Plate circular hole identification method, system and equipment
By employing dual-light source tilt illumination and image fusion technology, the problems of light interference and computational redundancy on furniture board production lines have been solved, enabling efficient and high-speed circular hole recognition and improving detection accuracy and speed.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-03-13
AI Technical Summary
Traditional visual inspection technologies face challenges in furniture panel production lines, including light interference, difficulty in balancing recognition efficiency and accuracy, and redundant calculations in invalid areas. These issues make it difficult to meet the demands of high-speed production in terms of both inspection speed and accuracy.
By employing a dual-light source tilt illumination and grayscale conversion method, dual-light source images are acquired and paired point by point according to pixel position. The smaller grayscale value is selected for image fusion. Combined with real-time displacement acquisition and image stitching, halo and reflection interference are eliminated, thereby improving detection accuracy and speed.
It achieves high-precision and high-efficiency circular hole recognition on high-speed production lines, improving recognition accuracy by more than 80%, reducing false edges by 90%, reducing computational complexity by 98%, and achieving a detection frame rate of 120 frames/second, meeting the requirements of high-precision and high-speed detection.
Smart Images
Figure CN121661020A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of furniture board testing technology, specifically relating to a method, system, and device for identifying round holes in boards. Background Technology
[0002] In furniture panel production, the inspection of parameters such as the position and size of round holes is a crucial step in ensuring product assembly accuracy and performance. Especially on furniture panel production lines, where panels typically move continuously at speeds of around 1 m / s, traditional visual inspection technologies face multiple challenges: 1. Significant illumination interference: Under single-source illumination, a strong reflective area easily forms at the bottom of the circular aperture, and halo diffusion easily occurs at the edges, resulting in reduced grayscale contrast between the circular aperture target and the background in the acquired image, and an increase in false edge features. See also Figure 1 For example, when a circular hole in a metal workpiece is illuminated by a coaxial light source, reflections at the bottom of the hole can obscure the true edge; deep holes will exhibit blurred edges under oblique lighting. To suppress illumination interference, existing technologies mainly employ image preprocessing optimization or geometric algorithm fitting. However, preprocessing methods can only partially eliminate noise and cannot fundamentally solve the feature distortion caused by reflections and halos; while geometric algorithms can improve accuracy to some extent, they suffer from high computational load and poor real-time performance, making them unsuitable for the inspection needs of high-speed production lines. For instance, traditional circular hole detection based on the least squares method requires multiple steps such as edge extraction and contour fitting, resulting in a detection frame rate of only less than 10 frames per second, which is unsuitable for high-speed inspection scenarios exceeding 30 frames per second.
[0003] 2. Difficulty in balancing recognition efficiency and accuracy: When there is interference such as oil stains and scratches on the surface of the workpiece, the difficulty of feature extraction from single-light source images is further increased. This causes traditional algorithms to either miss detections due to stringent parameters (such as excessively strict radius constraints) or make false detections due to lenient parameters (such as excessively low contour screening standards), making it difficult to achieve an accuracy rate of over 95%.
[0004] 3. Redundancy in calculation of invalid regions: Existing technologies often perform full-pixel processing on the entire image, while the circular hole to be detected only occupies a very small area of the image (usually ≤10%). The invalid calculation of a large number of background areas leads to an increase in the overall detection time, which further limits the improvement of detection speed. Summary of the Invention
[0005] The purpose of this invention is to provide a method, system, and device for identifying circular holes in sheet metal.
[0006] The first aspect of this application provides a method for identifying circular holes in a sheet metal, comprising: Obtain a first image of the circular hole in the board material under the illumination of the first light source; A second image of the circular hole in the board material is obtained under the illumination of the second light source; the emitted light from both the first and second light sources is obliquely illuminating the surface of the board material, and the oblique directions are opposite. Perform grayscale conversion on the first and second images; The first and second images are paired pixel by pixel, and the smaller gray value of each pixel is selected as the pixel value of the fused image to obtain the final circular hole image.
[0007] In one embodiment of this application, the emitted light from the first light source is tilted downstream; The emitted light from the second light source is tilted upstream.
[0008] In one embodiment of this application, the irradiation areas of the first light source and the second light source on the surface of the plate are spaced a certain distance apart.
[0009] In one embodiment of this application, the method for acquiring the first image or the second image includes: During the conveying process of the sheet material, several initial images of the sheet material's circular holes passing through the illumination area of the corresponding light source are continuously acquired at preset displacement intervals. Crops out the effective region image containing the circular hole from the initial image; Several effective area images under the same illumination area are stitched together to form a first image or a second image.
