, the camera, the light source and the bearing may be arranged in other ways as long as a clear and complete bearing appearance image can be acquired.
According to the bearing appearance detection system, the appearance gray level image acquisition operation of the bearing is realized according to the image acquisition device, and then whether the bearing is filled or not is analyzed according to the appearance gray level image, namely whether the bearing is provided with the ball is detected. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, can remove the manual detection in later stage to realize the unmanned automated production of the whole flow of equipment packing. This scheme is disposable to detect multiple bad to definite classification, the problem of the analysis equipment of being convenient for, detection efficiency is high simultaneously, and the beat is less than 0.2S/piece, and the outward appearance that can compatible different kinds of ball detects, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 21. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing preset parameters for comparative analysis. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a bearing appearance detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 21 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program: analyzing whether the bearing is filled according to the appearance gray level image of the bearing; when the bearing is filled with materials, cutting the corresponding position of the appearance gray image according to a preset rectangular area to obtain a gray image of the region of interest; and segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
In one embodiment, the processor, when executing the computer program, further performs the steps of: carrying out gray level analysis according to the appearance gray level image of the bearing to obtain a first gray level mean value of the appearance gray level image; if the first gray average value is smaller than a first preset gray threshold value, the bearing is charged; and when the first gray average value is greater than or equal to a first preset gray threshold value, obtaining a detection result of the material absence of the bearing.
In one embodiment, the processor, when executing the computer program, further performs the steps of: cutting the background gray image according to a preset circular area, and calculating a second gray average value of the cut circular gray image; when the second gray average value is smaller than or equal to a second preset gray threshold value, the foreground gray image is cut according to the preset ring area, and the pixel area of the cut ring gray image is calculated; when the area of the pixel is smaller than the area of the preset pixel, calculating a third gray average value of the ring gray image; and when the third gray average value is larger than a third preset gray threshold value, obtaining a qualified detection result of the bearing.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the second gray average value is larger than a second preset gray threshold value, obtaining a detection result that the balls are loaded askew.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the pixel area is larger than or equal to the preset pixel area, obtaining the detection result that the ball is positively arranged but not oiled.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the third gray average value is smaller than a third preset gray threshold value, obtaining a detection result of reverse ball loading but oil pumping.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the second gray average value is smaller than or equal to a second preset gray threshold value, removing a connected domain of which the pixel area is smaller than the area of a preset connected pixel in the foreground gray image; counting the number of the residual connected domains in the foreground gray level image; and when the number of the residual connected domains is not zero, cutting the foreground gray-scale image according to a preset ring area, and calculating the pixel area of the cut ring gray-scale image.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the number of the residual connected domains is zero, obtaining the detection result of the missing or reverse installation of the ball bearings.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: analyzing whether the bearing is filled according to the appearance gray level image of the bearing; when the bearing is filled with materials, cutting the corresponding position of the appearance gray image according to a preset rectangular area to obtain a gray image of the region of interest; and segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out gray level analysis according to the appearance gray level image of the bearing to obtain a first gray level mean value of the appearance gray level image; if the first gray average value is smaller than a first preset gray threshold value, the bearing is charged; and when the first gray average value is greater than or equal to a first preset gray threshold value, obtaining a detection result of the material absence of the bearing.
In one embodiment, the computer program when executed by the processor further performs the steps of: cutting the background gray image according to a preset circular area, and calculating a second gray average value of the cut circular gray image; when the second gray average value is smaller than or equal to a second preset gray threshold value, the foreground gray image is cut according to the preset ring area, and the pixel area of the cut ring gray image is calculated; when the area of the pixel is smaller than the area of the preset pixel, calculating a third gray average value of the ring gray image; and when the third gray average value is larger than a third preset gray threshold value, obtaining a qualified detection result of the bearing.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the second gray average value is larger than a second preset gray threshold value, obtaining a detection result that the balls are loaded askew.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the pixel area is larger than or equal to the preset pixel area, obtaining the detection result that the ball is positively arranged but not oiled.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the third gray average value is smaller than a third preset gray threshold value, obtaining a detection result of reverse ball loading but oil pumping.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the second gray average value is smaller than or equal to a second preset gray threshold value, removing a connected domain of which the pixel area is smaller than the area of a preset connected pixel in the foreground gray image; counting the number of the residual connected domains in the foreground gray level image; and when the number of the residual connected domains is not zero, cutting the foreground gray-scale image according to a preset ring area, and calculating the pixel area of the cut ring gray-scale image.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the number of the residual connected domains is zero, obtaining the detection result of the missing or reverse installation of the ball bearings.
