A method and system for detecting the polishing quality of injection molded parts

Abstract

The present invention relates to the field of image processing technology, and in particular to a method and system for detecting the polishing quality of injection molded parts. The method comprises the steps of: collecting an injection molded part polishing image, obtaining the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point, obtaining the local feature intensity of each pixel point based on the gradient amplitude and the surrounding pixels point, merging the pixels points according to the difference in the local feature intensity between the pixels points to obtain a plurality of blocks, adaptively obtaining the optimal low threshold of each block according to the local feature intensity of the pixels in each block, obtaining the high threshold of each block according to the optimal low threshold of each block; obtaining the edge pixel points of each block according to the optimal low threshold and high threshold of each block, and evaluating the polishing quality of the injection molded part according to the edge pixel points in each block. The present invention improves the accuracy of defect detection.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for detecting the polishing quality of injection molded parts. Background Art

[0002] Inspecting the polishing quality of injection molded parts is a crucial step in ensuring product quality in the manufacturing industry. Traditional methods rely primarily on manual visual inspection, which is inefficient and limited by operator experience and fatigue, easily leading to misjudgments or missed detections. With the advancement of image processing technology, automated inspection systems are increasingly being used in injection molded part polishing quality inspection, analyzing images of the part surface to identify defects.

[0003] In the process of inspecting the polishing quality of injection molded parts, the Canny edge detection algorithm is usually used to detect the edges of defective areas. The Canny edge detection algorithm calculates the gradient amplitude of each pixel in the injection molded part polishing image and identifies the edge by judging the relationship between the gradient amplitude of the pixel and the preset high threshold and low threshold. The high threshold is the gradient amplitude threshold used to determine strong edges. If the gradient amplitude is greater than the high threshold, the pixel is marked as a "strong edge pixel". The low threshold is the gradient amplitude threshold used to determine weak edges. If the gradient amplitude is between the high threshold and the low threshold, the pixel is marked as a "weak edge pixel". The pixels less than the low threshold are discarded, thereby identifying the defective edges in the injection molded part polishing image.

[0004] Since there are defect features of different intensities in the polished images of injection molded parts, that is, some defects have large grayscale value differences from the surrounding areas, while some defects have small grayscale value differences from the surrounding areas, the fixed high and low thresholds set by the traditional Canny edge detection algorithm cannot effectively identify defect features. For defect areas with obvious grayscale changes, the fixed threshold may be too high, causing these features to be ignored; and for defect areas with insignificant grayscale changes, the fixed threshold may be too low, causing some non-defective edges to be mistakenly identified as defect features, resulting in inaccurate quality inspection results. Summary of the Invention

[0005] In order to solve the technical problem that fixed high and low thresholds set by the Canny edge detection algorithm cannot effectively identify defects, the present invention provides a method and system for detecting the polishing quality of injection molded parts.

[0006] In a first aspect, the present invention provides a method for inspecting the polishing quality of injection molded parts, which adopts the following technical solution:

[0007] A method for inspecting the polishing quality of injection molded parts, comprising the steps of:

[0008] Collect images of injection molded parts being polished;

[0009] Obtaining the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point, and obtaining the local feature intensity of each pixel point based on the gradient amplitude and the surrounding pixels points;

[0010] Based on the difference in local feature intensities between pixels, the pixels in the injection molded part polishing image are merged to obtain several blocks; based on the average of the local feature intensities of all pixels in each block, the optimal low threshold of each block is obtained; based on the optimal low threshold of each block, the high threshold of each block is obtained; based on the optimal low threshold and high threshold of each block, the edge pixels of each block are obtained;

[0011] The polishing quality of injection molded parts is evaluated based on the edge pixels in each block.

[0012] The innovation of the present invention lies in obtaining the local feature intensity of each pixel point based on the local features of each pixel point, and then merging the pixels based on the difference in the local feature intensity of the pixel point quality inspection, which can merge defects of different degrees into separate blocks, so as to facilitate the subsequent adaptive acquisition of the optimal low threshold value of each block; then, based on the local feature intensity of the pixel points in each block, the optimal low threshold value of each block is adaptively obtained, and the low threshold value is increased for blocks with a large degree of defects to avoid detecting details that are not defects. The low threshold value is downgraded for blocks with a small degree of defects to facilitate the detection of weak defect edges and improve the accuracy of defect detection.

