Quantitative evaluation method, device, equipment, medium and product for particleboard appearance quality

Abstract

The present application discloses a particleboard appearance quality quantitative evaluation method, device, equipment, medium and product, and relates to the field of particleboard appearance quality grading. The method comprises determining a set of sub-images to be detected based on a surface image of the particleboard; performing defect detection on the set of sub-images to be detected based on a deep learning defect detection model to determine a set of defect detection results; dividing the set of defect detection results according to defect categories to determine defect information of each type of defect; the defect information comprises area parameters and grayscale similarity; determining a defect quantization value of each type of defect based on the defect information; determining a final score of the particleboard based on the defect quantization value of each type of defect; and dividing the board grade based on the final score. The board grade is used to quantitatively evaluate the appearance quality of the particleboard. The present application can improve the quality inspection efficiency of the particleboard industry and improve the working environment.

Description

Technical Field

[0001] The present application relates to the field of particleboard appearance quality grading, and in particular to a particleboard appearance quality quantitative evaluation method, device, equipment, medium and product. Background Art

[0002] Particleboard is the main base material for customized home furnishings. With the increasing popularity and rapid development of customized home furnishings, the demand for particleboard, which accounts for most of the board usage in the customized home furnishing industry, is also increasing.

[0003] In 2023, the output of particleboard in China will exceed that of fiberboard for the first time, becoming the second largest type of wood-based panel. With the increase in output, the pressure of quality inspection is also increasing. At present, the evaluation and grading of the appearance quality of particleboard mainly rely on human visual observation, which is completely dependent on the experience of workers, with low efficiency, poor accuracy and high labor intensity. Therefore, it is urgent to introduce more accurate, objective and efficient quantitative evaluation and grading methods of appearance quality to replace manual inspection, use quantitative evaluation values ​​to objectively evaluate the appearance quality of particleboard, and improve the quality inspection efficiency and labor environment of the particleboard industry. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for quantitative evaluation of the appearance quality of particleboard, which can give an objective quantitative evaluation score according to the defects on the surface of the particleboard and grade the particleboard according to the score, thereby improving the quality inspection efficiency of the particleboard industry and improving the working environment.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In a first aspect, the present application provides a method for quantitatively evaluating the appearance quality of particleboard, comprising the following steps.

[0007] According to the surface image of the particle board, a set of sub-images to be detected is determined.

[0008] A deep learning-based defect detection model is used to perform defect detection on the set of sub-images to be detected, and a set of defect detection results is determined.

[0009] The defect detection result set is divided according to defect categories to determine defect information of each defect category; the defect information includes area parameters and grayscale similarity.

[0010] A defect quantification value of each type of defect is determined according to the defect information.

[0011] Based on the defect quantification value of each type of defect, the final score of the particle board is determined.

[0012] The board grades are divided according to the final scores; the board grades are used to evaluate the appearance quality of the particleboard.

[0013] In a second aspect, the present application provides a device for quantitatively evaluating the appearance quality of particleboard, comprising the following modules.

[0014] The module for determining the sub-image set to be detected is used to determine the sub-image set to be detected according to the surface image of the particle board.

[0015] The defect detection result set determination module is used to perform defect detection on the sub-image set to be detected based on a deep learning defect detection model to determine a defect detection result set.

[0016] The defect information determination module is used to divide the defect detection result set according to defect categories and determine the defect information of each defect category; the defect information includes area parameters and grayscale similarity.

[0017] The defect quantization value determination module is used to determine the defect quantization value of each type of defect according to the defect information.

[0018] The final score determination module is used to determine the final score of the particle board according to the defect quantification value of each type of defect.

[0019] An evaluation module is used to classify the board material according to the final score; the board material grade is used to evaluate the appearance quality of the particleboard.

[0020] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for quantitatively evaluating the appearance quality of particleboard.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for quantitatively evaluating the appearance quality of particleboard.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for quantitatively evaluating the appearance quality of particleboard.

[0023] According to the specific embodiments provided by the present application, the present application discloses the following technical effects: the present application performs defect detection on the surface image of the particleboard based on a deep learning defect detection model to give an objective quantitative evaluation score according to the defects on the surface of the particleboard, and grades the particleboard according to the final score to evaluate the appearance quality of the particleboard. Compared with the manual detection method, the present application can realize the grading and evaluation of the particleboard by only collecting the surface image, without the need for manual detection, which greatly improves the quality inspection efficiency of the particleboard industry and improves the working environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 This is a flow chart of the quantitative evaluation method for the appearance quality of particleboard provided in this application.