It will be understood by those of ordinary skill in the art that all or a portion of the processes of the methods of the embodiments described above may be implemented by a computer program that may be stored on a non-volatile computer-readable storage medium, which when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory.
The computer equipment and the storage medium realize the appearance gray level image acquisition operation of the bearing according to the image acquisition device, and then analyze whether the bearing is filled according to the appearance gray level image, namely, detect whether the bearing is filled with balls. And under the condition that the bearing is detected to be loaded, further cutting a specified position of the image according to a preset rectangular region to obtain a gray image of the region of interest, segmenting according to a preset segmentation threshold value to obtain a foreground gray image and a background gray image, and finally analyzing according to the foreground gray image and the background gray image to obtain a detection result of bearing appearance detection, thereby realizing detection operation of various adverse conditions of the bearing. Above-mentioned scheme replaces manual detection through automated inspection, and automated inspection replaces the loaded down with trivial details inspection of staff, prevents that the defective work from flowing to next process, causes unusual shut down, can remove the manual detection in later stage to realize the unmanned automated production of the whole flow of equipment packing. This scheme is disposable to detect multiple bad to definite classification, the problem of the analysis equipment of being convenient for, detection efficiency is high simultaneously, and the beat is less than 0.2S/piece, and the outward appearance that can compatible different kinds of ball detects, compares with traditional bearing outward appearance detection mode and has stronger detection reliability.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the claims. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (13)
1. A bearing appearance detection method is characterized by comprising the following steps:
analyzing whether the bearing is provided with materials or not according to an appearance gray image of the bearing, wherein the appearance gray image is obtained by carrying out image acquisition on the bearing through an image acquisition device;
when the bearing is filled with materials, cutting the corresponding position of the appearance gray image according to a preset rectangular area to obtain a gray image of an interested area;
and segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
2. The bearing appearance detection method according to claim 1, wherein the step of analyzing whether the bearing is in a material state according to the appearance gray level image of the bearing comprises:
carrying out gray level analysis according to the appearance gray level image of the bearing to obtain a first gray level mean value of the appearance gray level image;
and if the first gray average value is smaller than a first preset gray threshold value, the bearing is filled with materials.
3. The bearing appearance inspection method according to claim 1, wherein after the step of analyzing whether the bearing is in a material state according to the appearance gray scale image of the bearing, the method further comprises:
and when the bearing is free of materials, obtaining a detection result of the absence of the materials of the bearing.
4. The bearing appearance detection method according to claim 1, wherein the step of analyzing the foreground gray image and the background gray image to obtain the detection result of the ball state of the bearing comprises:
cutting the background gray image according to a preset circular area, and calculating a second gray average value of the cut circular gray image;
when the second gray average value is smaller than or equal to the second preset gray threshold value, the foreground gray image is cut according to a preset ring area, and the pixel area of the cut ring gray image is calculated;
when the pixel area is smaller than a preset pixel area, calculating a third gray average value of the ring gray image;
and when the third gray average value is greater than a third preset gray threshold value, obtaining a qualified detection result of the bearing, wherein the third preset gray threshold value is greater than the second preset gray threshold value, and the first preset gray threshold value is greater than the third preset gray threshold value.
5. The bearing appearance detecting method according to claim 4, wherein after the step of cropping the background gray image according to a preset circular area and calculating the second gray average of the cropped circular gray image, the method further comprises:
and when the second gray average value is larger than the second preset gray threshold value, obtaining a detection result that the balls are loaded askew.