[0013] Preferably, obtaining the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point includes:

[0014] The Sobel operator is used to obtain the gradient amplitude of each pixel in the injection molded part polishing image, and the eight neighborhood pixels of each pixel in the injection molded part polishing image are recorded as the surrounding pixels of each pixel.

[0015] Preferably, obtaining the local feature intensity of each pixel includes:

[0016] ;

[0017] Where, Represents the local feature intensity of the i-th pixel; Represents the gradient amplitude of the i-th pixel; Represents the number of pixels surrounding the i-th pixel; Represents the gradient amplitude of the jth surrounding pixel of the i-th pixel; norm() represents the normalization function.

[0018] It can reflect the local features of each pixel, making it easier to merge pixels with similar features into blocks.

[0019] Preferably, the obtaining of a plurality of blocks includes:

[0020] A feature threshold Q1 is preset, and the absolute value of the difference in local feature intensity between the i-th pixel and each pixel in its four neighborhoods is recorded as the feature difference value between the i-th pixel and each of its four neighborhood pixels. All four neighborhood pixels whose feature difference values ​​are less than Q1 are recorded as the target pixels of the i-th pixel; the i-th pixel is merged with all its target pixels to obtain the i-th block; the target pixel of each pixel in the i-th block is obtained, and it is merged with the i-th block to obtain a new i-th block; and so on, until there is no target pixel for each pixel in the new i-th block, and the new i-th block is recorded as the i-th block; and each block is obtained.

[0021] The pixels belonging to the same area can be merged together to obtain blocks, which facilitates the subsequent adaptive acquisition of the optimal low threshold for each block.

[0022] Preferably, obtaining the optimal low threshold value for each block includes:

[0023] ;

[0024] Where, represents the optimal low threshold of the b-th block; Represents the preset low threshold; Represents the mean of the local feature intensity of all pixels in the b-th block; Represents the preset local feature intensity reference value; Represents the preset hyperparameters.

[0025] For blocks with large defects, the low threshold is increased to avoid detecting details that are not defects. For blocks with small defects, the low threshold is lowered to facilitate the detection of weak defect edges, thereby improving the accuracy of defect detection.

[0026] Preferably, obtaining the high threshold of each block according to the optimal low threshold of each block includes:

[0027] The double of the optimal low threshold of each block is used as the high threshold of each block.

[0028] Preferably, obtaining edge pixel points of each block according to the optimal low threshold and high threshold of each block includes:

[0029] The pixels in the bth block whose gradient amplitude is greater than the high threshold are regarded as the strong edge pixels of the bth block, the pixels in the bth block whose gradient amplitude is between the high threshold and the low threshold are regarded as the weak edge pixels of the bth block, and the strong edge pixels of the bth block and the weak edge points in the eight-neighborhood range of its strong edge pixels are regarded as the edge pixels of the bth block.

[0030] Preferably, the evaluating the polishing quality of the injection molded part according to the edge pixel points in each block includes:

[0031] A pixel number threshold T2 is preset; based on the edge pixels in each block, several edges of the injection molded part polishing image are obtained. If the total number of pixels of any edge of the injection molded part polishing image is greater than the pixel number threshold T2, the edge is recorded as the target edge of the injection molded part polishing image, and all target edges of the injection molded part polishing image are obtained;

[0032] If the ratio of the number of pixels of all target edges of the injection molded part polishing image to the number of pixels in the injection molded part polishing image is greater than 0.1, the system will issue an early warning to remind the staff that the quality of the injection molded part polishing is unqualified.

[0033] The accuracy of defect detection is improved, and defects of different degrees can be detected.

[0034] Preferably, collecting the injection molded part polishing image includes:

[0035] A high-resolution CMOS camera is used to shoot the polished surface of the injection molded part, and an RGB image of the injection molded part polishing is collected. The RGB image of the injection molded part polishing is grayscaled and recorded as the injection molded part polishing image.

