Multifunctional computer detection equipment and operation method thereof

Abstract

The invention provides multifunctional computer detection equipment and an operation method thereof, relates to the technical field of computer detection equipment, and aims to effectively remove image noise and burrs caused by chippings in a processing process by performing multiple image processing on a processing image, ensure accurate identification of image edges and improve the processing efficiency. And further, the material processing precision is improved. And meanwhile, the illumination intensity is adaptively adjusted in a manner of gradually refining the multi-stage subintervals, so that the image acquisition is performed under the optimal illumination condition, the image quality is improved, and the interference of noise and shadow is reduced. The whole scheme realizes automation and intelligence, can adapt to different working environments and material types, reduces human intervention, and improves the operation convenience and the comprehensive performance of the system. And furthermore, the rejection rate of materials is reduced, the economic benefit is remarkably improved, and therefore the high-strength and high-user satisfaction degree can be achieved on the market.

Description

Technical Field

[0001] The present invention relates to the technical field of computer detection equipment, in particular to a multifunctional computer detection equipment and an operation method thereof. Background Art

[0002] In modern industrial production, the processing accuracy and efficiency of materials directly affect the quality and production cost of products. Traditional CNC machine tool processing systems usually rely on fixed lighting conditions and simple image processing algorithms. These systems have many deficiencies in the process of image acquisition, processing and analysis, such as unstable lighting conditions leading to poor image quality, simple image processing algorithms cannot effectively remove noise, and the recognized image edges are inaccurate. Especially after working for a period of time, the debris on the CNC machine tool is easy to form subtle noise patterns, which affects the recognition effect of the image edge, and then affects the quality and accuracy of material processing. In addition, most of the lighting control modules in the prior art are based on fixed light intensity or heuristic rules, and cannot adaptively adjust the light intensity to cope with different materials and working environments, resulting in low adaptability and intelligence of the system. In recent years, with the development of industrial cameras and high-performance processors, combined with the progress of image processing technology, how to design a set of highly automated and intelligent multifunctional computer detection equipment to solve the above problems has become a technical problem that needs to be solved urgently.

[0003] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0004] The object of the present invention is to provide a multifunctional computer detection device and an operation method thereof to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A multifunctional computer detection device, comprising:

[0007] An image acquisition module, which is electrically connected to the image analysis module and is used to acquire a processing image of the material to be processed and send it to the image analysis module;

[0008] An image analysis module, which is electrically connected to the data analysis module and is used to perform image processing on the processed image and send the processed processed image to the data analysis module;

[0009] A data analysis module, which is electrically connected to the material processing module and the comprehensive processing module and is preset with an image processing algorithm, and is used to substitute the processed image into the image processing algorithm to identify the image edge of the processed image, and send the processed image after identification to the material processing module and the comprehensive processing module;

[0010] A material processing module, wherein the material processing module is used to process the material to be processed according to the processed image after the recognition is completed;

[0011] A comprehensive processing module, which is electrically connected to the lighting control module and is used to generate an error ratio between the image area of ​​the material to be processed in the processing image and the preset actual area of ​​the material to be processed, and send a control signal to the lighting control module according to the error ratio;

[0012] The lighting control module includes a control unit and a lighting unit. The control unit is electrically connected to the data analysis module and is used to adjust the light intensity of the lighting unit according to a control signal. The lighting unit is electrically connected to the control unit and is used to illuminate the material to be processed.

[0013] Preferably, the image processing includes image cropping and grayscale conversion, which are used to unify the image size of the processed images and convert the processed images of the same size into corresponding grayscale images.

[0014] Preferably, the image edge recognition logic of the processed image is:

[0015] Generate a corresponding image threshold according to the processed image, use the image threshold to perform binarization processing on the processed image, and obtain a binary image of the processed image;

[0016] Perform an opening operation on the binary image of the processed image, then perform connected component analysis to find all connected regions and calculate the area of ​​each connected region;

[0017] The area of ​​each connected region is compared with a preset area threshold, and the connected regions with an area smaller than the area threshold are deleted to obtain the final binary edge image.

