Foaming material surface defect detection method and system

Abstract

The invention relates to the technical field of defect detection, in particular to a foam material surface defect detection method and system. Comprising the following steps that a camera sensor is used for scanning a to-be-detected foaming material area to obtain an RGB color image, image augmentation processing is conducted on the obtained RGB color image to improve the definition of the RGB color image, coarse registration is conducted on the RGB color image subjected to image augmentation adaptation preprocessing and a defect-free standard image, and the defect-free standard image is obtained; according to the method, an image without obvious defects and an image with the obvious defects can be obtained, the image without the obvious defects and a standard image without the defects are subjected to fine registration, and if the image without the obvious defects has the unobvious defects, the image without the obvious defects is marked as an image with the unobvious defects. Whether defects exist on the surface of the foaming material or not can be detected, whether obvious defects exist or not can be detected, the number of the defects can be detected, and the detection efficiency and the detection accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of foam material surface defect detection, and in particular to a foam material surface defect detection method and system. Background Art

[0002] Foam material is a material with unique properties and is widely used in many fields. Foam material refers to a porous material formed by a large number of bubbles inside the material through physical or chemical methods. These bubbles are evenly distributed in the material matrix, giving the material low density, high specific strength, good thermal insulation and sound insulation properties.

[0003] The properties of foam materials (such as thermal insulation, cushioning, mechanical properties, etc.) are closely related to their microstructure and overall uniformity. Defects (such as uneven holes, cracks, etc.) will destroy the structural integrity of the material and lead to unstable performance. For example, if the foam materials used in the field of building insulation have hole defects or cracks, their thermal insulation performance will be reduced, affecting the energy-saving effect of the building; in the packaging industry, if the foam materials used for cushioning protection have cracks or abnormal local density, they may not be able to effectively absorb impact energy, resulting in damage to the packaged items. Therefore, after the production of the foam materials, it is necessary to perform defect detection on the surface of the foam materials.

[0004] For example, the Chinese patent publication number CN108230321A discloses a defect detection method and device. The comparative patent compares the grayscale value of the pixels in the variance image of the area with a specified threshold. If there is a pixel whose grayscale value exceeds the specified threshold, it can be determined that the location of the pixel is a defective area and the defective area is marked, thereby realizing automatic detection of defects on the cover glass surface.

[0005] Although the above-mentioned comparative patent can determine whether the area to be inspected is a defective area by comparing the grayscale value of the area to be inspected with the specified threshold, the detection method provided has low detection accuracy and incomplete detection results. Some minor defects that are not obvious defects do not affect the normal sales and use of the product in certain product applications, resulting in the sales of products with defects. Therefore, it needs to be improved. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for detecting surface defects of foaming materials. If an image with no obvious defects is consistent with a standard image with no defects, then the image with no obvious defects does not have any inconspicuous defects, that is, the image with no obvious defects does not have any defects, aiming to solve the problems in the prior art.

[0007] The present invention is implemented as follows: a method for detecting surface defects of a foam material, applied to a surface defect detection device, specifically comprising the following steps:

[0008] S101, displaying an editing control on the main interface, determining whether to obtain a summary operation of the editing control, and if the surface defect detection device obtains the summary operation of the editing control, then using a camera sensor to scan the foam material area to be tested to obtain an RGB color image set;

[0009] S102, performing image augmentation and adaptation preprocessing on the acquired RGB color image set to improve the clarity of the RGB color image;

[0010] S103, performing a first recognition and registration on the RGB color image after the image augmentation and adaptation preprocessing and the defect-free standard image preset by the system; if there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image without obvious defects; performing a second recognition and registration on the image without obvious defects and the defect-free standard image; if the image without obvious defects is consistent with the defect-free standard image, the image without obvious defects does not have an inconspicuous defect, that is, the image without obvious defects does not have a defect; if the image without obvious defects is inconsistent with the defect-free standard image, the image without obvious defects has an inconspicuous defect, and the image without obvious defects is marked as an image with an inconspicuous defect;

[0011] S104, if there is an obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects;

[0012] S105, performing a second recognition and registration on the image with obvious defects and the standard image without defects, identifying defect feature points in the image with obvious defects and the standard image without defects, and marking the defect feature points in the identified image with obvious defects and the standard image without defects according to the obtained summarization operation of the editing control, and after the marking is completed, a defect set is formed and output to the terminal.