6. The bearing appearance detecting method according to claim 4, wherein after the step of clipping the foreground gray image according to a preset ring region and calculating a pixel area of the clipped ring gray image when the second gray average value is less than or equal to the second preset gray threshold value, the method further comprises:
and when the pixel area is larger than or equal to the preset pixel area, obtaining the detection result that the ball is aligned but not oiled.
7. The bearing appearance inspection method according to claim 4, wherein after the step of calculating the third mean gray level of the ring gray level image when the pixel area is smaller than the preset pixel area, the method further comprises:
and when the third gray average value is smaller than the third preset gray threshold value, obtaining a detection result of the reverse ball loading but the oil pumping.
8. The bearing appearance detection method according to claim 4, wherein the step of clipping the foreground gray image according to a preset ring region and calculating a pixel area of the clipped ring gray image when the second gray average value is less than or equal to the second preset gray threshold value comprises:
when the second gray average value is smaller than or equal to the second preset gray threshold value, removing a connected domain of which the pixel area is smaller than a preset connected pixel area in the foreground gray image;
counting the number of the residual connected domains in the foreground gray-scale image;
and when the number of the residual connected domains is not zero, cutting the foreground gray-scale image according to a preset circular ring region, and calculating the pixel area of the cut circular ring gray-scale image.
9. The bearing appearance inspection method according to claim 8, wherein after the step of counting the number of the remaining connected components in the foreground gray-scale image, the method further comprises:
and when the number of the residual connected domains is zero, obtaining the detection result of the missing or reverse installation of the ball bearings.
10. The utility model provides a bearing outward appearance detection device which characterized in that includes:
the material analysis module is used for analyzing whether the bearing is provided with materials or not according to the appearance gray level image of the bearing, and the appearance gray level image is obtained by carrying out image acquisition on the bearing through an image acquisition device.
And the interested region acquisition module is used for cutting the corresponding position of the appearance gray image according to a preset rectangular region to obtain the gray image of the interested region when the bearing is charged.
And the detection analysis module is used for segmenting the gray level image of the region of interest according to a preset segmentation threshold value to obtain a foreground gray level image and a background gray level image, and analyzing according to the foreground gray level image and the background gray level image to obtain a ball state detection result of the bearing.
11. A bearing appearance detection system is characterized by comprising an image acquisition device and a bearing detector, wherein the image acquisition device is connected with the bearing detector, the image acquisition device is used for carrying out image acquisition on a bearing to obtain a corresponding appearance gray scale map, and the bearing detector is used for carrying out bearing appearance detection according to the method of any one of claims 1 to 9.
12. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 9 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010241842.1A CN111462074B (en) | 2020-03-31 | 2020-03-31 | Bearing appearance detection method, device, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010241842.1A CN111462074B (en) | 2020-03-31 | 2020-03-31 | Bearing appearance detection method, device, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111462074A true CN111462074A (en) | 2020-07-28 |
| CN111462074B CN111462074B (en) | 2024-03-19 |
Family
ID=71678457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010241842.1A Active CN111462074B (en) | 2020-03-31 | 2020-03-31 | Bearing appearance detection method, device, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462074B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730459A (en) * | 2021-02-05 | 2021-04-30 | 北京嘉恒中自图像技术有限公司 | Bearing inner ring end surface defect detection method based on multi-angle light source shooting image |
