Corrugated carton production quality detection method and system based on intelligent analysis

Abstract

The invention discloses a corrugated carton production quality detection method and system based on intelligent analysis. The method comprises the following steps: firstly, acquiring front and side image data of a carton, extracting textural features by using LBP feature description, converting the textural features into feature vectors, and calculating vector data variance to judge material consistency; meanwhile, a preset point is set in the carton image area, the thickness value of the preset point is obtained and mapped into a gray value, the gray value is subjected to linear regression fitting to generate a linear equation, a transition gray value is obtained based on the fitting equation, the image area is filled, and a thickness distribution diagram based on gray expression is obtained; calculating a gray average value of each image area, comparing the gray average value with a standard value, evaluating thickness uniformity, and generating a thickness uniformity index; and finally, quality comprehensive evaluation is carried out by combining the material consistency and the thickness uniformity, and corrugated carton production equipment parameters are optimized, so that accurate detection and processing optimization control of carton quality are realized.

Description

Technical Field

[0001] The present invention relates to the field of carton production analysis, and more specifically, to a method and system for detecting the production quality of corrugated carton based on intelligent analysis. Background Art

[0002] As an essential component of the packaging industry, the quality of corrugated cardboard directly impacts product protection, transportation safety, and consumer experience. Traditional corrugated cardboard production quality testing relies primarily on manual visual inspection and simple physical measurements. This method is not only inefficient but also susceptible to human influence, making it difficult to guarantee the accuracy and consistency of test results. Furthermore, there is a lack of technical means to accurately analyze key quality indicators such as cardboard texture characteristics, material consistency, material uniformity, and thickness distribution. However, with the development of intelligent quality inspection using image analysis, the use of advanced information technology and intelligent methods to intelligently test the production quality of corrugated cardboard has become an inevitable trend in the industry. Therefore, a corrugated cardboard production quality inspection method based on intelligent analysis is urgently needed. Summary of the Invention

[0003] The present invention overcomes the defects of the prior art and proposes a method and system for detecting the production quality of corrugated paper boxes based on intelligent analysis.

[0004] A first aspect of the present invention provides a method for detecting the production quality of corrugated paper boxes based on intelligent analysis, comprising: Obtain the front image data and side image data of the target carton; Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value; Obtain a carton image area and divide it into N image areas. The center point of each image area is used as a preset point. Obtain the thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. Perform linear regression fitting based on N grayscale values and generate a linear equation. Obtain the transition grayscale value between every two grayscale values through the linear equation. Fill the transition grayscale value into N image regions to obtain a thickness distribution map based on grayscale representation. Calculate the grayscale mean of all pixels in each image area to obtain N grayscale means. Compare these N grayscale means with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Quality assessment is performed using the material consistency index and thickness uniformity index, and production equipment parameters are optimized.

[0005] In this solution, the front image data and side image data of the target carton are obtained as follows: Using a high-definition camera, during the corrugated box production process, the front and side image data of the target box are obtained after it is flattened. The front image data and the side image data are preprocessed by image enhancement, noise reduction and standardization.

[0006] In this solution, based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value, specifically: Grayscale processing is performed on the front image data and the side image data to generate a first grayscale image and a second grayscale image; In the first grayscale image, a 3×3 matrix area is set for each pixel, with the selected pixel as the center point. The grayscale value of the pixel in the matrix area is determined to be greater than or equal to the grayscale value of the center point. If so, it is marked as 1, otherwise it is marked as 0; After the matrix domain is judged, the grayscale values of the pixels in the domain are sequentially obtained to obtain a binary value, and the binary value is converted into a decimal number to obtain the LBP code of the matrix domain; Calculate the LBP code of each pixel and statistically form an LBP histogram, use the LBP histogram as a texture feature, and generate multiple LBP feature vectors through the LBP histogram; The variance of multiple LBP feature vectors is calculated, and the difference between the feature vectors is calculated by the Manhattan distance value, and the first variance is obtained; calculating a second variance based on the second grayscale image; The material consistency is evaluated based on the mean of the first variance and the second variance to obtain the material consistency index.

[0007] In this solution, the carton image area is obtained and divided into N image areas in the carton image area. The center point of each image area is used as a preset point, and the thickness value of the preset point is obtained. The thickness value is mapped to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas, specifically: For the front image data, obtain the carton image area of the target carton. In the carton image area, divide N image areas from left to right and set N preset points. The intervals between adjacent preset points are consistent, and each preset point corresponds to the center point of an image area. The thickness values of N preset points are measured and obtained, a mapping relationship between the thickness value interval and the grayscale value interval is established, and the thickness values are mapped into the preset grayscale range to obtain N grayscale values.