[0018] Preferably, the generation logic of the image threshold is:

[0019] Generate the grayscale histogram and normalized histogram of the processed image after image processing, and then calculate the weights of the foreground and background of the processed image. The calculation formula is:

[0020]

[0021] Where W B (k), W F(k) represents the weights of foreground and background, P(i) represents the normalized frequency of the i-th pixel, L represents the grayscale level, and k represents the segmentation threshold;

[0022] According to the weights of the foreground and background of the processed image, the corresponding average gray value is calculated using the following formula:

[0023]

[0024] Where H B (k), H F (k) represents the average gray value of foreground and background respectively;

[0025] Then, the inter-class variance is calculated based on the weights and average grayscale values ​​of the foreground and background of the processed image. The calculation formula is:

[0026]

[0027] In the formula It represents the inter-class variance when the segmentation threshold is k. The value range of k is traversed and the k value that maximizes the inter-class variance is selected as the final image threshold.

[0028] Preferably, the maximum area of ​​all connected regions is calibrated as S max , area threshold S y =τ·S max , where τ represents the fluctuation coefficient, and the fluctuation coefficient is calculated by the number of connected regions. The calculation method of the fluctuation coefficient τ is:

[0029]

[0030] Where M represents the number of connected regions, and M is a positive integer.

[0031] Preferably, the logic for adjusting the lighting control module is:

[0032] The adjustable range of light intensity is divided into k1 first-level sub-intervals, and the error ratio corresponding to the light intensity when the light intensity is the minimum value of each first-level sub-interval is calculated respectively;

[0033] The first-level sub-interval with the smallest error ratio is divided into k2 second-level sub-intervals, and the second sub-interval with the smallest error ratio is found and divided again. Similarly, after n divisions, when each n-level sub-interval contains only one data, the division is considered to be completed, and the data in the n-level sub-interval with the smallest error ratio is used as the optimal light intensity corresponding to the material to be processed.

[0034] Preferably, the error ratio The calculation method is: Where s0 is the preset actual area.

[0035] A method for operating a multifunctional computer detection device, the method being applicable to the above detection device, and comprising the following specific steps:

[0036] S1: Collect the size data of the material to be processed, calculate the corresponding actual area, and pre-process the material to be processed;

[0037] S2: collecting a processing image of the material to be processed during the pre-processing process, performing image processing on the processing image, identifying the image edge of the material to be processed in the processing image, and generating an error ratio based on the processing image and the actual area;

[0038] S3: Adjust the illumination intensity to generate error ratios under different illumination intensities, take the illumination intensity with the smallest error ratio as the optimal illumination intensity, and bind and store the optimal illumination intensity with the material number of the material to be processed.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention effectively removes image noise and burrs caused by debris during the processing process by performing multiple image processing on the processed image, ensuring accurate identification of image edges, thereby improving the accuracy of material processing. At the same time, the light intensity is adaptively adjusted by gradually refining the multi-level sub-intervals to ensure that image acquisition is carried out under optimal lighting conditions, thereby improving image quality and reducing interference from noise and shadows. The overall solution realizes automation and intelligence, can adapt to different working environments and material types, reduces human intervention, and improves the convenience of operation and the overall performance of the system. Furthermore, the scrap rate of materials is reduced, and the economic benefits are significantly improved, making the present invention more competitive and with higher user satisfaction in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the module structure of the present invention;

[0042] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0043] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0044] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0045] Example:

[0046] See also Figure 1 , the present invention provides a technical solution:

[0047] A multifunctional computer detection device comprises: an image acquisition module, an image analysis module, a data analysis module, a material processing module, a comprehensive processing module and a lighting control module.

[0048] The image acquisition module is electrically connected to the image analysis module, and a high-resolution industrial camera of the Basler acA1920-40uc series may be used to acquire the processing image of the material to be processed and send it to the image analysis module.

[0049] The image analysis module is electrically connected to the data analysis module, and can use a high-performance embedded processor of the NVIDIA Jetson Xavier series to process the processed image and send the processed image to the data analysis module. The image processing includes image cropping and grayscale conversion, which are used to unify the image size of the processed image and convert the processed images of the same size into corresponding grayscale images. The grayscale image is converted using a weighted average method. The specific conversion method can be expressed as:

[0050] H(x,y)y)=0.299·R(x,y)+0.587·G(x,y)+0.114B(x,y)

[0051] Where H(x,y) represents the grayscale value of the pixel with coordinates (x,y), R(x,y), G(x,y), and B(x,y) represent the red, green, and blue channel components of the pixel with coordinates (x,y), respectively.