[0026] Figure 2 This is a schematic diagram of the quantitative evaluation process of the particleboard appearance quality provided in this application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0029] The embodiment of the present application provides a method for quantitatively evaluating the appearance quality of particleboard. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, Figure 1 As shown, the method includes the following steps.

[0030] S1: Determine a set of sub-images to be detected based on the surface image of the particle board.

[0031] S2: Perform defect detection on the set of sub-images to be detected based on a deep learning defect detection model to determine a set of defect detection results.

[0032] S3: Divide the defect detection result set according to defect categories to determine defect information of each defect category; the defect information includes area parameters and grayscale similarity.

[0033] S4: Determine a defect quantization value for each type of defect according to the defect information.

[0034] S5: Determine the final score of the particle board according to the defect quantification value of each type of defect.

[0035] S6: Classify the board materials according to the final scores; the board materials grades are used to evaluate the appearance quality of the particleboard.

[0036] In an exemplary embodiment, S1 may be replaced by the following steps.

[0037] S11: Acquire a surface image of a particle board; the surface image includes at least one of a front surface image and a back surface image of the particle board.

[0038] Further, the surface image of the particle board is obtained , whose size is Pixels, where Indicates width, Indicates altitude.

[0039] In this embodiment, the surface image may be a front surface image and / or a back surface image of the particle board, that is, the surface image may be a front surface image obtained by photographing the front side of the particle board, or may be a back surface image obtained by photographing the back side of the particle board. The surface image may be photographed by a single planar array or linear array camera, or may be photographed by multiple planar array or linear array cameras in blocks and then spliced ​​together.

[0040] S12: Using a viewfinder to perform trimming sampling on the surface image to determine a new surface image.

[0041] Furthermore, after acquiring the surface image, the present embodiment can also use a fixed-size view frame to perform edge sampling on the color image. Specifically, the center of the view frame is made to coincide with the center of the color image, and the portion of the color image within the view frame is cut out as the sampling image, so as to eliminate the influence of the redundant background on the quantitative evaluation and facilitate the subsequent sliding window cutting operation, and finally the sampling image is used as the new surface image. .

[0042] S13: pre-processing the new surface image to determine a set of sub-images to be detected, specifically including the following steps.

[0043] S131: grayscale the new surface image to determine a grayscale image.

[0044] S132: performing rectangular sliding window segmentation on the grayscale image to determine the segmented rectangular sub-images and a set of sub-images to be detected; the set of sub-images to be detected includes all the segmented rectangular sub-images.

[0045] Furthermore, the preprocessing includes image graying and image sliding window slicing. The sub-image to be detected is a group of images, each of which is a part of the new surface image.

[0046] Preprocessing the new surface image to obtain a sub-image to be detected includes: graying the surface image to obtain a grayscale image ; Divide the grayscale image into rectangular sliding windows to obtain a set of rectangular sub-images ,in, For the The rectangular sub-graph after the segmentation, = 1 , 2 ,...,n .

[0047] When graying the surface image, an existing image graying method can be used, including but not limited to selecting a pixel point for each pixel point of the surface image. The maximum value of the pixel value of the channel is taken as the gray value, and the pixel point is selected The average value of the pixel value of the channel is taken as the gray value, and the pixel point is selected The weighted average of the pixel values ​​of the channels is used as the grayscale value to grayscale the surface image to obtain a grayscale image. The pixel value of each pixel point of the grayscale image is the grayscale value obtained by the above calculation.

[0048] The purpose of sliding window segmentation is to Split into non-overlapping or partially overlapping subgraphs , the size of each sub-graph is , is the width of the rectangular sub-image after segmentation, is the height of the rectangular sub-image after segmentation, so as to avoid direct detection of large-format particle board surface images and improve the detection accuracy.

[0049] like Figure 2 As shown, the process of cutting the graph can be expressed as: , where Slice is a function that receives a large image and predefined sub-image sizes and the overlap ratio between subgraphs , and returns a set of segmented rectangular sub-graphs .