[0008] In this solution, linear regression fitting is performed based on N grayscale values to generate a linear equation. The transition grayscale value between every two grayscale values is obtained through the linear equation. The transition grayscale value is filled in the N image areas to obtain a thickness distribution map based on grayscale representation: By presetting a linear equation, taking N grayscale values as dependent variables and the pixel positions corresponding to the grayscale values as independent variables, a linear regression fitting is performed to generate a linear equation; Calculate the transition grayscale value between each grayscale value through a linear equation, and fill it into N image areas based on the transition grayscale value; In the carton image area, the transition grayscale value is calculated based on the linear equation, and the grayscale value of the pixels in the entire carton image area is filled so that the grayscale value of the pixels from left to right in the carton image area conforms to the numerical change of the linear equation, and a thickness distribution map based on grayscale representation is obtained.

[0009] In this solution, the grayscale mean of all pixels in each image area is calculated to obtain N grayscale means. The N grayscale means are compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index, which is specifically: Calculate the grayscale mean of all pixels in each image area and obtain N grayscale means; The difference between the N grayscale means and the standard value is calculated to generate an average difference, and the thickness uniformity index is generated based on the average difference.

[0010] In this solution, the material consistency index and thickness uniformity index are used to evaluate quality and optimize production equipment parameters, specifically: Obtain processing data corresponding to the material association step and the thickness processing step; Based on the material consistency index and thickness uniformity index, the material association step and thickness processing step are respectively inspected and evaluated for processing quality. The parameters of the processing equipment are optimized based on the processing data, and the equipment production is dynamically adjusted.

[0011] A second aspect of the present invention further provides a corrugated cardboard box production quality detection system based on intelligent analysis, the system comprising: a memory and a processor, the memory including a corrugated cardboard box production quality detection program based on intelligent analysis, the corrugated cardboard box production quality detection program based on intelligent analysis, when executed by the processor, implementing the following steps: Obtain the front image data and side image data of the target carton; Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value; Obtain a carton image area and divide it into N image areas. The center point of each image area is used as a preset point. Obtain the thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. Perform linear regression fitting based on N grayscale values and generate a linear equation. Obtain the transition grayscale value between every two grayscale values through the linear equation. Fill the transition grayscale value into N image regions to obtain a thickness distribution map based on grayscale representation. Calculate the grayscale mean of all pixels in each image area to obtain N grayscale means. Compare these N grayscale means with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Quality assessment is performed using the material consistency index and thickness uniformity index, and production equipment parameters are optimized.

[0012] The third aspect of the present invention also provides a computer-readable storage medium, which includes a corrugated cardboard production quality detection program based on intelligent analysis. When the corrugated cardboard production quality detection program based on intelligent analysis is executed by a processor, the steps of the corrugated cardboard production quality detection method based on intelligent analysis as described in any one of the above items are implemented.

[0013] The present invention discloses a corrugated cardboard production quality inspection method and system based on intelligent analysis. First, the front and side image data of the cardboard are obtained, and the texture features are extracted and converted into feature vectors using LBP feature description. The variance of the vector data is calculated to determine the consistency of the material. At the same time, preset points are set in the cardboard image area, and the thickness values of the preset points are obtained and mapped to grayscale values. The grayscale values are fitted to generate a linear equation through linear regression. Based on the fitted equation, the transition grayscale values are obtained and the image area is filled to obtain a thickness distribution map based on grayscale representation. The grayscale mean of each image area is calculated and compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Finally, a comprehensive quality assessment is performed by combining material consistency and thickness uniformity, and the parameters of the corrugated cardboard production equipment are optimized to achieve accurate detection of cardboard quality and processing optimization control. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart showing a method for detecting the production quality of corrugated paper boxes based on intelligent analysis according to the present invention is shown; Figure 2A block diagram of a corrugated box production quality inspection system based on intelligent analysis of the present invention is shown. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1 The flowchart of the present invention shows a method for detecting the production quality of corrugated paper boxes based on intelligent analysis.

[0018] like Figure 1 As shown, the first aspect of the present invention provides a method for detecting the production quality of corrugated paper boxes based on intelligent analysis, comprising: S102, obtaining front image data and side image data of the target carton; S104, performing regional texture feature extraction and feature vector conversion on the front image data and the side image data based on the LBP feature description form to obtain multiple LBP feature vectors, calculating data variance based on the multiple LBP feature vectors, and generating a material consistency index based on the variance value; S106: Acquire a carton image area and divide the carton image area into N image areas. The center point of each image area is used as a preset point. Obtain a thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. S108, performing linear regression fitting based on the N grayscale values and generating a linear equation, obtaining a transition grayscale value between every two grayscale values through the linear equation, filling the transition grayscale value into the N image regions, and obtaining a thickness distribution map based on grayscale representation; S110, calculating the grayscale mean of all pixels in each image area to obtain N grayscale mean values, and comparing the N grayscale mean values with standard values to evaluate thickness uniformity and generate a thickness uniformity index; S112, quality assessment is performed using the material consistency index and thickness uniformity index and parameters of production equipment are optimized.