[0052] The data analysis module is electrically connected to the material processing module and the comprehensive processing module, and is preset with an image processing algorithm. It can use an Intel Core series high-performance CPU to substitute the processed image into the image processing algorithm to identify the image edge of the processed image, and send the processed image after identification to the material processing module and the comprehensive processing module.

[0053] The material processing module uses a CNC machine tool to process the material to be processed according to the processing image after recognition.

[0054] The comprehensive processing module is electrically connected to the lighting control module and can use a high-performance processor of the Raspberry Pi series to generate an error ratio between the image area of ​​the material to be processed in the processing image and the preset actual area of ​​the material to be processed, and send a control signal to the lighting control module according to the error ratio.

[0055] The lighting control module includes a control unit and a lighting unit. The control unit is electrically connected to the data analysis module and can use a Siemens S7-1200 series PLC controller to adjust the light intensity of the lighting unit according to a control signal. The lighting unit is electrically connected to the control unit and can use a Thorlabs LEDD1B series brightness-adjustable LED to illuminate the material to be processed.

[0056] The image acquisition module, image analysis module, data analysis module and comprehensive processing module can be integrated on the same PCB board to control the material processing module and lighting control module. The combination of the above modules enables the entire multifunctional computer detection equipment to maintain high efficiency and accuracy in the entire process of acquisition, processing, analysis and processing. The close cooperation between the modules and the use of high-performance equipment ensure the real-time and reliability of the system.

[0057] The image edge recognition logic of the processed image is:

[0058] A corresponding image threshold is generated according to the processed image, and the processed image is binarized using the image threshold to obtain a binary image of the processed image.

[0059] The logic for generating image threshold is:

[0060] Generate the grayscale histogram and normalized histogram of the processed image after image processing, and then calculate the weights of the foreground and background of the processed image. The calculation formula is:

[0061]

[0062] Where W B (k), W F(k) represents the weights of foreground and background, P(i) represents the normalized frequency of the i-th pixel, L represents the grayscale level, and k represents the segmentation threshold;

[0063] According to the weights of the foreground and background of the processed image, the corresponding average gray value is calculated using the following formula:

[0064]

[0065] Where H B (k), H F (k) represents the average gray value of foreground and background respectively;

[0066] Then, the inter-class variance is calculated based on the weights and average grayscale values ​​of the foreground and background of the processed image. The calculation formula is:

[0067]

[0068] In the formula It represents the inter-class variance when the segmentation threshold is k. The value range of k is traversed and the k value that maximizes the inter-class variance is selected as the final image threshold.

[0069] In this step, the image threshold is set based on the Otsu algorithm. By automatically calculating the inter-class variance, the system has stronger adaptability and can automatically adjust the threshold according to the image features, resulting in better segmentation effect. The system can adapt to different lighting conditions and image quality, enhance the adaptability and robustness of the system, improve the reliability of the overall system, and significantly improve the intelligence level and processing capabilities of the system, making this multifunctional detection equipment more competitive in the market and with higher user satisfaction.

[0070] The binary image of the processed image is opened, and then connected component analysis is performed to find all connected regions and calculate the area of ​​each connected region.

[0071] The maximum area of ​​all connected regions is marked as S max , area threshold S y =τ·S max , where τ represents the fluctuation coefficient, and the fluctuation coefficient is calculated by the number of connected regions. The calculation method of the fluctuation coefficient τ is:

[0072]

[0073] Where M represents the number of connected regions, and M is a positive integer.

[0074] It is understandable that in the process of industrial material processing, the debris generated during the processing process is usually cleaned up, so the remaining debris usually does not have a large image, but a scattered fragmented image. Therefore, in the processed image after the opening operation, the debris that is close to the edge of the material to be processed and forms burrs has been removed, and only the material to be processed with the largest area and several groups of smaller debris are left in the connected area. The size of the fluctuation coefficient is inversely proportional to the number of connected areas, because the more connected areas there are, the more dispersed the debris is, the smaller the area of ​​the corresponding noise figure is, and the smaller the area of ​​the corresponding area threshold is. Conversely, the more connected areas there are, the more concentrated the debris is, the larger the area of ​​the corresponding noise figure is, and the larger the area of ​​the corresponding area threshold is.