[0013] Further, in S101, if the surface defect detection device obtains the summary operation of the editing control, and then uses a camera sensor to scan the foam material area to be tested to obtain an RGB color image set, it includes:

[0014] Receiving a summary request of an editing control sent by a terminal through a preset network, wherein the summary request of the editing control is used to request to establish a connection with the surface defect detection device;

[0015] If the summary request of the editing control sent by the terminal includes the summary set of the editing control, connecting with the terminal according to the summary request of the editing control, and after the connection is completed, scanning the foaming material area to be tested by using a camera sensor to obtain an RGB color image set;

[0016] The camera sensor is any one of a video camera, an infrared camera and an inspection robot.

[0017] Furthermore, in S102, the acquired RGB color image set is subjected to image augmentation and adaptation preprocessing, and the image augmentation and adaptation preprocessing features include hue, saturation, brightness, contrast change, image flipping, rotation, Gaussian noise, image displacement and center segmentation.

[0018] Further, in S103, the first recognition and registration includes:

[0019] Acquire recognition models of multiple defect-free standard images, and sort the recognition models of the multiple defect-free standard images in order;

[0020] Acquire the preprocessed RGB color image, input the preprocessed RGB color image into the recognition model of the first-ranked defect-free standard image for recognition, and if no imperfection or damage is directly recognized, the RGB color image is an image without obvious defects;

[0021] If imperfections or damage are directly identified, the RGB color image is an image with obvious defects;

[0022] and imperfections or damage include, but are not limited to, scratches, dents, cracks, rust, corrosion, uneven coating and holes.

[0023] Further, in S104, the image with obvious defects is not analyzed for the image without obvious defects, and the precise registration of the image without obvious defects includes the following steps:

[0024] S1041, dividing the image without obvious defects and the standard image without defects into multiple small image areas equally, performing a magnification and brightening process on all the small image areas on the image without obvious defects and the standard image without defects, and then comparing all the small image areas of the two one by one, if all the small image areas of the two are consistent, then the image without obvious defects does not have an inconspicuous defect;

[0025] S1042: If there are inconsistent areas in all small image areas of the two, the image without obvious defects has inconspicuous defects.

[0026] Furthermore, in S1042, the following steps are also included:

[0027] S10421. Locate all inconsistent small image regions;

[0028] S10422, shielding a part of the background of the located small image area by using the generated background masking area, so as to better focus on the area with inconspicuous defects, and generating a new local positioning area;

[0029] S10423. Enlarge and crop the new local positioning area to capture more detailed information, so that the inconspicuous features in the small image area are more obvious, which is convenient for more effective extraction of inconspicuous defect feature information, so as to achieve comparison of inconsistent areas existing in the image without obvious defects and the standard image without defects.

[0030] Further, in S1042, non-obvious defects include but are not limited to microscopic cracks and scratches and slight deformation or dislocation.

[0031] Further, in S10423, the new local positioning area is enlarged and cropped to capture more detailed information, making the unclear features in the small image area more obvious, including:

[0032] Acquire the located small image area, identify the edge contour of the small image area and generate edge contour features, and generate a background masking area outside the edge contour features to shield a part of the background of the small image area;

[0033] Identify and mark the high-amplitude chromatic aberration areas within the edge contour features, and enlarge and crop the marked high-amplitude chromatic aberration areas to capture more detailed information.

[0034] Compared with the prior art, the present invention provides a foam material surface defect detection method and system, which has the following beneficial effects:

[0035] 1. The present invention can detect whether there are obvious defects on the surface of the foaming material by performing a first recognition registration on the RGB color image after image augmentation and adaptation preprocessing and the defect-free standard image;

[0036] If there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image without obvious defects, that is, there is no obvious defect on the surface of the inspected foam material; if there is a significant difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects, that is, there is an obvious defect on the surface of the inspected foam material, that is, there is a defect.

