Method for extracting effective area of bearing outer diameter chamfer based on visual algorithm
By using an RGB tri-color camera and different light sources to light the outer diameter surface and chamfer of the bearing and segment the response differences of the color image, the problem of difficult to identify and divide the boundary area between the chamfer of the outer ring and the outer diameter surface of the bearing in the prior art is solved, and accurate detection and defect identification of the chamfer of the outer ring of the bearing are achieved.
Patent Information
- Application Number
- CN202411589903.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-08
- Publication Date
- 2025-02-28
AI Technical Summary
The prior art is difficult to effectively identify and divide the boundary area between the chamfer of the bearing outer ring and the outer diameter surface, resulting in the inability to accurately detect the chamfer of the bearing outer ring.
The RGB tri-color camera is used to light the outer diameter surface and chamfer of the bearing with red coaxial light and two blue bar lights. Through the difference in response of the color image under different light sources, the bearing surface and chamfered area are segmented to achieve accurate image segmentation and defect recognition.
Accurate detection of the chamfer of the bearing outer ring is realized, defects can be effectively identified, and the accuracy and efficiency of detection are improved.
Smart Images
Figure CN119540170A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of visual inspection, and in particular relates to a method for extracting an effective area of a bearing outer diameter chamfer based on a visual algorithm. Background Art
[0002] As one of the most important basic parts in the industrial field, bearings are widely used and come in many types. In the past, the focus of bearing quality control was more on the processing accuracy and mechanical properties of bearings, because these are related to the various performance and life of mechanical products. However, in recent years, the appearance quality of bearings has received more and more attention. On the one hand, it affects the appearance of the product. On the other hand, surface defects (such as bumps, rust, cracks, black skin, etc.) will also seriously affect the performance and life of mechanical products.
[0003] At present, most large bearing factories have installed some imported or domestic automatic defect detection equipment based on machine vision, which has reduced labor and costs to a certain extent, and the detection results are stable. In the entire process of bearing processing, the key components are the outer ring, inner ring and roller. At present, there are detection equipment for the inner and outer rings, rollers and finished products of bearings.
[0004] For chamfer detection of bearing outer rings, the traditional method is to use a black and white camera plus a coaxial light source to illuminate the outer diameter of the bearing. Since the chamfered surface and the outer diameter surface are not on the same plane, the boundary area between the chamfer and the outer diameter surface is blurred and cannot be effectively segmented by the algorithm, and defects cannot be effectively identified. Therefore, it is impossible to accurately detect the chamfer of the bearing outer ring. Summary of the invention
[0005] The main technical problem solved by the present invention is to provide a method for extracting the effective area of the chamfer of the outer diameter of a bearing based on a visual algorithm. The method adopts an RGB three-color camera to distinguish three channels. Each pixel bit of each channel represents the color depth, that is, 0 to 255 represents the blackest to the brightest. The three channels are superimposed to form a color image. One red coaxial light is used to illuminate the outer diameter surface of the bearing, and two blue strip lights are used to illuminate the chamfer of the outer diameter of the bearing. The response difference of the color image under different light sources is used to segment the bearing surface and the chamfer area. The image of the area can be accurately segmented, defects can be effectively identified, and accurate detection of the chamfer of the outer ring of the bearing can be achieved.
[0006] In order to solve the above technical problems, a technical solution adopted by the present invention is: a method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm, the method comprising the following steps:
[0007] S1 obtains a color image of the bearing;
[0008] S2 crops the color image to obtain a region with a chamfered area;
[0009] S3 uses the response differences of color images under different light sources to segment the bearing surface and chamfer area;
[0010] S4 clips the red channel to obtain the area including the bearing surface and chamfer, and clips the blue channel to obtain the bearing surface area;
[0011] S5 extracts the chamfered area by performing a regional difference operation on the threshold segmentation results of the red channel and the blue channel.
[0012] Preferably,
[0013] In S1, an RGB color camera is used to photograph the outer diameter surface of the bearing to obtain the original color image.
[0014] Preferably,
[0015] In S1, the position of the chamfered area is selected in the acquired original color image, and the rectangular coordinates of the ROI are determined: x min ≤x≤x max ,y min ≤y≤y max ;
[0016] Wherein, ROI represents the region of interest, x represents the abscissa of the region of interest, and y represents the ordinate of the region of interest.