[0075] The area of ​​each connected region is compared with a preset area threshold, and the connected regions with an area smaller than the area threshold are deleted to obtain the final binary edge image.

[0076] In the prior art, the image edge of the processed image is usually found by gradient calculation, so as to facilitate the control of the CNC machine tool to process the material edge of the material to be processed. However, after working for a period of time, there are small debris on the CNC machine tool, and the brush of the CNC machine tool cannot completely clean all the debris. Then these debris are easy to form various subtle noise patterns in the processed image, which not only affects the recognition effect of the image edge in the processed image, but also if the debris is close to the material edge of the material to be processed, it is easy to make the identified image edge have more burrs, which will also affect the subsequent processing. In this step of the present scheme, the binarization process makes the target area and the background area in the image more clearly separated, which is helpful for the subsequent opening operation and connected component analysis. The opening operation includes first performing an erosion operation on the binary image and then performing an expansion operation, which can effectively remove the burrs on the edge of the binary image, making the identified image edge smoother and more accurate. The connected component analysis provides detailed regional information, which is convenient for subsequent screening according to the area threshold. By using the preset area threshold, the connected areas with an area smaller than the threshold are deleted, and the noise graphics formed by the debris can be removed, reducing misidentification and interference, and improving the accuracy and efficiency of image processing. This can not only enhance the robustness and adaptability of the system, but also improve the quality and accuracy of material processing, reduce the scrap rate of materials, and play a role in improving economic benefits.

[0077] The logic for adjusting the lighting control module is:

[0078] The adjustable range of light intensity is divided into k1 first-level sub-intervals, and the error ratio corresponding to the light intensity when the light intensity is the minimum value of each first-level sub-interval is calculated respectively;

[0079] The first-level sub-interval with the smallest error ratio is divided into k2 second-level sub-intervals, and the second sub-interval with the smallest error ratio is found and divided again. Similarly, after n divisions, when each n-level sub-interval contains only one data, the division is considered to be completed, and the data in the n-level sub-interval with the smallest error ratio is used as the optimal light intensity corresponding to the material to be processed.

[0080] Error ratio The calculation method is: Where S0 is the preset actual area.

[0081] It is understandable that different materials to be processed have different shapes, size data, etc., so the quality of the processed images generated under different light intensities is also different. By accurately adjusting the light intensity, it is ensured that image acquisition is carried out under optimal lighting conditions, which improves image quality and reduces interference from noise and shadows. Adaptive light adjustment enables the system to adapt to different working environments and materials, improves the intelligence level of the system, reduces human intervention, and improves the convenience of operation.

[0082] See also Figure 2 The present invention also provides an operation method of a multifunctional computer detection device, which is applicable to the above detection device, and the specific steps include:

[0083] S1: Collect the size data of the material to be processed, calculate the corresponding actual area, and pre-process the material to be processed;

[0084] S2: collecting a processing image of the material to be processed during the pre-processing process, performing image processing on the processing image, identifying the image edge of the material to be processed in the processing image, and generating an error ratio based on the processing image and the actual area;

[0085] S3: Adjust the illumination intensity to generate error ratios under different illumination intensities, take the illumination intensity with the smallest error ratio as the optimal illumination intensity, and bind and store the optimal illumination intensity with the material number of the material to be processed.

[0086] In summary, the present invention effectively removes image noise and burrs caused by debris during the processing process by performing multiple image processing on the processed image, ensuring accurate identification of image edges, thereby improving the accuracy of material processing. At the same time, the light intensity is adaptively adjusted by gradually refining the multi-level sub-intervals to ensure that image acquisition is carried out under optimal lighting conditions, thereby improving image quality and reducing interference from noise and shadows. The overall solution realizes automation and intelligence, can adapt to different working environments and material types, reduces human intervention, and improves the convenience of operation and the overall performance of the system. Furthermore, the scrap rate of materials is reduced, and the economic benefits are significantly improved, making the present invention more competitive and with higher user satisfaction in the market.