[0036] In a second aspect, the present invention provides an injection molded part polishing quality inspection system, which adopts the following technical solution:

[0037] A system for inspecting the polishing quality of injection molded parts includes a processor and a memory. The memory stores computer program instructions. When the computer program instructions are executed by the processor, the above-mentioned method for inspecting the polishing quality of injection molded parts is implemented.

[0038] By adopting the above technical solution, the above-mentioned method for inspecting the polishing quality of injection molded parts is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby manufacturing a terminal device based on the memory and the processor for easy use.

[0039] The present invention has the following technical effects: the purpose of the present invention is to obtain the local feature intensity of each pixel point according to the local features of each pixel point, and then merge the pixels according to the difference in the local feature intensity of the pixel point quality inspection, so that defects of different degrees can be merged into blocks respectively, which is convenient for subsequent adaptive acquisition of the optimal low threshold of each block; then, according to the local feature intensity of the pixel points in each block, the optimal low threshold of each block is adaptively obtained, and the low threshold is increased for blocks with a large degree of defects to avoid detecting details that are not defects. The low threshold is downgraded for blocks with a small degree of defects to facilitate the detection of weak defect edges and improve the accuracy of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding numbers represent the same or corresponding parts.

[0041] Figure 1 This is a flow chart of a method for inspecting the polishing quality of injection molded parts according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0043] The embodiment of the present invention discloses a method for inspecting the polishing quality of injection molded parts. Figure 1 , including steps S1 to S4:

[0044] S1: Collect images of injection molded parts being polished.

[0045] It should be noted that the present invention first needs to collect the surface image of the injection molded part after polishing, and then evaluate the polishing quality of the injection molded part by using an image processing algorithm.

[0046] In the implementation of the present invention, a high-resolution CMOS camera is used to shoot the polished surface of the injection molded part to collect the polished RGB image of the injection molded part. It should be noted that the focus and aperture are adjusted during shooting to ensure a clear focus on the surface of the injection molded part.

[0047] The RGB image of the injection molded part polishing is converted into grayscale and recorded as the injection molded part polishing image.

[0048] S2: Obtain the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point, and obtain the local feature intensity of each pixel point based on the gradient amplitude and the surrounding pixels of each pixel point.

[0049] It should be noted that in the process of inspecting the polishing quality of injection molded parts, the Canny edge detection algorithm is usually used to detect the edges of defective areas. The Canny edge detection algorithm calculates the gradient amplitude of each pixel in the injection molded part polishing image, and identifies the edge by judging the relationship between the gradient amplitude of the pixel and the preset high threshold and low threshold. Since there are defect features of different intensities in the injection molded part polishing image, that is, some defects have large grayscale values ​​different from those of the surrounding areas, while some defects have small grayscale values ​​different from those of the surrounding areas, the traditional Canny edge detection algorithm sets fixed high and low values ​​to better identify defect features. For defect areas with obvious grayscale changes, the fixed threshold is too high, causing these features to be ignored; and for defect areas with insignificant grayscale changes, the fixed threshold is too low, causing some non-defective edges to be mistakenly identified as defect features, resulting in inaccurate quality inspection results.

[0050] Therefore, the purpose of the present invention is to divide the normal area (the area with good polishing quality of the injection molded part), the defect area with obvious grayscale changes, and the defect area with no obvious grayscale changes in the injection molded part polishing image into a separate block, and further perform edge detection based on the characteristics of each block and the low threshold of each block.

[0051] Since the grayscale value distribution of the pixels in the normal area of ​​the injection molded part polishing image is relatively uniform, the gradient amplitude of the pixels in the normal area of ​​the injection molded part polishing image is low, and the gradient value difference between the pixels in the normal area and the surrounding pixels is small; while the gradient values ​​of the pixels in the defective area with obvious grayscale changes and the defective area with insignificant grayscale changes in the injection molded part polishing image are larger than those in the normal area, and the gradient values ​​of the pixels and the surrounding pixels are greatly different. Therefore, the local feature intensity of each pixel is obtained by analyzing the gradient amplitude of each pixel and the gradient amplitude difference between each pixel and the surrounding pixels.

[0052] It should be further explained that, since the degree of grayscale change in different defect areas is different, the local feature intensity of the pixels in the defect areas with different grayscale changes is different. The local feature intensity of the pixels in the same defect area is approximate. Therefore, when the blocks are subsequently divided according to the local feature intensity of each pixel, the normal area, the defect area with obvious grayscale change, and the defect area with insignificant grayscale change can be divided into a separate block respectively.

