Machine vision-based detection method for the adhesion of special-shaped filter rod forming paper

Abstract

The present invention discloses a method for detecting the fit of shaped filter rod forming paper based on machine vision. The main design concept of the present invention is to combine machine vision technology to detect the state of the forming paper of the shaped filter rod, that is, to extract a variety of contour-related information from the filter rod end face image to accurately identify the gap portion where the filter rod forming paper is not in contact with the filter rod tow. Then, the geometric information of the filter rod outer contour and the inner contour generated by the unfitted area is used to obtain parameter indicators for evaluating the fit from different dimensions. Finally, the results corresponding to the multi-dimensional indicators are integrated to determine the quality of the shaped filter rod product. The gap detection and indicator determination method proposed by the present invention provides accurate and real data support for shaped filter rod detection in a more scientific way, has guiding significance for the production of shaped filter rods, and also provides a solid foundation for improving the level of cigarette manufacturing.

Description

Technical Field

[0001] The present invention relates to the field of cigarette manufacturing, and in particular to a method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision. Background Art

[0002] The public's demand for cigarette consumption is becoming increasingly diversified and personalized. In order to meet the growing needs of consumers, various cigarettes with distinctive characteristics such as short, thin and medium-burst have emerged. Among them, filters with different shapes, appearances and functions are also one of the diversified product directions. For example, special-shaped filters with hollow composite structures are widely loved by consumers. Such special-shaped hollow composite filter rods are generally used in high-end cigarettes. Therefore, consumers have high requirements for the smoking experience, novelty and aesthetics of the filters.

[0003] The hollow section of a special-shaped filter tip is manufactured using a special process. While it offers advantages such as high hardness and aesthetic appeal, it also suffers from poor outer circumference roundness. This roundness issue can lead to delamination during the composite molding of the tipping paper and the hollow section of the filter tip, resulting in poor fit between the tipping paper and the filter tip, which in turn affects the aesthetics and smoking experience of the final product. Therefore, the industry urgently needs a solution that can reliably detect the fit of the tipping paper for specific special-shaped filter tips to assess its impact on subsequent processes and final product quality. Summary of the Invention

[0004] In view of the above, the present invention aims to provide a method for detecting the fit of special-shaped filter rod forming paper based on machine vision, so as to make up for the lack of detection of the forming effect of special-shaped filter rods in the industry.

[0005] The technical solution adopted in the present invention is as follows:

[0006] A method for detecting the conformity of special-shaped filter rod forming paper based on machine vision, comprising:

[0007] Acquire an end face image of the filter rod to be tested;

[0008] Extracting the outer contour line of the filter rod to be tested and the inner contour line of the unattached area of ​​the forming paper based on the end face image;

[0009] Obtaining the height of the non-attached area according to the outer contour line and the inner contour line;

[0010] Calculating the area of ​​the non-fitted region according to the outer contour line, the inner contour line, and the height;

[0011] Obtain at least two index parameters using the outer contour line, the inner contour line, and the area;

[0012] The index parameters are integrated with the preset standard threshold to determine whether the forming paper fit of the filter rod to be tested is qualified.

[0013] In at least one possible implementation manner, obtaining at least two indicator parameters by using the outer contour line, the inner contour line, and the area includes:

[0014] Calculating the delamination coefficient of the unfitted area according to the length information of the outer contour line and the inner contour line; and

[0015] The average height coefficient of the non-bonded area is calculated according to the area of ​​the non-bonded area and the length of the inner contour line.

[0016] In at least one possible implementation manner, the layering coefficient is a ratio of the length of the inner contour line to the length of the outer contour line.

[0017] In at least one possible implementation manner, the average height coefficient is a ratio of the area to the length of the inner contour line.

[0018] In at least one possible implementation, the fusing of the index parameters and combining with a preset standard threshold to determine whether the forming paper conformity of the filter rod to be tested is qualified includes:

[0019] The normalized results of the plurality of indicator parameters are weighted according to preset weights to obtain an evaluation score;

[0020] Whether the forming paper's lamination degree is qualified is determined based on a comparison result between the evaluation score and a preset standard score.