[0087] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0088] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A multifunctional computer detection device, characterized in that: include: An image acquisition module, which is electrically connected to the image analysis module and is used to acquire a processing image of the material to be processed and send it to the image analysis module; An image analysis module, which is electrically connected to the data analysis module and is used to perform image processing on the processed image and send the processed processed image to the data analysis module; A data analysis module, which is electrically connected to the material processing module and the comprehensive processing module and is preset with an image processing algorithm, and is used to substitute the processed image into the image processing algorithm to identify the image edge of the processed image, and send the processed image after identification to the material processing module and the comprehensive processing module; A material processing module, wherein the material processing module is used to process the material to be processed according to the processed image after the recognition is completed; A comprehensive processing module, which is electrically connected to the lighting control module and is used to generate an error ratio between the image area of ​​the material to be processed in the processing image and the preset actual area of ​​the material to be processed, and send a control signal to the lighting control module according to the error ratio; The lighting control module includes a control unit and a lighting unit. The control unit is electrically connected to the data analysis module and is used to adjust the light intensity of the lighting unit according to a control signal. The lighting unit is electrically connected to the control unit and is used to illuminate the material to be processed.

2. A multifunctional computer detection device according to claim 1, characterized in that: The image processing includes image cropping and grayscale conversion, which are used to unify the image size of processed images and convert processed images of the same size into corresponding grayscale images.

3. A multifunctional computer detection device according to claim 2, characterized in that: The image edge recognition logic of the processed image is: Generate a corresponding image threshold according to the processed image, use the image threshold to perform binarization processing on the processed image, and obtain a binary image of the processed image; Perform an opening operation on the binary image of the processed image, then perform connected component analysis to find all connected regions and calculate the area of ​​each connected region; The area of ​​each connected region is compared with a preset area threshold, and the connected regions with an area smaller than the area threshold are deleted to obtain the final binary edge image.

4. A multifunctional computer detection device according to claim 3, characterized in that: The generation logic of the image threshold is: Generate the grayscale histogram and normalized histogram of the processed image after image processing, and then calculate the weights of the foreground and background of the processed image. The calculation formula is: Where W B (k), W F (k) represents the weights of foreground and background, P(i) represents the normalized frequency of the i-th pixel, L represents the grayscale level, and k represents the segmentation threshold; According to the weights of the foreground and background of the processed image, the corresponding average gray value is calculated using the following formula: Where H B (k), H F (k) represents the average gray value of foreground and background respectively; Then, the inter-class variance is calculated based on the weights and average grayscale values ​​of the foreground and background of the processed image. The calculation formula is: In the formula It represents the inter-class variance when the segmentation threshold is k. The value range of k is traversed and the k value that maximizes the inter-class variance is selected as the final image threshold.

5. A multifunctional computer detection device according to claim 3, characterized in that: The maximum area of ​​all connected regions is marked as S max , area threshold S y =τ·S max , where τ represents the fluctuation coefficient, and the fluctuation coefficient is calculated by the number of connected regions. The calculation method of the fluctuation coefficient τ is: Where M represents the number of connected regions, and M is a positive integer.

6. A multifunctional computer detection device according to claim 5, characterized in that: The logic for adjusting the lighting control module is: The adjustable range of light intensity is divided into k1 first-level sub-intervals, and the error ratio corresponding to the light intensity when the light intensity is the minimum value of each first-level sub-interval is calculated respectively; The first-level sub-interval with the smallest error ratio is further divided into k2 second-level sub-intervals, and the second sub-interval with the smallest error ratio is found and divided again. Similarly, after n divisions, when each n-level sub-interval contains only one data, the division is considered to be completed, and the data in the n-level sub-interval with the smallest error ratio is used as the optimal light intensity corresponding to the material to be processed.

7. A multifunctional computer detection device according to claim 6, characterized in that: The error ratio The calculation method is: Where S0 is the preset actual area.

8. A method for operating a multifunctional computer detection device, characterized in that: The operating method is applicable to the detection device according to any one of claims 1 to 7, and the specific steps include: S1: Collect the size data of the material to be processed, calculate the corresponding actual area, and pre-process the material to be processed; S2: collecting a processing image of the material to be processed during the pre-processing process, performing image processing on the processing image, identifying the image edge of the material to be processed in the processing image, and generating an error ratio based on the processing image and the actual area; S3: Adjust the illumination intensity to generate error ratios under different illumination intensities, take the illumination intensity with the smallest error ratio as the optimal illumination intensity, and bind and store the optimal illumination intensity with the material number of the material to be processed.

Images