[0019] According to an embodiment of the present invention, the obtaining of the front image data and the side image data of the target carton is specifically as follows: Using a high-definition camera, during the corrugated box production process, the front and side image data of the target box are obtained after it is flattened. The front image data and the side image data are preprocessed by image enhancement, noise reduction and standardization.

[0020] It should be noted that front image data refers to the image of the corrugated cardboard box when it is flattened, generally including both the front and back sides, collectively referred to herein as the front image, and stored in the front image data. It should be understood that the image data obtained here can be non-finished carton products, that is, corrugated paper products in the production process, which are subjected to quality inspection and early production intervention if any abnormalities are found. Side image data specifically refers to the image of the cross section of the carton, which can be used to analyze the texture and thickness information of the corrugated paper cross section.

[0021] According to an embodiment of the present invention, based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors, data variance is calculated based on the multiple LBP feature vectors, and a material consistency index is generated based on the variance value, specifically: grayscale processing is performed on the front image data and the side image data to generate a first grayscale image and a second grayscale image; In the first grayscale image, a 3×3 matrix area is set for each pixel, with the selected pixel as the center point. The grayscale value of the pixel in the matrix area is determined to be greater than or equal to the grayscale value of the center point. If so, it is marked as 1, otherwise it is marked as 0; After the matrix domain is judged, the grayscale values of the pixels in the domain are sequentially obtained to obtain a binary value, and the binary value is converted into a decimal number to obtain the LBP code of the matrix domain; Calculate the LBP code of each pixel and statistically form an LBP histogram, use the LBP histogram as a texture feature, and generate multiple LBP feature vectors through the LBP histogram; The variance of multiple LBP feature vectors is calculated, and the difference between the feature vectors is calculated by the Manhattan distance value, and the first variance is obtained; calculating a second variance based on the second grayscale image; The material consistency is evaluated based on the mean of the first variance and the second variance to obtain the material consistency index.

[0022] It should be noted that texture features can reflect the distribution of material texture and the uniformity of the material. The uniformity and standardization of the material greatly affect the production quality and qualified rate of corrugated boxes. The binary values are obtained sequentially, that is, the 8 values ​​except the center point are obtained sequentially. The value in the upper left corner of the 3×3 area can be used as the first value, and the binary value is an 8-bit binary number. The feature vector extraction process is performed for each pixel point to achieve regional texture feature extraction. The LBP feature vector can reflect the material texture characteristics in vector form. The second variance is calculated in the same way as the first method.

[0023] The variance of multiple LBP feature vectors is calculated, that is, each LBP feature vector is taken as a data point for variance calculation, and the difference between data points is calculated using Manhattan distance.

[0024] The larger the variance, the greater the degree of discreteness of the texture features and texture contours, and the lower the degree of material consistency. The LBP form of texture feature calculation is suitable for surface images and cross-sectional images of corrugated paper (corresponding to front image data and side image data).

[0025] The material consistency index is as follows:

[0026] Where P is the material consistency index, S1 and S2 are the first and second variances, respectively. Specifically, the material consistency index is equal to the inverse of the mean of the first and second variances, and is inversely proportional to the mean of the first and second variances.

[0027] Manhattan distance is calculated as follows: ; d is the distance representation, A and B are two eigenvectors, is the value of the k-th dimension of vector A, is the value of the kth dimension of vector B, and n is the total number of dimensions of the vector.

[0028] According to an embodiment of the present invention, the carton image area is obtained, and N image areas are divided in the carton image area. The center point of each image area is used as a preset point, and the thickness value of the preset point is obtained. The thickness value is mapped within a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas, specifically: For the front image data, obtain the carton image area of the target carton. In the carton image area, divide N image areas from left to right and set N preset points. The intervals between adjacent preset points are consistent, and each preset point corresponds to the center point of an image area. The thickness values of N preset points are measured and obtained, a mapping relationship between the thickness value interval and the grayscale value interval is established, and the thickness values are mapped into the preset grayscale range to obtain N grayscale values.

[0029] It should be noted that the mapping relationship between the thickness value interval and the grayscale value interval is specifically to map [min, max] to [0, 255], where min and max are the minimum and maximum thickness values, and the mapping method is consistent with the data normalization form.