| CN113012121A (en) * | 2021-03-09 | 2021-06-22 | 普迪飞半导体技术(上海)有限公司 | Method and device for processing bare chip scanning result, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408555A (en) * | 2015-12-27 | 2017-02-15 | 华南理工大学 | Bearing surface flaw detection method based on image vision |
| CN107967681A (en) * | 2017-11-24 | 2018-04-27 | 常熟理工学院 | Defect inspection method is hindered in a kind of elevator compensation chain punching based on machine vision |
| CN109636777A (en) * | 2018-11-20 | 2019-04-16 | 广州方纬智慧大脑研究开发有限公司 | A kind of fault detection method of traffic lights, system and storage medium |
| WO2019237520A1 (en) * | 2018-06-11 | 2019-12-19 | 平安科技（深圳）有限公司 | Image matching method and apparatus, computer device, and storage medium |
-
2020
- 2020-03-31 CN CN202010241842.1A patent/CN111462074B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106408555A (en) * | 2015-12-27 | 2017-02-15 | 华南理工大学 | Bearing surface flaw detection method based on image vision |
| CN107967681A (en) * | 2017-11-24 | 2018-04-27 | 常熟理工学院 | Defect inspection method is hindered in a kind of elevator compensation chain punching based on machine vision |
| WO2019237520A1 (en) * | 2018-06-11 | 2019-12-19 | 平安科技（深圳）有限公司 | Image matching method and apparatus, computer device, and storage medium |
| CN109636777A (en) * | 2018-11-20 | 2019-04-16 | 广州方纬智慧大脑研究开发有限公司 | A kind of fault detection method of traffic lights, system and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 崔明等: "基于机器视觉的轴承滚动体缺陷检测算法研究", pages 74 - 78 * |
| 黄俊敏等: "基于机器视觉的轴承密封圈缺陷检测方法", vol. 24, no. 4, pages 13 - 15 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112730459A (en) * | 2021-02-05 | 2021-04-30 | 北京嘉恒中自图像技术有限公司 | Bearing inner ring end surface defect detection method based on multi-angle light source shooting image |
| CN112730459B (en) * | 2021-02-05 | 2023-01-24 | 北京嘉恒中自图像技术有限公司 | Bearing inner ring end surface defect detection method based on multi-angle light source shooting image |
| CN113012121A (en) * | 2021-03-09 | 2021-06-22 | 普迪飞半导体技术(上海)有限公司 | Method and device for processing bare chip scanning result, electronic equipment and storage medium |
| CN113012121B (en) * | 2021-03-09 | 2022-09-06 | 普迪飞半导体技术(上海)有限公司 | Method and device for processing bare chip scanning result, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462074B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108683907B (en) | Optical module pixel defect detection method, device and equipment | |
| CN112348773B (en) | Screen defect detection method and device and electronic equipment | |
| US20200349875A1 (en) | Display screen quality detection method, apparatus, electronic device and storage medium | |
| CN108827970B (en) | AOI system-based method and system for automatically judging defects of different panels | |
| CN111462074A (en) | Bearing appearance detection method, device and system, computer equipment and storage medium | |
| CN110476056A (en) | A kind of visible detection method, detection device and robot | |
| CN108734684B (en) | Image background subtraction for dynamic illumination scene | |
| CN110441316B (en) | Battery surface defect detection method and detection system | |
| CN105260716A (en) | Fault indicator state identification method and fault indicator state identification device | |
| US9230188B2 (en) | Objective metric relating to perceptual color differences between images | |
| CN114331997A (en) | Wire defect monitoring method based on image recognition | |
| CN111353507B (en) | Image recognition method and device for oil stains on surface of transformer substation device | |
| CN110118786B (en) | Detection method, detection device and industrial equipment | |
| WO2024016715A1 (en) | Method and apparatus for testing imaging consistency of system, and computer storage medium | |
| CN111369591A (en) | Method, device and equipment for tracking moving object | |
| CN112767397B (en) | Workpiece detection method, workpiece detection device, and storage medium | |
| CN115393343A (en) | Mine cage shoe fault detection method and device based on video analysis | |
| CN114549346A (en) | Blurred image recognition method, device, equipment and storage medium | |
| CN108447107B (en) | Method and apparatus for generating video | |
| CN111833309A (en) | Photovoltaic cell detection method and device | |
| CN115601606B (en) | Store state detection method, device, equipment and storage medium | |
| CN117191809B (en) | Glass detection equipment fault monitoring and early warning system based on data analysis | |
| US20230342897A1 (en) | Method to detect camera blemishes | |
| CN115578630B (en) | Method and system for judging working gear of air switch | |
| CN112464928B (en) | Digital meter reading identification method, device, equipment and storage medium |
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 |