[0050] Furthermore, when the surface image is segmented into rectangular sliding windows, a fixed width and height should be used. A rectangular window, for example, of size A rectangular window is drawn from the upper left corner of the large-format particleboard image and moves to the right with a step size less than or equal to the window size to avoid missing defects at the edge of the sliding window. When the first row of windows moves to the end of the image width, the window returns to the beginning of this row and moves downward with a step size less than or equal to the window size. The window then continues to move from left to right, and finally a set of sub-images with a size equal to the rectangular window size is obtained.

[0051] The specific process of cutting the image is as follows: First, calculate the actual step length along the width and height of the image respectively and ,in, .

[0052] 。

[0053] 。

[0054] Then calculate the number of slices along the width direction and the number of slices along the height direction .

[0055] .

[0056] .

[0057] Then determine the position of each sub-graph , for each and , is the number of slice rows, is the number of slice columns, and there is the following formula.

[0058] 。

[0059] 。

[0060] 。

[0061] 。

[0062] When selecting the overlap ratio When, generally based on experience The remainder is 0 and The remainder result is 0.

[0063] According to the above formula, we can get the subgraph And a set of cut rectangular sub-graphs S .

[0064] In an exemplary embodiment, S2 may be replaced by the following steps.

[0065] For the above set of subgraphs to be detected Use a deep learning-based defect detection model to perform defect detection, stitch it back to the original image, perform NMS operation, and obtain a defect detection result set .

[0066] in , Indicates defects, , corresponding to the type of surface defects of each particle board , the center point of the defect area , Defect Width , Defect height and confidence .

[0067] Because when When the sub-images are cut, there are overlapping areas between them. If the step size of the sliding window is small when cutting the sub-images, there may be small defect targets in the repeated area, such as wood shavings, which will cause the defect target to be detected on both sub-images at the same time. There are two detection frames for the defect on the spliced ​​original image, resulting in repeated detection results. Therefore, NMS operation is required. The NMS method is a general method and will not be described here.

[0068] Among them, deep learning-based defect detection models can include target detection models such as YOLO series, SSD, Mask R-CNN, and VisionTransformer.

[0069] In the above embodiment, the surface defects of the particle board include seven categories: spot defects, wood chips, oil stains, edge chipping, chalk marks, surface scratches, and cracks.

[0070] In an exemplary embodiment, the defect detection result set Reclassify by category and obtain the detection result set of various defects ,in This is the set of the first type of plate defects. This is the set of defective wood shavings of the second type. That is the kThe set of defective wood chips is similar. For example, the first defect of the first type of spot defect can be expressed as: .

[0071] According to the above defect information, calculate The area parameter of each defect in Similarity to grayscale Among them, the grayscale similarity It is an indicator to characterize the similarity between the defect area and the background. is the average gray value of the defect area, is the average gray value of the background.

[0072] S3 can be replaced by the following steps.

[0073] S31: Exploitation Determine the area parameters of various defects; among them, is the first k Class Defect i The area parameter of the defect area; is the first k Class Defect i The width of the defect area; is the first k Class Defect i The height of the defect area.

[0074] S32: Exploitation Determine the grayscale similarity of each type of defect; among them, is the first k Class Defect i The grayscale similarity of the defect areas.

[0075] In an exemplary embodiment, S4 may be replaced by the following steps.

[0076] S41: Determine the maximum single defect area or maximum length according to different defect categories; the defect categories include spot defects, wood shavings, oil stains, edge chippings, chalk marks, surface scratches and cracks; among them, for spot defects, wood shavings, oil stains, edge chippings and chalk marks, determine the maximum single defect area; for surface scratches and cracks, determine the maximum length.

[0077] Furthermore, the number of defects of various types and the largest single defect area are counted to obtain the defect number vector and the maximum single area vector of each defect or maximum length For the first five types of defects, namely, patchy defects, wood shavings, oil stains, edge collapse, and chalk marks, it is necessary to calculate their maximum single area. For surface scratches and cracks, it is necessary to calculate the maximum side length .

[0078] .

[0079] .

[0080] S42: Determine the maximum single defect area and the maximum length based on the maximum single defect area and the maximum length. k Evaluation benchmark index value of this type of defect.

[0081] Furthermore, according to the actual grading and evaluation of the factory, the evaluation benchmark index value of the k-th defect is specified. , , is the defect quantity vector evaluation benchmark index value, is the benchmark index value for area vector evaluation.