[0037] 2. The present invention can detect whether an image without obvious defects has inconspicuous defects by performing a second recognition registration on an image without obvious defects and a standard image without defects;

[0038] If the image without obvious defects is consistent with the standard image without defects, then the image without obvious defects does not have any inconspicuous defects, that is, the image without obvious defects has no defects; if the image without obvious defects is inconsistent with the standard image without defects, then the image without obvious defects has inconspicuous defects, and the image without obvious defects is marked as an image with inconspicuous defects.

[0039] A foam material surface defect detection system, used to execute the foam material surface defect detection method, the surface defect detection system comprising:

[0040] An image acquisition unit, used to acquire an RGB color image of the foam material area to be tested;

[0041] An image augmentation processing unit, used to improve the clarity of the RGB color image;

[0042] A coarse registration unit is used to detect whether there are obvious defects in the RGB color image;

[0043] The precise registration unit is used to detect whether there are subtle defects in the RGB color image.

[0044] Specifically, the fine registration unit includes a positioning module for locating all inconsistent small image regions;

[0045] Background shielding module, which shields part of the background of a small image area by generating a background mask area to retain the features of the inconspicuous defect area;

[0046] The magnification and cropping module is used to magnify and crop the small image area that shields the background, so as to more effectively extract the feature information of the inconspicuous defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic flow chart of a foam material surface defect detection method proposed by the present invention;

[0048] Figure 2 A schematic flowchart of the process of the inductive operation of the surface defect detection device acquiring the editing control in the foam material surface defect detection method proposed by the present invention;

[0049] Figure 3 This is a structural schematic diagram of a foam material surface defect detection system proposed by the present invention;

[0050] Figure 4 This is a schematic structural diagram of a precise registration unit in a foam material surface defect detection system proposed by the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0053] The same or similar numbers in the drawings of this embodiment correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0054] The surface defects of foam materials mainly include the following:

[0055] 1. Burrs: Burrs refer to the phenomenon that the surface of the foamed product is not smooth, neat or has burrs. This defect will affect the appearance and performance of the product;

[0056] 2. Bubbles: Bubbles refer to the gas-filled cavities formed inside the foamed product, which will affect the sealing, mechanical properties and appearance of the product. The generation of bubbles is related to factors such as moisture or impurities in the raw materials, unstable mold temperature or failure to heat to the appropriate temperature, improper temperature and pressure control during the foaming process, and unreasonable foaming process12.

[0057] 3. Cells: The cells on the surface of the foamed sheet are a sign of low local density of the melt. Generally, there are two types of cells: strip cells and round cells. The appearance of cells is related to raw material factors such as resin, foaming agent, regulator, calcium carbonate, stabilizer, as well as molds and processes.

[0058] 4. Stratification: Stratification refers to uneven distribution of foam, with raw materials that have not reacted completely in the middle. The foam will feel wet and sticky when touched by hand. Stratification is caused by uneven mixing of P material and I material during reaction, lack of pre-mixing or insufficient mixing of raw materials, incorrect setting of raw material ratio, abnormal flow metering of equipment, and abnormal mixing pressure.

[0059] 5. False material: False material refers to the product that has no obvious defects on the appearance, but the foam feels collapsed after being touched. Cutting the surface and observing it will reveal filamentous foam with coarse pores. False material is caused by insufficient internal pressure of the foam, sudden drop in internal pressure of the foam caused by material inrush, insufficient internal pressure of the foam caused by mismatch between mold air cushion deflation time and material temperature and mold temperature, insufficient foam fluidity caused by product structure design, insufficient casting material, and expired or unevenly mixed foaming material.

[0060] To detect surface defects of foam materials, refer to Figure 1-Figure 2 As shown, a foam material surface defect detection method is applied to a surface defect detection device, specifically comprising the following steps:

[0061] S101, displaying an editing control on the main interface, determining whether to obtain a summary operation of the editing control, if the surface defect detection device obtains the summary operation of the editing control, then using a camera sensor to scan the foam material area to be tested to obtain an RGB color image set;

[0062] If the surface defect detection device obtains the summary operation of the editing control, and then uses the camera sensor to scan the foam material area to be tested to obtain an RGB color image set, it includes:

[0063] Receiving a summary request of the editing control sent by the terminal through a preset network, the summary request of the editing control is used to request to establish a connection with the surface defect detection device;