[0010] In one embodiment of this application, the method for cropping an effective region image containing a circular hole based on an initial image includes: Image cropping is performed based on the estimated range obtained by multiplying the diameter of the circular hole by the magnification factor; and The image cropped according to the estimated range is reconfirmed. If the distance between the cropped area boundary and the edge of the circular hole is less than 5 pixels, it is expanded outward to 5 pixels.
[0011] A second aspect of this application provides a system for identifying circular holes in a sheet metal substrate, comprising: The first image acquisition module is used to acquire a first image of the circular hole in the board material under the illumination of the first light source; The second image acquisition module is used to acquire a second image of the circular hole in the board material under the illumination of the second light source; the emitted light from the first light source and the second light source are both obliquely illuminating the surface of the board material, and the oblique directions are opposite. The grayscale conversion module is used to perform grayscale conversion on the first image and the second image; The image fusion module is used to pair the first image and the second image pixel by pixel, select the smaller gray value of each pixel as the pixel value of the fused image, and obtain the final circular hole image.
[0012] A third aspect of this application provides a device for identifying circular holes in a sheet metal, comprising: A conveying device for conveying sheet metal along the y-direction; The first light source and the second light source are used to form a first irradiation area and a second irradiation area that are spaced apart along the y-direction on the conveying device; An image acquisition module, located above the conveying device, is used to acquire images of the board material. The control module is electrically connected to the conveying device, the first light source, the second light source, and the image acquisition module. It is used to control the image acquisition module to continuously acquire several initial images of the circular holes in the plate passing through the illumination area of the corresponding light source at preset displacement intervals. The processing module is used to stitch together several initial images under the same illumination area into a first image or a second image; and to execute the plate circular hole recognition method as described above to obtain the final circular hole image.
[0013] In one embodiment of this application, the plate hole identification device further includes: The initial position detection module, electrically connected to the control module, is located upstream of the first light source and is used to detect whether the circular hole in the board has reached the initial position. After the circular hole in the board reaches its initial position, the control module controls the image acquisition module to acquire a first initial image of the circular hole reaching the first illumination area at a first preset time interval. Then, at a second preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole passing through the first illumination area. After acquiring the last initial image of the circular hole in the board passing through the first irradiation area, the control module controls the image acquisition module to acquire the first initial image of the circular hole in the board reaching the second irradiation area at a third preset time interval. Then, at a fourth preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole in the board passing through the second irradiation area.
[0014] In one embodiment of this application, the conveying device includes an encoder electrically connected to the control module; The control module acquires the encoder reading at the same time as the image acquisition module acquires each initial image. The processing module calculates the corresponding pixel offset based on the displacement offset between the initial images, and stitches or merges the initial images based on the corresponding pixel offset.
[0015] The beneficial effects of this invention are: Unlike existing technologies, this application provides a method for identifying circular holes in sheet metal, comprising: acquiring a first image of a circular hole in a sheet metal under illumination by a first light source; acquiring a second image of a circular hole in a sheet metal under illumination by a second light source; wherein the emitted light from both the first and second light sources is obliquely illuminating the surface of the sheet metal, and the oblique directions are opposite; performing grayscale conversion on the first and second images; pairing the first and second images pixel by pixel, selecting the smaller grayscale value of each pixel as the pixel value of the fused image, and obtaining the final circular hole image. The method for identifying circular holes in sheet metal of this invention uses differential illumination of the circular hole in the sheet metal by dual light sources to obtain the first and second images respectively, and then uses pixel-level minimum grayscale value fusion to obtain the final circular hole image. This eliminates reflection and halo interference from the acquisition source, and the purity of the circular hole feature in the fused image is improved by more than 80% compared to the single-light source image, while false edges are reduced by 90%, effectively improving the accuracy of circular hole identification.
[0016] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.
[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0019] Figure 1 This is a schematic diagram of the reflection at the bottom of the hole; Figure 2 This is a flowchart of a preferred embodiment of the method for identifying circular holes in a sheet metal substrate according to the present invention; Figure 3 This is a top view of a preferred embodiment of the present invention under light source illumination; Figure 4 This is a side view of the light source illumination according to a preferred embodiment of the present invention; Figure 5 This is a schematic diagram of a preferred embodiment of the present invention showing the circular hole passing through the first irradiation area; Figure 6 This is a schematic diagram of a preferred embodiment of the present invention showing the circular hole passing through the second irradiation area; Figure 7This is a control principle diagram of a plate circular hole identification device according to a preferred embodiment of the present invention.