[0030] It is worth mentioning here that traditional technology has difficulty in analyzing the material uniformity and thickness distribution differences of cartons. If the cartons are subjected to multi-point inspection or the texture material and other quality issues of the cartons are analyzed through manual experience, it will greatly consume manpower and material resources and is not very practical. Therefore, the present invention uses the LBP operator to extract texture features of the carton material image and calculates the corresponding feature vector based on the LBP operator. The LBP operator can analyze the texture and contour features of each pixel in the form of a matrix field, and generate feature data by statistically analyzing the LBP histogram. The degree of consistency of the material is judged based on the variance of the data. This method is suitable for material distribution analysis of cartons. As for thickness distribution, the present invention obtains the thickness values of multiple preset points and maps them to the grayscale values of the image, and expresses the thickness distribution in grayscale values. It can be understood here that for the thickness distribution of corrugated boxes, it generally conforms to regional linear changes. Based on this, the present invention linearly fits the grayscale values of preset points in a carton image area in the form of grayscale values, infers the grayscale values of the remaining pixel positions by fitting linear equations, and forms a thickness distribution map by filling in transition grayscale values, so that the thickness distribution can be analyzed as a whole, and the quality thickness distribution can be detected in a more intuitive and efficient form.

[0031] In addition, in the carton image area of the present invention, the area is specifically divided in the horizontal direction, and linear equation fitting is performed to realize the grayscale value filling of each area from left to right. Based on the distribution accuracy requirements and quality requirements of the carton, horizontal and vertical area division can be performed. For example, 6×6 image areas are divided in a grid form, and the grayscale value of the center point of each image area is obtained (obtained by measuring the thickness value), and multiple continuous image areas are set to perform linear grayscale value linear fitting. For example, the grayscale values corresponding to the 6 vertically connected areas are set for linear fitting, and the transition grayscale value is calculated and filled.

[0032] According to an embodiment of the present invention, the linear regression fitting is performed based on N grayscale values, and a linear equation is generated. The transition grayscale value between each two grayscale values is obtained through the linear equation, and the transition grayscale value is filled in the N image areas. The thickness distribution map based on grayscale representation is specifically obtained as follows: By presetting a linear equation, taking N grayscale values as dependent variables and the pixel positions corresponding to the grayscale values as independent variables, a linear regression fitting is performed to generate a linear equation; Calculate the transition grayscale value between each grayscale value through a linear equation, and fill it into N image areas based on the transition grayscale value; In the carton image area, the transition grayscale value is calculated based on the linear equation, and the grayscale value of the pixels in the entire carton image area is filled so that the grayscale value of the pixels from left to right in the carton image area conforms to the numerical change of the linear equation, and a thickness distribution map based on grayscale representation is obtained.

[0033] It should be noted that the transition grayscale value is calculated using a linear equation. The linear equation determines the change trend of the overall carton grayscale, and further determines the thickness change trend, thereby realizing intelligent thickness distribution analysis, optimizing production steps, and improving the production process and quality detection capabilities of corrugated paper.

[0034] The linear equation is specifically:

[0035] Among them, β0 is the intercept, is the slope, is the error term, The independent variable and the dependent variable are respectively. When the pixel position corresponding to the grayscale value is used as the independent variable, the x (horizontal) coordinate of the pixel can be used as the pixel position and set as the independent variable.

[0036] According to an embodiment of the present invention, the grayscale mean of all pixels in each image area is calculated to obtain N grayscale means. The N grayscale means are compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index, which is specifically: Calculate the grayscale mean of all pixels in each image area and obtain N grayscale means; The difference between the N grayscale means and the standard value is calculated to generate an average difference, and the thickness uniformity index is generated based on the average difference.

[0037] It should be noted that the standard value can be set within 10, which is specifically set by production quality requirements. The smaller the value, the higher the thickness uniformity requirement for corrugated paper. The thickness uniformity index is inversely proportional to the average difference. The larger the average difference, the lower the thickness uniformity.

[0038] According to an embodiment of the present invention, the quality assessment is performed using the material consistency index and the thickness uniformity index and the parameters of the production equipment are optimized, specifically: Obtain processing data corresponding to the material association step and the thickness processing step; Based on the material consistency index and thickness uniformity index, the material association step and thickness processing step are respectively inspected and evaluated for processing quality. The parameters of the processing equipment are optimized based on the processing data, and the equipment production is dynamically adjusted.

[0039] It should be noted that the processing data includes parameter settings, processing time, processing detection information, etc. Material-related steps include raw material selection, corrugated roller rolling and forming, bonding and forming, and other processing steps that are related to material texture. Thickness processing steps include flattening, die-cutting, drying, printing and other steps. This step has a great influence and correlation with the thickness distribution change of the carton. The material consistency index and thickness uniformity index can be used to conduct refined detection and evaluation of processing quality, and further adjust the parameters and optimize the processing steps to achieve efficient quality detection and intelligent processing optimization of corrugated paper, reduce manpower and material resources consumption, and improve the level of automated production.