[0053] In the embodiment of the present invention, the Sobel operator is used to obtain the gradient amplitude of each pixel in the injection molded part polishing image, and the eight neighboring pixels of each pixel in the injection molded part polishing image are recorded as the surrounding pixels of each pixel;

[0054] Get the local feature intensity of each pixel:

[0055] ;

[0056] Where, Represents the local feature intensity of the i-th pixel; Represents the gradient amplitude of the i-th pixel; Represents the number of pixels surrounding the i-th pixel; Represents the gradient amplitude of the jth surrounding pixel of the i-th pixel; norm() represents the normalization function; Represents the gradient amplitude of the pixel point. The larger the value, the greater the local feature intensity of the pixel point. Represents the difference in gradient amplitude between the i-th pixel and its surrounding pixels. The smaller its value, the greater the difference in gradient amplitude between the i-th pixel and its surrounding pixels, which means that the gradient change between the i-th pixel and its surrounding pixels is large, and the local feature intensity of the i-th pixel is greater.

[0057] It should be noted that for areas with good polishing quality of injection molded parts, the grayscale value distribution of pixels in this area is relatively uniform. Therefore, if the gradient amplitude of any pixel is small, and the gradient amplitude difference between this pixel and its neighboring pixels is small, the local feature intensity of this pixel is small, and the pixel is more likely to belong to an area with good polishing quality of injection molded parts, that is, a normal area.

[0058] For areas with poor polishing quality of injection molded parts, that is, areas with defects such as scratches, the grayscale values ​​of the pixels in this area and their neighboring pixels are unevenly distributed. Therefore, if the gradient amplitude of any pixel is large and the gradient amplitude difference between this pixel and its neighboring pixels is large, the greater the local feature intensity of the pixel, the more likely the pixel belongs to an area with poor polishing quality of the injection molded part, that is, a defective area.

[0059] S3: Based on the difference in local feature intensity between pixels, the pixels in the injection molded part polishing image are merged to obtain several blocks. Based on the local feature intensity of the pixels in each block, the optimal low threshold of each block is adaptively obtained. Based on the optimal low threshold of each block, the high threshold of each block is obtained. Based on the optimal low threshold and high threshold of each block, the edge pixels of each block are obtained.

[0060] It should be noted that the above steps obtain the local feature intensity of each pixel point, and then merge the pixels according to the difference in local feature intensity between the pixels to obtain several blocks in the injection molded part polishing image. If the difference in local feature intensity between the pixels is small, it means that the pixels should be merged.

[0061] In an embodiment of the present invention, a feature threshold Q1=0.3 is preset, and the absolute value of the difference between the local feature intensity of the i-th pixel and each pixel within its four neighborhoods is recorded as the feature difference value between the i-th pixel and each of its four neighborhood pixels, and all four neighborhood pixels whose feature difference values ​​are less than Q1 are recorded as target pixels of the i-th pixel; the i-th pixel is merged with all its target pixels to obtain the i-th block; the target pixel of each pixel in the i-th block is obtained, and the target pixel is merged with the i-th block to obtain a new i-th block; and so on, until there is no target pixel for each pixel in the new i-th block, and the new i-th block is recorded as the i-th block;

[0062] Any pixel point in the injection molded part polishing image except the pixel points of the i-th block is recorded as the n-th pixel point. The i-th pixel point is expanded to obtain the n-th block. This process is repeated until there are no pixels in the injection molded part polishing image, and each block is obtained.

[0063] It should be noted that the local feature intensity of pixels in defect areas with obvious grayscale changes is relatively large. Therefore, if the pixels in any block are more likely to be defect areas with obvious grayscale changes, the low threshold needs to be appropriately increased to avoid detecting some non-defect edge details in the defect area. The local feature intensity of pixels in defect areas with subtle grayscale changes is smaller than that in defect areas with obvious grayscale changes. Therefore, if the pixels in any block are more likely to be defect areas with subtle grayscale changes, the low threshold needs to be appropriately lowered to detect some faint defect edge details in the defect area.