[0020] In the picture: Conveying device 1, photoelectric sensor 11, first light source 2, first irradiation area 21, second light source 3, second irradiation area 31, camera 4. Detailed Implementation
[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0022] This application provides a method, system, and device for identifying circular holes in sheet metal, which are described in detail below. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments of this application. Furthermore, the descriptions of each embodiment have their own emphasis; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments.
[0023] See Figure 2 One embodiment of this application provides a method for identifying circular holes in a sheet metal, comprising: Obtain a first image of the circular hole in the board material under the illumination of the first light source; A second image of the circular hole in the board material is obtained under the illumination of the second light source; the emitted light from both the first and second light sources is obliquely illuminating the surface of the board material, and the oblique directions are opposite. Perform grayscale conversion on the first and second images; The first and second images are paired pixel by pixel, and the smaller gray value of each pixel is selected as the pixel value of the fused image to obtain the final circular hole image.
[0024] In one embodiment, the arrangement of the light source can participate in... Figure 3 and Figure 4 Optionally, the emitted light from the first light source 2 is tilted downstream; the emitted light from the second light source 3 is tilted upstream.
[0025] For example, the first light source may be at a 75° angle to the horizontal direction and deflected downstream, forming a first irradiation area 21 on the conveying device 1; the second light source may be at a 75° angle to the horizontal direction and deflected upstream, forming a second irradiation area 31 on the conveying device 1. Of course, other angles may be used in other embodiments.
[0026] Optionally, the illumination areas of the first and second light sources on the surface of the board are spaced a certain distance apart. This facilitates image acquisition from the circular holes in the board under a single light source.
[0027] Furthermore, the method for acquiring the first image or the second image includes: during the conveying process of the board, continuously acquiring several initial images of the area illuminated by the corresponding light source through the circular holes of the board at preset displacement intervals; cropping an effective area image containing the circular holes based on the initial images; and stitching several effective area images under the same illumination area into a first image or a second image.
[0028] In one embodiment, Figure 5 Three initial images of the circular holes in the plate passing through the first irradiation area 21 were collected. Figure 6 Three initial images of the circular holes in the plate passing through the second irradiation area 21 were collected.
[0029] In one embodiment, in order to reduce the amount of subsequent calculations, an effective area image containing the circular hole can be cropped from the initial image, and several effective area images under the same illumination area can be stitched together to form a first image or a second image.
[0030] Specifically, the method for cropping an effective region image containing a circular hole based on an initial image may include: cropping the image according to an estimated range obtained by multiplying the diameter of the circular hole by a magnification factor; and performing a secondary confirmation on the image cropped according to the estimated range, if the distance between the boundary of the cropped area and the edge of the circular hole is less than 5 pixels, then extending it outward to 5 pixels.
[0031] For example, in one embodiment, the actual area of the circular hole in the image can be directly estimated based on the pre-obtained edge position of the board and the pixel ratio. Combining this with the known standard size of the circular hole, the estimated area is calculated proportionally, and an image containing the hole is cropped, ensuring that the cropped area covers the hole and its surrounding area with appropriate margin. For example, the diameter of the estimated area can be the diameter of the hole multiplied by 1.2; other coefficients can also be used in other embodiments. The estimated cropped area can then be reconfirmed. If the distance between the boundary of the cropped area and the edge of the hole is less than 5 pixels, it is expanded outwards to 5 pixels to avoid loss of edge information, resulting in the final processed area for the circular hole. This method can reduce the area of a single processed circular hole to 5%-10% of the original image, significantly reducing the amount of subsequent computation.
[0032] Based on the above embodiments, one embodiment of this application also provides a board circular hole recognition system, including: a first image acquisition module for acquiring a first image of a circular hole in a board under illumination by a first light source; a second image acquisition module for acquiring a second image of a circular hole in a board under illumination by a second light source; wherein the emitted light from the first light source and the second light source are both obliquely illuminating the surface of the board, and the oblique directions are opposite; a grayscale conversion module for performing grayscale conversion on the first image and the second image; and an image fusion module for pairing the first image and the second image point by point according to pixel position, selecting the smaller grayscale value of each pixel as the pixel value of the fused image, to obtain the final circular hole image.