[0082] In this embodiment, the defect quantity vector evaluation benchmark index value matrix is .

[0083] Assume that the area vector evaluation benchmark value matrix .

[0084] S43: Determine the defect quantization value of each type of defect according to the defect information and the evaluation benchmark index value.

[0085] Furthermore, for the Class defects, calculate their defect quantification value .

[0086] .

[0087] Get the quantized value matrix of 7 types of defects , For the k The number of class defects, Taken from The elements in .

[0088] In an exemplary embodiment, S5 may be replaced by the following steps.

[0089] S51: Calculate a grading correction coefficient according to the evaluation benchmark index value, the maximum single defect area and the maximum length.

[0090] Furthermore, the classification correction coefficients are calculated, including the defect quantity vector correction coefficient and area vector correction factor .

[0091] .

[0092] .

[0093] in, and are two constant coefficient vectors. In this embodiment, , ; is the classification adjustment factor; N is the defect quantity vector; T Represents the transposition of a vector.

[0094] S52: Calculate each type of defect score vector according to the grading correction coefficient.

[0095] Furthermore, after obtaining the correction coefficient, the score vectors of various defects are calculated according to the following formula: .

[0096] .

[0097] in, It indicates the maximum quantitative score that can be achieved without any defects. is the adjustment coefficient vector of the quantized values ​​of various defects. , .

[0098] S53: Determine the final score of the particle board according to the minimum defect score vector, the maximum defect score vector and the average defect score vector in each defect score vector.

[0099] Furthermore, the minimum value in the defect score vector : .

[0100] Calculate the average defect quantification score : .

[0101] Calculate the final score : .

[0102] In an exemplary embodiment, S6 may be replaced by the following steps.

[0103] S61: Exploitation Divide the board grades; among them, For the board grade, , , There are three board grades; For the final score; and is the classification adjustment factor; is the maximum value of the defect score vector.

[0104] In this embodiment, .

[0105] In order to evaluate the specific quantitative evaluation performance of this application, 274 particleboard images were selected for testing. Defect detection was performed on them and the defect detection results were saved. According to the defect detection results, the quantitative evaluation score of the appearance quality of each particleboard image was calculated, and the boards were divided into first-level, second-level, and third-level boards according to the scores. Table 1 is a grading result table of some example images.

[0106] Table 1

[0107]

[0108] This embodiment can achieve grading of the appearance quality of the particleboard surface by collecting statistics on the defect detection results of the particleboard surface image and designing corresponding quantitative evaluation indicators and quantitative evaluation methods.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a particleboard appearance quality quantitative evaluation device for implementing the particleboard appearance quality quantitative evaluation method mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more particleboard appearance quality quantitative evaluation device embodiments provided below can refer to the limitations of the particleboard appearance quality quantitative evaluation method mentioned above, and will not be repeated here.

[0110] In an exemplary embodiment, a device for quantitatively evaluating the appearance quality of particleboard is provided, comprising the following modules.

[0111] The module for determining the sub-image set to be detected is used to determine the sub-image set to be detected according to the surface image of the particle board.

[0112] The defect detection result set determination module is used to perform defect detection on the sub-image set to be detected based on a deep learning defect detection model to determine a defect detection result set.

[0113] The defect information determination module is used to divide the defect detection result set according to defect categories and determine the defect information of each defect category; the defect information includes area parameters and grayscale similarity.

[0114] The defect quantization value determination module is used to determine the defect quantization value of each type of defect according to the defect information.

[0115] The final score determination module is used to determine the final score of the particle board according to the defect quantification value of each type of defect.

[0116] An evaluation module is used to classify the board material according to the final score; the board material grade is used to evaluate the appearance quality of the particleboard.

[0117] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store particleboard appearance quality quantitative evaluation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a particleboard appearance quality quantitative evaluation method is implemented.

[0118] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above method is implemented when the processor executes the computer program.