[0064] Therefore, in the present invention, a local feature intensity reference value is preset. If the mean value of the local feature intensity of the pixels in any block is greater than the local feature intensity reference value, it is considered that the block is more likely to be a defect area with obvious grayscale changes, and the low threshold of the block is increased at this time; if the mean value of the local feature intensity of the pixels in any block is less than the local feature intensity reference value, it is considered that the block is more likely to be a defect area or a normal area with insignificant grayscale changes, and the low threshold of the block is lowered at this time. When the block is a defect area with insignificant grayscale changes, lowering the low threshold can detect weak edges. When the block is a normal area with grayscale distribution, lowering the low threshold cannot detect edges.

[0065] In the embodiment of the present invention, a low threshold is preset In other embodiments, implementers may preset the low threshold value according to the specific implementation.

[0066] Get the optimal low threshold for each block:

[0067] ;

[0068] Where, represents the optimal low threshold of the b-th block; Represents the preset low threshold; Represents the mean of the local feature intensities of all pixels in the bth block; Represents a preset local feature intensity reference value. In the embodiment of the present invention, the preset local feature intensity reference value In other embodiments, the implementer can preset The value of Represents a preset hyperparameter. In the embodiment of the present invention, the preset In other embodiments, the implementer can preset The value of

[0069] Known The value of represents the adjustment amount of the preset low threshold; if The value is greater than When , it means that the mean of the local feature intensity of all pixels in the bth block is large. At this time, the pixels in the bth block are more likely to be defect areas with obvious grayscale changes. At this time, it is necessary to appropriately increase the low threshold to avoid detecting some non-defective edge details in the defect area.

[0070] like The value is less than When , it means that the mean value of the local feature intensity of all pixels in the bth block is small. At this time, the pixels in the bth block are more likely to be defective areas or normal areas with inconspicuous grayscale changes. At this time, it is necessary to appropriately lower the low threshold to detect some faint edge details in the inconspicuous defective areas, while the grayscale values ​​of the normal areas are evenly distributed, and lowering the low threshold has no effect.

[0071] The function is to adjust the adjustment amount of the preset low threshold to avoid the adjustment amount of the preset low threshold being too large or too small, which causes the preset low threshold to be adjusted too large or too small.

[0072] It should be noted that the high threshold of each block is obtained according to the low threshold of each block. Therefore, based on the low threshold and high threshold of each block, edge detection is performed on each block to obtain the edge pixel points of each block, that is, several edges of the injection molded part polishing image are obtained.

[0073] In an embodiment of the present invention, twice the optimal low threshold of the b-th block is used as the high threshold of the b-th block, pixels in the b-th block whose gradient amplitude is greater than the high threshold are used as strong edge pixels of the b-th block, pixels in the b-th block whose gradient amplitude is between the high threshold and the low threshold are used as weak edge pixels of the b-th block, and strong edge pixels of the b-th block and weak edge points within the eight-neighborhood range of its strong edge pixels are used as edge pixels in the b-th block.

[0074] Similarly, obtain the edge pixels in each block.

[0075] S4: Evaluate the polishing quality of injection molded parts based on the edge pixels in each block.

[0076] It should be noted that, first, several edges of the injection molded part polishing image are obtained based on the edge pixel points in each block, and the noise edges in the injection molded part polishing image are filtered to obtain the target edge in the injection molded part polishing image, that is, the defect edge; if the number of pixel points on the target edge in the injection molded part polishing image is greater, it means that the polishing quality of the injection molded part is worse.

[0077] In an embodiment of the present invention, a pixel number threshold T2 is preset to be 10. In other embodiments, the implementer may preset the value of T2 according to specific implementation conditions. Based on the edge pixels in each block, a plurality of edges of the injection molded part polishing image are obtained. If the total number of pixels of any edge of the injection molded part polishing image is greater than the pixel number threshold T2, the edge is recorded as a target edge of the injection molded part polishing image, and all target edges of the injection molded part polishing image are obtained.

[0078] If the ratio of the number of pixels on all target edges to the number of pixels in the injection molded part polishing image is greater than 0.1, the system will issue an early warning to remind the staff that the quality of the injection molded part polishing is unqualified.