[0033] In this embodiment, the working method of each module can be as described above, and will not be repeated here.
[0034] See Figure 3 , Figure 4 and Figure 7 Based on the above embodiments, one embodiment of this application also provides a plate circular hole identification device, including: Conveying device 1 is used to convey sheet metal along the y-direction; see [link / reference] Figure 3 and Figure 4 The arrow in the diagram points in the y-direction. The first light source 2 and the second light source 3 are used to form a first irradiation area 21 and a second irradiation area 31 that are spaced apart along the y direction on the conveying device 1; Image acquisition module 4 is located above conveying device 1 and is used to acquire images of the board material; The control module is electrically connected to the conveying device 1, the first light source 2, the second light source 3, and the image acquisition module 4. It is used to control the image acquisition module 4 to continuously acquire several initial images of the circular holes of the plate passing through the illumination area of the corresponding light source at preset displacement intervals. The processing module, electrically connected to the control module, is used to stitch together several initial images under the same irradiation area into a first image or a second image; and to execute the plate circular hole recognition method as described above, resulting in a final circular hole image.
[0035] In one embodiment, the plate hole identification device further includes: The initial position detection module 11 is electrically connected to the control module and is located upstream of the first light source 2. It is used to detect whether the circular hole in the board has reached the initial position. After the circular hole in the board reaches its initial position, the control module controls the image acquisition module to acquire the first initial image of the circular hole reaching the first irradiation area 21 at a first preset time interval. Then, at a second preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole passing through the first irradiation area 21. After acquiring the last initial image of the circular hole of the board passing through the first irradiation area 21, the control module controls the image acquisition module to acquire the first initial image of the circular hole of the board reaching the second irradiation area 31 at a third preset time interval. Then, at a fourth preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole of the board passing through the second irradiation area 31.
[0036] Optionally, the conveying device includes an encoder electrically connected to the control module; The control module acquires the encoder reading at the same time as the image acquisition module acquires each initial image. The processing module calculates the corresponding pixel offset based on the displacement offset between the initial images, and stitches or merges the initial images based on the corresponding pixel offset.
[0037] In some embodiments, the image acquisition module 4 may be an industrial camera with a global shutter of 5 megapixels or higher (to avoid motion blur), a frame rate of ≥150 frames / second, and an exposure time of ≤10μs; the control module may be a PLC; the initial position detection module 11 may be a photoelectric sensor (response time ≤1μs); the conveying device 1 may be a conveyor belt driven by a motor, and may also include an encoder for recording the conveying position; the processing module may be a PC.
[0038] The following is a specific example of the process for identifying round holes in a board material: First, the sheet material is placed on the conveying device 1, and the conveying device 1 conveys the sheet material forward along the y direction; When the initial position detection module 11 detects a circular hole on the plate, it sends a trigger detection signal to the control module. After a first preset time, the circular hole reaches the first irradiation area 21. At this time, the control module controls the image acquisition module 4 to capture the first initial image of the circular hole within the first irradiation area 21. (See below) Figure 5 The first image in the document. Optionally, the first preset duration can be obtained by dividing the distance from the photoelectric sensor detection position to the lower edge of the first irradiation area 21 by the material conveying speed. Then, the control module can also control the image acquisition module to acquire several initial images of the circular hole of the material passing through the first irradiation area 21 at intervals of a second preset duration, see [link to document]. Figure 5 The second and third images are shown. Optionally, the second preset duration can be obtained based on the diameter of the circular hole, the width of the first irradiation area 21, the number of images, the conveying speed of the board, etc. After capturing the last initial image of the circular hole within the first irradiation area 21, the control module controls the image acquisition module 4 to capture the first initial image of the circular hole reaching the second irradiation area 31 at intervals of the third preset duration. See [link to relevant documentation]. Figure 6The first image in the document. The third preset duration can be obtained based on the interval between the first irradiation area 21 and the second irradiation area 31, the material conveying speed, etc. Then, at fourth preset duration intervals, the image acquisition module 4 acquires several initial images of the circular hole in the material passing through the second irradiation area 31. See [link / reference]. Figure 6 The second and third images are shown. Similarly, the fourth preset duration can be obtained based on the diameter of the circular hole, the width of the first irradiation area 21, the number of images, the material conveying speed, etc. The control module transmits each initial image and its encoder reading at the time of capture to the processing module; Before stitching images together, they need to be aligned; for example: • Coordinate mapping relationship establishment: The mapping relationship k (unit: pixels / mm) of "physical displacement of board material - pixel displacement of image" is obtained in advance through system calibration. The calibration method is as follows: take the intersection of two checkerboard grids in the standard checkerboard template, one point is taken near the upper edge of the image, and the other point is taken near the lower edge. The mapping relationship k is obtained through pixel interval / physical interval.