[0064] If the summary request of the edit control sent by the terminal includes the summary set of the edit control, the terminal is connected according to the summary request of the edit control, and after the connection is completed, the camera sensor is used to scan the foam material area to be tested to obtain the RGB color image set;

[0065] The camera sensor is any one of a video camera, an infrared camera and an inspection robot;

[0066] S102, performing image augmentation and adaptation preprocessing on the acquired RGB color image set to improve the clarity of the RGB color image;

[0067] Among them, the acquired RGB color image set is subjected to image augmentation and adaptation preprocessing, and the image augmentation and adaptation preprocessing features include hue, saturation, brightness, contrast change, image flipping, rotation, Gaussian noise, image displacement and center segmentation.

[0068] S103, performing a first recognition and registration on the RGB color image after the image augmentation and adaptation preprocessing and the defect-free standard image preset by the system; if there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image without obvious defects; performing a second recognition and registration on the image without obvious defects and the defect-free standard image; if the image without obvious defects is consistent with the defect-free standard image, the image without obvious defects does not have an inconspicuous defect, that is, the image without obvious defects does not have a defect; if the image without obvious defects is inconsistent with the defect-free standard image, the image without obvious defects has an inconspicuous defect, and the image without obvious defects is marked as an image with an inconspicuous defect;

[0069] Specifically, by performing a first recognition registration on the RGB color image after image augmentation and adaptation preprocessing and the defect-free standard image, it is possible to detect whether there are obvious defects on the surface of the foaming material;

[0070] If there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image without obvious defects, that is, the surface of the inspected foam material has no obvious defects; if there is a significant difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects, that is, the surface of the inspected foam material has obvious defects, that is, there are defects;

[0071] S104, if there is an obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects;

[0072] Wherein, the image with obvious defects is not analyzed, and the precise registration of the image without obvious defects includes the following steps:

[0073] S1041, dividing the image without obvious defects and the standard image without defects into multiple small image areas equally, performing a magnification and brightening process on all the small image areas on the image without obvious defects and the standard image without defects, and then comparing all the small image areas of the two one by one, if all the small image areas of the two are consistent, then the image without obvious defects does not have an inconspicuous defect;

[0074] S1042. If there are inconsistent areas in all small image areas of the two, the image without obvious defects has inconspicuous defects;

[0075] S105. Perform a second recognition and registration on the image with obvious defects and the standard image without defects, identify the defect feature points in the image with obvious defects and the standard image without defects, and mark the defect feature points in the identified image with obvious defects and the standard image without defects according to the summarization operation of the acquired editing control. After the marking is completed, a defect set is formed and output to the terminal. The present invention can detect whether an image without obvious defects has inconspicuous defects by performing a second recognition and registration on the image without obvious defects and the standard image without defects. If the image without obvious defects is consistent with the standard image without defects, the image without obvious defects does not have inconspicuous defects, that is, the image without obvious defects does not have defects. If the image without obvious defects is inconsistent with the standard image without defects, the image without obvious defects has inconspicuous defects, and the image without obvious defects is marked as an image with inconspicuous defects.

[0076] In S103 of this embodiment, the first recognition and registration includes:

[0077] Acquire recognition models of multiple defect-free standard images, and sort the recognition models of the multiple defect-free standard images in order;

[0078] Obtaining a preprocessed RGB color image, inputting the preprocessed RGB color image into the recognition model of the first-ranked defect-free standard image for recognition, if no imperfection or damage is directly recognized, the RGB color image is an image without obvious defects;

[0079] If imperfections or damage are directly identified, the RGB color image is an image with obvious defects;

[0080] and imperfections or damage include, but are not limited to, scratches, dents, cracks, rust, corrosion, uneven coating and holes.

[0081] In S1042 of this embodiment, the following steps are also included:

[0082] S10421. Locate all inconsistent small image regions;

[0083] S10422, shielding a part of the background of the located small image area by using the generated background masking area, so as to better focus on the area with inconspicuous defects, and generating a new local positioning area;

[0084] S10423. Enlarge and crop the new local positioning area to capture more detailed information, so that the inconspicuous features in the small image area are more obvious, which is convenient for more effective extraction of inconspicuous defect feature information, so as to achieve comparison of inconsistent areas existing in the image without obvious defects and the standard image without defects.