[0017] Preferably,
[0018] In S2, the original color image is cropped to obtain the ROI image, namely: ROI (x, y) = I (x, y), where x min ≤x≤x max ,y min ≤y≤y max .
[0019] Preferably,
[0020] In S3, the ROI image is decomposed into red, green and blue channels.
[0021]
[0022] Among them, R(x, y) represents the red channel, G(x, y) represents the green channel, and B(x, y) represents the blue channel. Indicates that the image of interest is obtained under the red channel. Indicates that the image of interest is obtained under the green channel. Indicates the region of interest under the blue channel.
[0023] Preferably,
[0024] In S4, the red channel is thresholded and the bearing surface and chamfer area are extracted;
[0025] Ω R =(x, y)|R(x, y)≥T r};
[0026] Among them, T r represents the threshold of the red channel, Ω R Represents the extraction of the bearing surface and chamfered area.
[0027] Preferably,
[0028] In S4, the blue channel is thresholded and the bearing surface area is extracted;
[0029] Ω B ={(x, y)|B(x, y)≥T b};
[0030] Among them, T b represents the threshold of the blue channel, Ω B Represents the extracted bearing surface area.
[0031] Preferably,
[0032] In S5, the difference between the red channel and the blue channel segmentation area is calculated to obtain the chamfer area Ω c ,Right now:
[0033]
[0034] Among them, Ω C Indicates the chamfered area.
[0035] The beneficial effects of the present invention are as follows:
[0036] This method uses an RGB three-color camera to distinguish three channels. Each pixel bit of each channel represents the color depth, that is, 0 to 255 represents the darkest to the brightest. The three channels are superimposed to form a color image. One red coaxial light is used to illuminate the outer diameter surface of the bearing, and two blue strip lights are used to illuminate the chamfer of the outer diameter of the bearing. The response difference of the color image under different light sources is used to segment the bearing surface and the chamfer area. The image of the area can be accurately segmented, defects can be effectively identified, and accurate detection of the chamfer of the bearing outer ring can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 It is a schematic diagram of the ROI region of the present invention;
[0038] Figure 2 It is a schematic diagram of the effective area extracted from the red layer of the present invention;
[0039] Figure 3 It is a schematic diagram of extracting the effective area in the blue layer of the present invention;
[0040] Figure 4 Schematic diagram of the chamfered area of the present invention. DETAILED DESCRIPTION
[0041] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.
[0042] Example:
[0043] A method for extracting an effective area of a bearing outer diameter chamfer based on a visual algorithm, the method comprising the following steps:
[0044] S1 obtains a color image of the bearing;
[0045] S2 crops the color image to obtain a region with a chamfered area;
[0046] S3 uses the response differences of color images under different light sources to segment the bearing surface and chamfer area;
[0047] S4 clips the red channel to obtain the area including the bearing surface and chamfer, and clips the blue channel to obtain the bearing surface area;
[0048] S5 extracts the chamfered area by performing a regional difference operation on the threshold segmentation results of the red channel and the blue channel.
[0049] Further,
[0050] In S1, an RGB color camera is used to photograph the outer diameter surface of the bearing, and a red coaxial light is used to illuminate the outer diameter surface of the bearing and two blue strip lights are used to illuminate the chamfer of the outer diameter of the bearing at the same time to obtain the original color image.
[0051] In S1, the position of the chamfered area is selected in the original color image obtained, referring to Figure 1 As shown, determine the rectangular coordinates of ROI: min ≤x≤x max ,y min ≤y≤y max ;
[0052] Wherein, ROI represents the region of interest, x represents the abscissa of the region of interest, and y represents the ordinate of the region of interest.
[0053] in addition,
[0054] In S2, the original color image is cropped to obtain a ROI image, which includes the surface and chamfer area of the bearing, namely: ROI (x, y) = I (x, y), where x min ≤x≤x max ,y min ≤y≤y max .
[0055] It needs to be further explained that
[0056] In S3, the ROI image is decomposed into red, green and blue channels.