[0119] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0120] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0122] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0123] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0125] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for quantitatively evaluating the appearance quality of particleboard, characterized in that: The particleboard appearance quality quantitative evaluation method comprises: According to the surface image of the particle board, a set of sub-images to be detected is determined; Perform defect detection on the set of sub-graphs to be detected based on a deep learning defect detection model to determine a set of defect detection results; According to defect categories, the defect detection result set is divided to determine defect information of each defect category; the defect information includes area parameters and grayscale similarity; Determine the defect quantification value of each type of defect according to the defect information, specifically including: determining the maximum single defect area or maximum length according to different defect categories; the defect categories include spot defects, wood shavings, oil stains, edge collapse, chalk marks, surface scratches and cracks; wherein, for spot defects, wood shavings, oil stains, edge collapse and chalk marks, determine the maximum single defect area; for surface scratches and cracks, determine the maximum length; based on the maximum single defect area and the maximum length, determine the maximum single defect area or maximum length; k Determine the defect quantification value of each type of defect according to the defect information and the evaluation benchmark indicator value; Determining a final score of the particle board according to the defect quantification value of each type of defect; The board grades are divided according to the final scores; the board grades are used to evaluate the appearance quality of the particleboard.

2. The particleboard appearance quality quantitative evaluation method according to claim 1, characterized in that: According to the surface image of the particle board, a set of sub-images to be detected is determined, including: Acquire a surface image of the particle board; the surface image includes at least one of a front surface image and a back surface image of the particle board; Using a viewfinder to perform trimming sampling on the surface image to determine a new surface image; Preprocessing the new surface image to determine a set of sub-images to be detected specifically includes: grayscale the new surface image to determine a grayscale image; The grayscale image is segmented using a rectangular sliding window to determine the segmented rectangular sub-images and a set of sub-images to be detected; the set of sub-images to be detected includes all the segmented rectangular sub-images.

3. The particleboard appearance quality quantitative evaluation method according to claim 1, characterized in that: According to the defect category, the defect detection result set is divided to determine the defect information of each defect category, specifically including: use Determine the area parameters of various defects; among them, is the first k Class Defect i The area parameter of the defect area; is the first k Class Defect i The width of the defect area; is the first k Class Defect i The height of the defect area; use Determine the grayscale similarity of various defects; among them, is the first k Class Defect i Grayscale similarity of defect areas; is the average gray value of the defect area; is the average gray value of the background.

4. The method for quantitatively evaluating the appearance quality of particleboard according to claim 1, characterized in that: The final score of the particleboard is determined based on the defect quantification value of each type of defect, including: Calculating a grading correction coefficient according to the evaluation benchmark index value, the maximum single defect area and the maximum length; Calculate each defect score vector according to the classification correction coefficient; The final score of the particle board is determined according to the minimum value of the defect score vector, the maximum value of the defect score vector and the average value of the defect score vector in each type of defect score vector.

5. The particleboard appearance quality quantitative evaluation method according to claim 1, characterized in that: The boards are graded according to the final scores, including: use Divide the board grades; among them, For the board grade, , , There are three board grades; For the final score; and is the classification adjustment factor; is the maximum value of the defect score vector.

6. A particleboard appearance quality quantitative evaluation device, characterized in that: The particleboard appearance quality quantitative evaluation device comprises: A module for determining a sub-image set to be detected, used for determining a sub-image set to be detected according to a surface image of the particle board; A defect detection result set determination module, used to perform defect detection on the sub-image set to be detected based on a deep learning defect detection model, and determine a defect detection result set; A defect information determination module, used to divide the defect detection result set according to defect categories and determine defect information of each defect category; the defect information includes area parameters and grayscale similarity; a defect quantization value determination module, used to determine the defect quantization value of each type of defect according to the defect information, specifically including: determining the maximum single defect area or maximum length according to different defect categories; the defect categories include spot defects, wood shavings, oil stains, edge collapse, chalk marks, surface scratches and cracks; wherein, for spot defects, wood shavings, oil stains, edge collapse and chalk marks, the maximum single defect area is determined; for surface scratches and cracks, the maximum length is determined; based on the maximum single defect area and the maximum length, the first k Determine the defect quantification value of each type of defect according to the defect information and the evaluation benchmark indicator value; A final score determination module, used to determine the final score of the particle board according to the defect quantification value of each type of defect; An evaluation module is used to classify the board material according to the final score; the board material grade is used to evaluate the appearance quality of the particleboard.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for quantitatively evaluating the appearance quality of particleboard according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for quantitatively evaluating the appearance quality of particleboard according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for quantitatively evaluating the appearance quality of particleboard according to any one of claims 1 to 5 is implemented.

Images