[0079] An embodiment of the present invention further discloses an injection molded part polishing quality detection system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an injection molded part polishing quality detection method according to the present invention is implemented.

Claims

1. A method for inspecting the polishing quality of injection molded parts, characterized in that: Including steps: Collect images of injection molded parts being polished; Obtaining the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point, and obtaining the local feature intensity of each pixel point based on the gradient amplitude and the surrounding pixels, including: ； Where, Represents the local feature intensity of the i-th pixel; Represents the gradient amplitude of the i-th pixel; Represents the number of pixels surrounding the i-th pixel; Represents the gradient amplitude of the jth surrounding pixel of the i-th pixel; norm() represents the normalization function; Based on the difference in local feature intensity between pixels, the pixels in the injection molded part polishing image are merged to obtain several blocks, including: A feature threshold Q1 is preset, and the absolute value of the difference between the local feature intensity of the i-th pixel and each pixel within its four neighborhoods is recorded as the feature difference value between the i-th pixel and each of its four neighborhood pixels. All four neighborhood pixels whose feature difference value is less than Q1 are recorded as the target pixel of the i-th pixel; the i-th pixel is merged with all its target pixels to obtain the i-th block; the target pixel of each pixel in the i-th block is obtained, and it is merged with the i-th block to obtain a new i-th block; and so on, until there is no target pixel for each pixel in the new i-th block, and the new i-th block is recorded as the i-th block; each block is obtained; According to the mean of the local feature intensity of all pixels in each block, the optimal low threshold of each block is obtained; according to the optimal low threshold of each block, the high threshold of each block is obtained; according to the optimal low threshold and high threshold of each block, the edge pixel points of each block are obtained; The polishing quality of injection molded parts is evaluated based on the edge pixels in each block.

2. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The step of obtaining the gradient amplitude of each pixel point in the injection molded part polishing image and the surrounding pixels of each pixel point includes: The Sobel operator is used to obtain the gradient amplitude of each pixel in the injection molded part polishing image, and the eight neighborhood pixels of each pixel in the injection molded part polishing image are recorded as the surrounding pixels of each pixel.

3. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The obtaining of the optimal low threshold value for each block includes: ； Where, represents the optimal low threshold of the b-th block; Represents the preset low threshold; Represents the mean of the local feature intensity of all pixels in the b-th block; Represents the preset local feature intensity reference value; Represents the preset hyperparameters.

4. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The step of obtaining a high threshold value for each block according to the optimal low threshold value for each block includes: The double of the optimal low threshold of each block is used as the high threshold of each block.

5. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The step of obtaining edge pixels of each block according to the optimal low threshold and high threshold of each block includes: The pixels in the bth block whose gradient amplitude is greater than the high threshold are regarded as the strong edge pixels of the bth block, the pixels in the bth block whose gradient amplitude is between the high threshold and the low threshold are regarded as the weak edge pixels of the bth block, and the strong edge pixels of the bth block and the weak edge points in the eight-neighborhood range of its strong edge pixels are regarded as the edge pixels of the bth block.

6. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The polishing quality of the injection molded parts is evaluated based on the edge pixels in each block, including: A pixel number threshold T2 is preset; based on the edge pixels in each block, several edges of the injection molded part polishing image are obtained. If the total number of pixels of any edge of the injection molded part polishing image is greater than the pixel number threshold T2, the edge is recorded as the target edge of the injection molded part polishing image, and all target edges of the injection molded part polishing image are obtained; If the ratio of the number of pixels of all target edges of the injection molded part polishing image to the number of pixels in the injection molded part polishing image is greater than 0.1, the system will issue an early warning to remind the staff that the quality of the injection molded part polishing is unqualified.

7. The method for inspecting the polishing quality of injection molded parts according to claim 1, wherein: The collecting of injection molded part polishing images includes: A high-resolution CMOS camera is used to shoot the polished surface of the injection molded part, and an RGB image of the injection molded part polishing is collected. The RGB image of the injection molded part polishing is grayscaled and recorded as the injection molded part polishing image.

8. A system for inspecting the polishing quality of injection molded parts, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an injection molded part polishing quality detection method according to any one of claims 1 to 7 is implemented.

Images