[0040] According to an embodiment of the present invention, the further embodiment includes: In the thickness distribution map, obtain grayscale images of N image regions; Calculate the maximum grayscale value, minimum grayscale value, grayscale mean, and grayscale variance in each grayscale image, and set the grayscale vector based on these four values; Generate N grayscale vectors based on N image regions; Based on the DBSCAN clustering algorithm, the domain radius and the minimum number of neighbors are set to perform density clustering on N grayscale vectors. The distance between grayscale vectors is calculated using the Manhattan distance, and M clusters are finally formed. Based on the size of N, it is evenly divided into Z numerical intervals, and the thickness consistency of the target carton is judged based on the numerical interval to which the cluster number M belongs.

[0041] It should be noted that, in an embodiment of the present invention, in addition to evaluating thickness uniformity by comparing N grayscale means with standard values, thickness uniformity can also be analyzed based on clustering. For the thickness distribution analysis of large cartons, it is often necessary to perform refined analysis of thickness uniformity in multiple regions. Therefore, the present invention sets a grayscale vector based on the grayscale characteristics of the image area to reflect the thickness characteristics of the area, and uses density clustering to determine the classification of N regions, and determines thickness consistency based on the number of clusters. This process can perform thickness distribution feature analysis on multiple regions, realize efficient and intelligent carton quality inspection, greatly reduce the participation of manual experience, and improve the level of automated carton inspection.

[0042] Based on the size of N, it is evenly divided into Z numerical intervals. For example, if N is 36 and Z is 6, it can be evenly divided into 6 intervals: [1, 6], [7, 12], [13, 18], [19, 24], [25, 30], and [31, 36]. The smaller M is, the closer to the interval it belongs, which means the thickness consistency is higher.

[0043] It should be noted that the grayscale vector includes four-dimensional values, and the values of each dimension are the maximum grayscale value, the minimum grayscale value, the grayscale mean, and the grayscale variance.

[0044] Figure 2 A block diagram of a corrugated box production quality inspection system based on intelligent analysis of the present invention is shown.

[0045] A second aspect of the present invention further provides a corrugated cardboard production quality detection system 2 based on intelligent analysis, the system comprising: a memory 21 and a processor 22, wherein the memory 21 includes a corrugated cardboard production quality detection program based on intelligent analysis, and when the corrugated cardboard production quality detection program based on intelligent analysis is executed by the processor 22, the following steps are implemented: Obtain the front image data and side image data of the target carton; Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value; Obtain a carton image area and divide it into N image areas. The center point of each image area is used as a preset point. Obtain the thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. Perform linear regression fitting based on N grayscale values and generate a linear equation. Obtain the transition grayscale value between every two grayscale values through the linear equation. Fill the transition grayscale value into N image regions to obtain a thickness distribution map based on grayscale representation. Calculate the grayscale mean of all pixels in each image area to obtain N grayscale means. Compare these N grayscale means with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Quality assessment is performed using the material consistency index and thickness uniformity index, and production equipment parameters are optimized.

[0046] According to an embodiment of the present invention, the obtaining of the front image data and the side image data of the target carton is specifically as follows: Using a high-definition camera, during the corrugated box production process, the front and side image data of the target box are obtained after it is flattened. The front image data and the side image data are preprocessed by image enhancement, noise reduction and standardization.

[0047] It should be noted that front image data refers to the image of the corrugated cardboard box when it is flattened, generally including both the front and back sides, collectively referred to herein as the front image, and stored in the front image data. It should be understood that the image data obtained here can be non-finished carton products, that is, corrugated paper products in the production process, which are subjected to quality inspection and early production intervention if any abnormalities are found. Side image data specifically refers to the image of the cross section of the carton, which can be used to analyze the texture and thickness information of the corrugated paper cross section.

[0048] According to an embodiment of the present invention, based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors, data variance is calculated based on the multiple LBP feature vectors, and a material consistency index is generated based on the variance value, specifically: grayscale processing is performed on the front image data and the side image data to generate a first grayscale image and a second grayscale image; In the first grayscale image, a 3×3 matrix area is set for each pixel, with the selected pixel as the center point. The grayscale value of the pixel in the matrix area is determined to be greater than or equal to the grayscale value of the center point. If so, it is marked as 1, otherwise it is marked as 0; After the matrix domain is judged, the grayscale values of the pixels in the domain are sequentially obtained to obtain a binary value, and the binary value is converted into a decimal number to obtain the LBP code of the matrix domain; Calculate the LBP code of each pixel and statistically form an LBP histogram, use the LBP histogram as a texture feature, and generate multiple LBP feature vectors through the LBP histogram; The variance of multiple LBP feature vectors is calculated, and the difference between the feature vectors is calculated by the Manhattan distance value, and the first variance is obtained; calculating a second variance based on the second grayscale image; The material consistency is evaluated based on the mean of the first variance and the second variance to obtain the material consistency index.