[0085] In S1042, non-obvious defects include, but are not limited to, microscopic cracks and scratches and slight deformations or misalignments.

[0086] In S10423, the new localized region is enlarged and cropped to capture more detailed information, making unclear features in small image regions more obvious, including:

[0087] Acquire the located small image area, identify the edge contour of the small image area and generate edge contour features, and generate a background masking area outside the edge contour features to shield a part of the background of the small image area;

[0088] Identify and mark the high-amplitude chromatic aberration areas within the edge contour features, and enlarge and crop the marked high-amplitude chromatic aberration areas to capture more detailed information.

[0089] Reference Figure 3-Figure 4As shown, a foam material surface defect detection system is used to execute the above-mentioned foam material surface defect detection method. The surface defect detection system includes: an image acquisition unit, used to obtain an RGB color image of the foam material area to be tested; an image augmentation processing unit, used to improve the clarity of the RGB color image; a coarse registration unit, used to detect whether there are obvious defects in the RGB color image; a fine registration unit, used to detect whether there are inconspicuous defects in the RGB color image. The present invention can detect whether there are obvious defects on the surface of the foam material by performing a first recognition and registration on the RGB color image after image augmentation adaptation preprocessing and the defect-free standard image; if there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects, that is, the inspected foam material surface has no obvious defects; if there is a significant difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects, that is, the inspected foam material surface has obvious defects, that is, defects exist.

[0090] The fine registration unit includes a positioning module, which is used to locate all inconsistent small image areas; a background shielding module, which shields part of the background of the small image area by generating a background masking area to retain the characteristics of the inconspicuous defect area; an enlargement and cropping module, which is used to enlarge and crop the small image area that shields the background, so as to more effectively extract the inconspicuous defect feature information. By performing a second recognition and registration on the image without obvious defects and the standard image without defects, it is possible to detect whether the image without obvious defects has inconspicuous defects; if the image without obvious defects is consistent with the standard image without defects, then the image without obvious defects does not have inconspicuous defects, that is, the image without obvious defects has no defects; if the image without obvious defects is inconsistent with the standard image without defects, then the image without obvious defects has inconspicuous defects, and the image without obvious defects is marked as an image with inconspicuous defects.

[0091] In this embodiment, the entire operation process can be controlled by a computer, and with the addition of a PLC, etc., automated operation control can be achieved. In each operation link, sensors can be set up to provide signal feedback to achieve sequential execution of steps. These are all common knowledge of current automated control and will not be described in detail in this embodiment.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting surface defects of a foaming material, characterized in that: Applied to surface defect detection equipment, specifically including the following steps: S101, displaying an editing control on the main interface, determining whether to obtain a summary operation of the editing control, and if the surface defect detection device obtains the summary operation of the editing control, then using a camera sensor to scan the foam material area to be tested to obtain an RGB color image set; S102, performing image augmentation and adaptation preprocessing on the acquired RGB color image set to improve the clarity of the RGB color image; S103, performing a first recognition and registration on the RGB color image after the image augmentation and adaptation preprocessing and the defect-free standard image preset by the system; if there is no obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image without obvious defects; performing a second recognition and registration on the image without obvious defects and the defect-free standard image; if the image without obvious defects is consistent with the defect-free standard image, the image without obvious defects does not have an inconspicuous defect, that is, the image without obvious defects does not have a defect; if the image without obvious defects is inconsistent with the defect-free standard image, the image without obvious defects has an inconspicuous defect, and the image without obvious defects is marked as an image with an inconspicuous defect; S104, if there is an obvious difference between the RGB color image and the defect-free standard image, the RGB color image is marked as an image with obvious defects; S105, performing a second recognition and registration on the image with obvious defects and the standard image without defects, identifying defect feature points in the image with obvious defects and the standard image without defects, and marking the defect feature points in the identified image with obvious defects and the standard image without defects according to the obtained summarization operation of the editing control, and after the marking is completed, a defect set is formed and output to the terminal.