[0039] • Motion offset calculation: The control module reads the encoder readings E_1 and E_2 when the image acquisition module 4 is triggered twice, and calculates the encoder reading difference DE = |E_2 - E_1|. Combined with the pre-calibrated mapping coefficient k, the physical displacement of the encoder is converted into the image pixel-level offset: (DP is the image pixel offset) DP = k * DE.
[0040] • Fast image alignment: Based on the calculated pixel offset DP, the image captured later is transformed in the y direction so that the positions of the circular holes in the two images completely overlap, thus completing the alignment. The alignment accuracy is ≤0.8 pixels and the registration time is ≤0.5ms (this method is more than 4 times faster than the ORB algorithm).
[0041] For example, it can be Figure 5 The second and third images in the image are aligned with the first image. Figure 6 All three pictures in the video are related to... Figure 5 The first image in the image is aligned.
[0042] After alignment, the initial images are cropped using circular holes and then stitched together. For example: Based on the calculated edge position of the board, the actual area of the circular hole in the image is directly estimated using pixel ratios. Combining this with the known standard size of the circular hole, the minimum effective area containing the hole is calculated and cropped proportionally (e.g., 1.2 times the diameter), ensuring that the cropped area covers the hole and its surrounding area with appropriate margin. The estimated cropped area is then reconfirmed. If the distance between the cropped area boundary and the edge of the circular hole is less than 5 pixels, the area is expanded outward to 5 pixels to avoid loss of edge information, thus obtaining the final circular hole processing area. This method can reduce the area of a single circular hole processing region to 5%-10% of the original image, significantly reducing the amount of subsequent computation.
[0043] It should be noted that the edge position of the board can be determined during the circular hole detection process by first collecting the encoder readings of the left and upper edges of the board entering the first irradiation area 21, and then calculating the relative position of the circular hole in the initial image from the edge of the board based on the encoder difference when the circular hole enters the first irradiation area 21. By analogy, the position of the circular hole in each image can be estimated, thereby enabling the extraction of the circular hole.
[0044] After stitching together the first and second images of the complete circular hole within the first illumination area 21 and the second illumination area 31, the first and second images are converted to grayscale (RGB images are converted to single-channel grayscale images) to preserve edge features while eliminating random noise. Then, the first and second images are paired pixel by pixel, and the smaller grayscale value of each pixel is selected as the pixel value of the fused image. This ensures that the area of reflection from the first light source in the second image corresponds to a low grayscale value, and the area of halo from the second light source in the first image corresponds to a low grayscale value. After fusion, the interference of reflection and halo is effectively suppressed, and the grayscale gradient at the edge of the circular hole is clear.
[0045] In summary, the circular hole recognition method for sheet metal of this invention replaces the traditional feature point matching algorithm with a registration scheme of "position coordinate transformation + pixel mapping". The registration time is reduced from ≥2ms to ≤0.5ms, and it is not affected by oil stains or scratches on the sheet metal surface. The registration accuracy is stable at ≤0.8 pixels, making it suitable for high-speed motion scenarios. By "real-time displacement acquisition + synchronous triggering", it achieves non-stop acquisition from dual light sources. Combined with fast coordinate transformation registration, it perfectly solves the problem of "motion acquisition misalignment", making it suitable for motion pipelines of about 1m / s and breaking the dependence of traditional dual-light source methods on static workpieces. The differentiated design of dual light source directions + pixel-level grayscale minimum value fusion eliminates reflection and halo interference from the acquisition source. The purity of the circular hole feature in the fused image is improved by more than 80% compared with the single light source image, and the false edges are reduced by 90%. The three-level speed-up design of "fast registration (≤0.5ms) + region clipping (reducing invalid calculations by 90%) + simplified Hough transform" reduces the overall computational complexity to O. (K×L) (K and L are the pixel size of the cropped area), which is 98% lower than the traditional method; the registration accuracy is ≤0.8 pixels, and the high signal-to-noise ratio of the fused image controls the fitting error within ±0.01mm, achieving a balance between "ultra-high speed detection (≥120 frames / second)" and "high-precision recognition (≥99% accuracy)".