[0049] It should be noted that texture features can reflect the distribution of material texture and the uniformity of the material. The uniformity and standardization of the material greatly affect the production quality and qualified rate of corrugated boxes. The binary values are obtained sequentially, that is, the 8 values ​​except the center point are obtained sequentially. The value in the upper left corner of the 3×3 area can be used as the first value, and the binary value is an 8-bit binary number. The feature vector extraction process is performed for each pixel point to achieve regional texture feature extraction. The LBP feature vector can reflect the material texture characteristics in vector form. The second variance is calculated in the same way as the first method.

[0050] The variance of multiple LBP feature vectors is calculated, that is, each LBP feature vector is taken as a data point for variance calculation, and the difference between data points is calculated using Manhattan distance.

[0051] The larger the variance, the greater the degree of discreteness of the texture features and texture contours, and the lower the degree of material consistency. The LBP form of texture feature calculation is suitable for surface images and cross-sectional images of corrugated paper (corresponding to front image data and side image data).

[0052] The material consistency index is as follows:

[0053] Where P is the material consistency index, S1 and S2 are the first and second variances, respectively. Specifically, the material consistency index is equal to the inverse of the mean of the first and second variances, and is inversely proportional to the mean of the first and second variances.

[0054] Manhattan distance is calculated as follows:

[0055] d is the distance representation, A and B are two eigenvectors, is the value of the k-th dimension of vector A, is the value of the kth dimension of vector B, and n is the total number of dimensions of the vector.

[0056] According to an embodiment of the present invention, the carton image area is obtained, and N image areas are divided in the carton image area. The center point of each image area is used as a preset point, and the thickness value of the preset point is obtained. The thickness value is mapped within a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas, specifically: For the front image data, obtain the carton image area of the target carton. In the carton image area, divide N image areas from left to right and set N preset points. The intervals between adjacent preset points are consistent, and each preset point corresponds to the center point of an image area. The thickness values of N preset points are measured and obtained, a mapping relationship between the thickness value interval and the grayscale value interval is established, and the thickness values are mapped into the preset grayscale range to obtain N grayscale values.

[0057] It should be noted that the mapping relationship between the thickness value interval and the grayscale value interval is specifically to map [min, max] to [0, 255], where min and max are the minimum and maximum thickness values, and the mapping method is consistent with the data normalization form.

[0058] It is worth mentioning here that traditional technology has difficulty in analyzing the material uniformity and thickness distribution differences of cartons. If the cartons are subjected to multi-point inspection or the texture material and other quality issues of the cartons are analyzed through manual experience, it will greatly consume manpower and material resources and is not very practical. Therefore, the present invention uses the LBP operator to extract texture features of the carton material image and calculates the corresponding feature vector based on the LBP operator. The LBP operator can analyze the texture and contour features of each pixel in the form of a matrix field, and generate feature data by statistically analyzing the LBP histogram. The degree of consistency of the material is judged based on the variance of the data. This method is suitable for material distribution analysis of cartons. As for thickness distribution, the present invention obtains the thickness values of multiple preset points and maps them to the grayscale values of the image, and expresses the thickness distribution in grayscale values. It can be understood here that for the thickness distribution of corrugated boxes, it generally conforms to regional linear changes. Based on this, the present invention linearly fits the grayscale values of preset points in a carton image area in the form of grayscale values, infers the grayscale values of the remaining pixel positions by fitting linear equations, and forms a thickness distribution map by filling in transition grayscale values, so that the thickness distribution can be analyzed as a whole, and the quality thickness distribution can be detected in a more intuitive and efficient form.

[0059] In addition, in the carton image area of the present invention, the area is specifically divided in the horizontal direction, and linear equation fitting is performed to realize the grayscale value filling of each area from left to right. Based on the distribution accuracy requirements and quality requirements of the carton, horizontal and vertical area division can be performed. For example, 6×6 image areas are divided in a grid form, and the grayscale value of the center point of each image area is obtained (obtained by measuring the thickness value), and multiple continuous image areas are set to perform linear grayscale value linear fitting. For example, the grayscale values corresponding to the 6 vertically connected areas are set for linear fitting, and the transition grayscale value is calculated and filled.

[0060] According to an embodiment of the present invention, the linear regression fitting is performed based on N grayscale values, and a linear equation is generated. The transition grayscale value between each two grayscale values is obtained through the linear equation, and the transition grayscale value is filled in the N image areas. The thickness distribution map based on grayscale representation is specifically obtained as follows: By presetting a linear equation, taking N grayscale values as dependent variables and the pixel positions corresponding to the grayscale values as independent variables, a linear regression fitting is performed to generate a linear equation; Calculate the transition grayscale value between each grayscale value through a linear equation, and fill it into N image areas based on the transition grayscale value; In the carton image area, the transition grayscale value is calculated based on the linear equation, and the grayscale value of the pixels in the entire carton image area is filled so that the grayscale value of the pixels from left to right in the carton image area conforms to the numerical change of the linear equation, and a thickness distribution map based on grayscale representation is obtained.