2. A foam material surface defect detection method according to claim 1, characterized in that: In S101, if the surface defect detection device obtains the summary operation of the editing control, then uses a camera sensor to scan the foam material area to be tested to obtain an RGB color image set, including: Receiving a summary request of an editing control sent by a terminal through a preset network, wherein the summary request of the editing control is used to request to establish a connection with the surface defect detection device; If the summary request of the editing control sent by the terminal includes the summary set of the editing control, connecting with the terminal according to the summary request of the editing control, and after the connection is completed, scanning the foaming material area to be tested by using a camera sensor to obtain an RGB color image set; The camera sensor is any one of a video camera, an infrared camera and an inspection robot.

3. A foam material surface defect detection method according to claim 2, characterized in that: In S102, the acquired RGB color image set is subjected to image augmentation and adaptation preprocessing, and the image augmentation and adaptation preprocessing features include hue, saturation, brightness, contrast change, image flipping, rotation, Gaussian noise, image displacement and center segmentation.

4. A method for detecting surface defects of a foam material according to claim 3, characterized in that: In S103, the first recognition and registration includes: Acquire recognition models of multiple defect-free standard images, and sort the recognition models of the multiple defect-free standard images in order; Acquire the preprocessed RGB color image, input the preprocessed RGB color image into the recognition model of the first-ranked defect-free standard image for recognition, and if no imperfection or damage is directly recognized, the RGB color image is an image without obvious defects; If imperfections or damage are directly identified, the RGB color image is an image with obvious defects; and imperfections or damage include, but are not limited to, scratches, dents, cracks, rust, corrosion, uneven coating and holes.

5. A foam material surface defect detection method according to claim 4, characterized in that: In S104, the image with obvious defects is not analyzed for the image without obvious defects, and the precise registration of the image without obvious defects includes the following steps: S1041, dividing the image without obvious defects and the standard image without defects into multiple small image areas equally, performing a magnification and brightening process on all the small image areas on the image without obvious defects and the standard image without defects, and then comparing all the small image areas of the two one by one, if all the small image areas of the two are consistent, then the image without obvious defects does not have an inconspicuous defect; S1042: If there are inconsistent areas in all small image areas of the two, the image without obvious defects has inconspicuous defects.

6. A foam material surface defect detection method according to claim 5, characterized in that: In S1042, the following steps are also included: S10421. Locate all inconsistent small image regions; S10422, shielding a part of the background of the located small image area by using the generated background masking area, so as to better focus on the area with inconspicuous defects, and generating a new local positioning area; S10423. Enlarge and crop the new local positioning area to capture more detailed information, so that the inconspicuous features in the small image area are more obvious, which is convenient for more effective extraction of inconspicuous defect feature information, so as to achieve comparison of inconsistent areas existing in the image without obvious defects and the standard image without defects.

7. A foam material surface defect detection method according to claim 6, characterized in that: In S1042, non-obvious defects include, but are not limited to, microscopic cracks and scratches and slight deformations or misalignments.

8. A method for detecting surface defects of a foam material according to claim 6, characterized in that: In S10423, the new localized region is enlarged and cropped to capture more detailed information, making unclear features in small image regions more obvious, including: Acquire the located small image area, identify the edge contour of the small image area and generate edge contour features, and generate a background masking area outside the edge contour features to shield a part of the background of the small image area; Identify and mark the high-amplitude chromatic aberration areas within the edge contour features, and enlarge and crop the marked high-amplitude chromatic aberration areas to capture more detailed information.

9. A foam material surface defect detection system, characterized in that: Used to perform the foam material surface defect detection method according to any one of claims 1 to 8, the surface defect detection system comprises: An image acquisition unit, used to acquire an RGB color image of the foam material area to be tested; An image augmentation processing unit, used to improve the clarity of the RGB color image; A coarse registration unit is used to detect whether there are obvious defects in the RGB color image; The precise registration unit is used to detect whether there are subtle defects in the RGB color image.

10. A foam material surface defect detection system according to claim 9, characterized in that: The fine registration unit includes a positioning module for locating all inconsistent small image areas; Background shielding module, which shields part of the background of a small image area by generating a background mask area to retain the features of the inconspicuous defect area; The magnification and cropping module is used to magnify and crop the small image area that shields the background, so as to more effectively extract the feature information of the inconspicuous defects.

Images