[0057]
[0058]
[0059] Among them, R(x, y) represents the red channel, G(x, y) represents the green channel, and B(x, y) represents the blue channel. Indicates that the image of interest is obtained under the red channel. Indicates that the image of interest is obtained under the green channel. Indicates the region of interest under the blue channel.
[0060] An algorithm is used to extract the effective area in the red layer. The extraction algorithm here belongs to the existing technology and will not be described in detail, so as to realize the threshold separation of the red channel in S4 and extract the bearing surface and chamfer area;
[0061] Ω R =(x, y)|R(x, y)≥T r};
[0062] Among them, T r represents the threshold of the red channel, Ω R Represents the extraction of the bearing surface and chamfered area.
[0063] The algorithm is used to extract the effective area in the blue layer, and the blue channel is thresholded in S4 to extract the bearing surface area;
[0064] Ω B ={(x, y)|B(x, y)≥T b};
[0065] Among them, T b represents the threshold of the blue channel, Ω B Represents the extracted bearing surface area.
[0066] It should be noted that
[0067] In S5, the difference between the red channel and the blue channel segmentation area is calculated to obtain the chamfer area Ω c ,Right now:
[0068]
[0069] Among them, Ω C Indicates the chamfered area.
[0070] This method uses an RGB three-color camera to distinguish three channels. Each pixel bit of each channel represents the color depth, that is, 0 to 255 represents the darkest to the brightest. The three channels are superimposed to form a color image. One red coaxial light is used to illuminate the outer diameter surface of the bearing, and two blue strip lights are used to illuminate the chamfer of the outer diameter of the bearing. The response difference of the color image under different light sources is used to segment the bearing surface and the chamfer area. The image of the area can be accurately segmented, defects can be effectively identified, and accurate detection of the chamfer of the bearing outer ring can be achieved.
[0071] The above are only embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm, characterized in that: The method comprises the following steps: S1 obtains a color image of the bearing; S2 crops the color image to obtain a region with a chamfered area; S3 uses the response differences of color images under different light sources to segment the bearing surface and chamfer area; S4 cropped the red channel to obtain the area including the bearing surface and chamfer, and cropped the blue channel to obtain the bearing surface area; S5 extracts the chamfered area by performing a regional difference operation on the threshold segmentation results of the red channel and the blue channel.
2. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 1, characterized in that: In S1, an RGB color camera is used to photograph the outer diameter surface of the bearing to obtain the original color image.
3. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 2, characterized in that: In S1, the position of the chamfered area is selected in the acquired original color image, and the rectangular coordinates of the ROI are determined: x min ≤x≤x max ,y min ≤y≤y max ; Wherein, ROI represents the region of interest, x represents the abscissa of the region of interest, and y represents the ordinate of the region of interest.
4. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 3 is characterized by: In S2, the original color image is cropped to obtain the ROI image, namely: ROI (x, y) = I (x, y), where x min ≤x≤x max ,y min ≤y≤y max .
5. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 4, characterized in that: In S3, the ROI image is decomposed into red, green and blue channels. Among them, R(x, y) represents the red channel, G(x, y) represents the green channel, and B(x, y) represents the blue channel. Indicates that the image of interest is obtained under the red channel. Indicates that the image of interest is obtained under the green channel. Indicates the region of interest under the blue channel.
6. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 5, characterized in that: In S4, the red channel is thresholded and the bearing surface and chamfer area are extracted; Ω R =(x,y)|R(x,y)≥T r }; Among them, T r represents the threshold of the red channel, Ω R Represents the extraction of the bearing surface and chamfered area.
7. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 6, characterized in that: In S4, the blue channel is thresholded and the bearing surface area is extracted; Ω B ={(x,y)|B(x,y)≥T b }; Among them, T b represents the threshold of the blue channel, Ω B Represents the extracted bearing surface area.
8. The method for extracting the effective area of the outer diameter chamfer of a bearing based on a visual algorithm according to claim 7, characterized in that: In S5, the difference between the red channel and the blue channel segmentation area is calculated to obtain the chamfer area Ω c ,Right now: Ω C = Ω R -Ω B = {(x, y)|(x, y) ∈ Ω R and Among them, Ω C Indicates the chamfered area.