[0061] It should be noted that the transition grayscale value is calculated using a linear equation. The linear equation determines the change trend of the overall carton grayscale, and further determines the thickness change trend, thereby realizing intelligent thickness distribution analysis, optimizing production steps, and improving the production process and quality detection capabilities of corrugated paper.

[0062] The linear equation is specifically:

[0063] Among them, β0 is the intercept, is the slope, is the error term, The independent variable and the dependent variable are respectively. When the pixel position corresponding to the grayscale value is used as the independent variable, the x (horizontal) coordinate of the pixel can be used as the pixel position and set as the independent variable.

[0064] According to an embodiment of the present invention, the grayscale mean of all pixels in each image area is calculated to obtain N grayscale means. The N grayscale means are compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index, which is specifically: Calculate the grayscale mean of all pixels in each image area and obtain N grayscale means; The difference between the N grayscale means and the standard value is calculated to generate an average difference, and the thickness uniformity index is generated based on the average difference.

[0065] It should be noted that the standard value can be set within 10, which is specifically set by production quality requirements. The smaller the value, the higher the thickness uniformity requirement for corrugated paper. The thickness uniformity index is inversely proportional to the average difference. The larger the average difference, the lower the thickness uniformity.

[0066] According to an embodiment of the present invention, the quality assessment is performed using the material consistency index and the thickness uniformity index and the parameters of the production equipment are optimized, specifically: Obtain processing data corresponding to the material association step and the thickness processing step; Based on the material consistency index and thickness uniformity index, the material association step and thickness processing step are respectively inspected and evaluated for processing quality. The parameters of the processing equipment are optimized based on the processing data, and the equipment production is dynamically adjusted.

[0067] It should be noted that the processing data includes parameter settings, processing time, processing detection information, etc. Material-related steps include raw material selection, corrugated roller rolling and forming, bonding and forming, and other processing steps that are related to material texture. Thickness processing steps include flattening, die-cutting, drying, printing and other steps. This step has a great influence and correlation with the thickness distribution change of the carton. The material consistency index and thickness uniformity index can be used to conduct refined detection and evaluation of processing quality, and further adjust the parameters and optimize the processing steps to achieve efficient quality detection and intelligent processing optimization of corrugated paper, reduce manpower and material resources consumption, and improve the level of automated production.

[0068] The third aspect of the present invention also provides a computer-readable storage medium, which includes a corrugated cardboard production quality detection program based on intelligent analysis. When the corrugated cardboard production quality detection program based on intelligent analysis is executed by a processor, the steps of the corrugated cardboard production quality detection method based on intelligent analysis as described in any one of the above items are implemented.

[0069] The present invention discloses a corrugated cardboard production quality inspection method and system based on intelligent analysis. First, the front and side image data of the cardboard are obtained, and the texture features are extracted and converted into feature vectors using LBP feature description. The variance of the vector data is calculated to determine the consistency of the material. At the same time, preset points are set in the cardboard image area, and the thickness values of the preset points are obtained and mapped to grayscale values. The grayscale values are fitted to generate a linear equation through linear regression. Based on the fitted equation, the transition grayscale values are obtained and the image area is filled to obtain a thickness distribution map based on grayscale representation. The grayscale mean of each image area is calculated and compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Finally, a comprehensive quality assessment is performed by combining material consistency and thickness uniformity, and the parameters of the corrugated cardboard production equipment are optimized to achieve accurate detection of cardboard quality and processing optimization control.

[0070] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0071] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0072] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0073] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0074] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0075] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis, characterized in that: include: Obtain the front image data and side image data of the target carton; Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value; Obtain a carton image area and divide it into N image areas. The center point of each image area is used as a preset point. Obtain the thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. Perform linear regression fitting based on N grayscale values and generate a linear equation. Obtain the transition grayscale value between every two grayscale values through the linear equation. Fill the transition grayscale value into N image regions to obtain a thickness distribution map based on grayscale representation. Calculate the grayscale mean of all pixels in each image area to obtain N grayscale means. Compare these N grayscale means with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Quality assessment is performed using the material consistency index and thickness uniformity index, and production equipment parameters are optimized.

2. A method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: The acquisition of the front image data and the side image data of the target carton is specifically as follows: Using a high-definition camera, during the corrugated box production process, the front and side image data of the target box are obtained after it is flattened. The front image data and the side image data are preprocessed by image enhancement, noise reduction and standardization.