[0046] It should be noted that all the devices (parts whose specific structures are not specified) selected in this application are general standard parts or parts known to those skilled in the art, and their structures and principles can be known to those skilled in the art through technical manuals or conventional experimental methods.
[0047] In the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.
[0048] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0049] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0050] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0051] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0052] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. A method for identifying round holes in a sheet metal, characterized in that, include: Obtain a first image of the circular hole in the board material under the illumination of the first light source; A second image of the circular hole in the board material is obtained under the illumination of the second light source; the emitted light from both the first and second light sources is obliquely illuminating the surface of the board material, and the oblique directions are opposite. Perform grayscale conversion on the first and second images; The first and second images are paired pixel by pixel, and the smaller gray value of each pixel is selected as the pixel value of the fused image to obtain the final circular hole image.
2. The method for identifying circular holes in a sheet metal according to claim 1, characterized in that, The emitted light from the first light source is tilted downstream; The emitted light from the second light source is tilted upstream.
3. The method for identifying circular holes in a sheet metal according to claim 1, characterized in that, The first light source and the second light source are spaced a certain distance apart on the surface of the plate.
4. The method for identifying circular holes in a sheet metal according to claim 1, characterized in that, The method for acquiring the first image or acquiring the second image includes: During the conveying process of the sheet material, several initial images of the sheet material's circular holes passing through the illumination area of the corresponding light source are continuously acquired at preset displacement intervals. Crops out the effective region image containing the circular hole from the initial image; Several effective area images under the same illumination area are stitched together to form a first image or a second image.
5. The method for identifying circular holes in a sheet metal according to claim 4, characterized in that, The method for cropping an effective region image containing a circular hole based on an initial image includes: Image cropping is performed based on the estimated range obtained by multiplying the diameter of the circular hole by the magnification factor; and The image cropped according to the estimated range is reconfirmed. If the distance between the cropped area boundary and the edge of the circular hole is less than 5 pixels, it is expanded outward to 5 pixels.
6. A system for identifying round holes in sheet metal, characterized in that, include: The first image acquisition module is used to acquire a first image of the circular hole in the board material under the illumination of the first light source; The second image acquisition module is used to acquire a second image of the circular hole in the board material under the illumination of the second light source; the emitted light from the first light source and the second light source are both obliquely illuminating the surface of the board material, and the oblique directions are opposite. The grayscale conversion module is used to perform grayscale conversion on the first image and the second image; The image fusion module is used to pair the first image and the second image pixel by pixel, select the smaller gray value of each pixel as the pixel value of the fused image, and obtain the final circular hole image.
7. A device for identifying round holes in sheet metal, characterized in that, include: A conveying device for conveying sheet metal along the y-direction; The first light source and the second light source are used to form a first irradiation area and a second irradiation area that are spaced apart along the y direction on the conveying device; An image acquisition module, located above the conveying device, is used to acquire images of the board material. The control module is electrically connected to the conveying device, the first light source, the second light source, and the image acquisition module. It is used to control the image acquisition module to continuously acquire several initial images of the circular holes in the plate passing through the illumination area of the corresponding light source at preset displacement intervals. The processing module is used to stitch together several initial images under the same illumination area into a first image or a second image; and to execute the plate circular hole recognition method as described in claim 1 to obtain the final circular hole image.
8. The plate hole identification device according to claim 7, characterized in that, Also includes: The initial position detection module, electrically connected to the control module, is located upstream of the first light source and is used to detect whether the circular hole in the board has reached the initial position. After the circular hole in the board reaches its initial position, the control module controls the image acquisition module to acquire a first initial image of the circular hole reaching the first illumination area at a first preset time interval. Then, at a second preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole passing through the first illumination area. After acquiring the last initial image of the circular hole in the board passing through the first irradiation area, the control module controls the image acquisition module to acquire the first initial image of the circular hole in the board reaching the second irradiation area at a third preset time interval. Then, at a fourth preset time interval, the control module controls the image acquisition module to acquire several initial images of the circular hole in the board passing through the second irradiation area.
9. The plate hole identification device according to claim 7, characterized in that, The conveying device includes an encoder electrically connected to the control module; The control module acquires the encoder reading at the same time as the image acquisition module acquires each initial image. The processing module calculates the corresponding pixel offset based on the displacement offset between the initial images, and stitches or merges the initial images based on the corresponding pixel offset.