3. The method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors, data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value, specifically: Grayscale processing is performed on the front image data and the side image data to generate a first grayscale image and a second grayscale image; In the first grayscale image, a 3×3 matrix area is set for each pixel, with the selected pixel as the center point. The grayscale value of the pixel in the matrix area is determined to be greater than or equal to the grayscale value of the center point. If so, it is marked as 1, otherwise it is marked as 0; After the matrix domain is judged, the grayscale values of the pixels in the domain are sequentially obtained to obtain a binary value, and the binary value is converted into a decimal number to obtain the LBP code of the matrix domain; Calculate the LBP code of each pixel and statistically form an LBP histogram, use the LBP histogram as a texture feature, and generate multiple LBP feature vectors through the LBP histogram; The variance of multiple LBP feature vectors is calculated, and the difference between the feature vectors is calculated by the Manhattan distance value, and the first variance is obtained; calculating a second variance based on the second grayscale image; The material consistency is evaluated based on the mean of the first variance and the second variance to obtain the material consistency index.

4. The method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: The carton image area is obtained, and N image areas are divided in the carton image area. The center point of each image area is used as a preset point, and the thickness value of the preset point is obtained. The thickness value is mapped within a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas, specifically: For the front image data, obtain the carton image area of the target carton. In the carton image area, divide N image areas from left to right and set N preset points. The intervals between adjacent preset points are consistent, and each preset point corresponds to the center point of an image area. The thickness values of N preset points are measured and obtained, a mapping relationship between the thickness value interval and the grayscale value interval is established, and the thickness values are mapped into the preset grayscale range to obtain N grayscale values.

5. The method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: The linear regression fitting is performed based on N grayscale values to generate a linear equation. The transition grayscale value between every two grayscale values is obtained through the linear equation. The transition grayscale value is filled in the N image areas to obtain a thickness distribution map based on grayscale representation: By presetting a linear equation, taking N grayscale values as dependent variables and the pixel positions corresponding to the grayscale values as independent variables, a linear regression fitting is performed to generate a linear equation; Calculate the transition grayscale value between each grayscale value through a linear equation, and fill it into N image areas based on the transition grayscale value; In the carton image area, the transition grayscale value is calculated based on the linear equation, and the grayscale value of the pixels in the entire carton image area is filled so that the grayscale value of the pixels from left to right in the carton image area conforms to the numerical change of the linear equation, and a thickness distribution map based on grayscale representation is obtained.

6. The method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: The grayscale mean of all pixels in each image area is calculated to obtain N grayscale means. The N grayscale means are compared with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index, which is specifically: Calculate the grayscale mean of all pixels in each image area and obtain N grayscale means; The difference between the N grayscale means and the standard value is calculated to generate an average difference, and the thickness uniformity index is generated based on the average difference.

7. The method for detecting the production quality of corrugated paperboard boxes based on intelligent analysis according to claim 1, characterized in that: The quality assessment is performed through the material consistency index and thickness uniformity index and the parameters of the production equipment are optimized, specifically: Obtain processing data corresponding to the material association step and the thickness processing step; Based on the material consistency index and thickness uniformity index, the material association step and thickness processing step are respectively inspected and evaluated for processing quality. The parameters of the processing equipment are optimized based on the processing data, and the equipment production is dynamically adjusted.

8. A corrugated box production quality inspection system based on intelligent analysis, characterized in that: The system includes: a memory and a processor. The memory includes a corrugated cardboard box production quality detection program based on intelligent analysis. When the corrugated cardboard box production quality detection program based on intelligent analysis is executed by the processor, the following steps are implemented: Obtain the front image data and side image data of the target carton; Based on the LBP feature description form, regional texture feature extraction and feature vector conversion are performed on the front image data and the side image data to obtain multiple LBP feature vectors. The data variance is calculated based on the multiple LBP feature vectors, and the material consistency index is generated based on the variance value; Obtain a carton image area and divide it into N image areas. The center point of each image area is used as a preset point. Obtain the thickness value of the preset point. Map the thickness value to a preset grayscale range to obtain N grayscale values. The N grayscale values are the grayscale values of the center pixels of the N image areas. Perform linear regression fitting based on N grayscale values and generate a linear equation. Obtain the transition grayscale value between every two grayscale values through the linear equation. Fill the transition grayscale value into N image regions to obtain a thickness distribution map based on grayscale representation. Calculate the grayscale mean of all pixels in each image area to obtain N grayscale means. Compare these N grayscale means with the standard value to evaluate the thickness uniformity and generate a thickness uniformity index. Quality assessment is performed using the material consistency index and thickness uniformity index, and production equipment parameters are optimized.

9. The corrugated box production quality inspection system based on intelligent analysis according to claim 8, characterized in that: The acquisition of the front image data and the side image data of the target carton is specifically as follows: Using a high-definition camera, during the corrugated box production process, the front and side image data of the target box are obtained after it is flattened. The front image data and the side image data are preprocessed by image enhancement, noise reduction and standardization.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a corrugated cardboard production quality detection program based on intelligent analysis. When the corrugated cardboard production quality detection program based on intelligent analysis is executed by the processor, the steps of the corrugated cardboard production quality detection method based on intelligent analysis as described in any one of claims 1 to 7 are implemented.

Images