[0021] In at least one possible implementation, the fusing of the index parameters and combining with a preset standard threshold to determine whether the forming paper conformity of the filter rod to be tested is qualified includes:

[0022] Based on the indicator parameters, obtaining respective preliminary evaluation results;

[0023] Based on the preliminary evaluation results, the degree of adhesion of the forming paper is determined according to the preset grades.

[0024] In at least one possible implementation, extracting the outer contour of the filter rod to be tested and the inner contour of the unattached area of ​​the forming paper based on the end face image includes:

[0025] Using an edge detection algorithm, obtaining a plurality of image edge information representing the peripheral contour and the hollow contour of the filter rod to be tested in the end face image;

[0026] The outer contour line and the inner contour line composed of pixel points are extracted based on the mutual position relationship and shape structure characteristics between the edge information of each image.

[0027] In at least one possible implementation, the detection method further includes:

[0028] Before extracting the contour, filtering and denoising the end face image and removing image distortion are performed;

[0029] The processed image is converted into a grayscale image, and the grayscale image is converted into a binary image.

[0030] The main design concept of this invention is to combine machine vision technology to detect the state of the filter paper of special-shaped filter rods. Specifically, it extracts a variety of contour-related information from the filter rod end face image to accurately identify the gaps where the filter rod forming paper is not bonded to the filter rod tow. Then, the geometric information of the filter rod's outer contour and the inner contour generated by the unbonded area is used to obtain parameter indicators for evaluating the degree of fit from different dimensions. Finally, the results corresponding to the multi-dimensional indicators are integrated to determine the quality of the special-shaped filter rod product. The gap detection and indicator determination method proposed by this invention provides more scientific and accurate data support for the detection of special-shaped filter rods, which is of guiding significance for the production of special-shaped filter rods and provides a solid foundation for improving the level of cigarette manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0032] Figure 1 A flow chart of a method for detecting the fit of special-shaped filter plug forming paper based on machine vision provided in an embodiment of the present invention;

[0033] Figure 2 A schematic cross-sectional view of a filter rod to be tested provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0035] The present invention proposes an embodiment of a method for detecting the conformity of special-shaped filter plug forming paper based on machine vision. Specifically, Figure 1 shown, including:

[0036] Step S1, obtaining an end face image of the filter rod to be tested;

[0037] In actual operation, an industrial CCD camera can be used to scan the end face of the special-shaped hollow filter rod. Compared with traditional projection measurement imaging, the measurement accuracy of high-resolution CCD imaging equipment can reach the micron level, so clear and comprehensive end face information of the filter rod to be tested can be obtained.

[0038] Step S2, extracting the outer contour line of the end face of the filter rod to be tested and the inner contour line of the area where the forming paper is not attached based on the end face image;

[0039] In actual operation, the end face image can be preprocessed first. For example, the end face image captured by the CCD camera is first subjected to bilateral filtering to remove noise, and then a distortion correction algorithm is used to remove image distortion. The color image is then converted into a grayscale image. Finally, the grayscale image can be converted into a binary image using a global threshold processing method.

[0040] Therefore, further, a mature edge detection method can be used to process the binary image obtained after the above preprocessing (of course, in other embodiments, edge detection can also be performed on the original image or the image obtained by other preprocessing methods), combined with Figure 2 As shown, the image edge information such as the peripheral contour and hollow contour of the filter rod to be tested is obtained. Then, through the mutual position relationship between each type of image edge information and its shape and structural characteristics, the end face outer contour line L1 composed of pixel points and the inner contour line L2 of the unattached area of ​​the forming paper composed of pixel points are finally extracted. The above implementation process can refer to mature machine vision technology.

[0041] Step S3: obtaining the height of the non-attached area according to the outer contour line and the inner contour line;

[0042] In actual operation, the distance between the outer contour line L1 and the inner contour line L2 can be calculated to extract the maximum value of the distance between the two as the height H. This can be obtained by combining pixel information and conventional geometric algorithms. This is not the focus and will not be elaborated on.

[0043] Step S4, calculating the area of ​​the non-attached region according to the outer contour line, the inner contour line and the height;

[0044] In actual operation, the area S of the non-fitted area can be obtained by combining the pixel information of the outer contour line L1 and the pixel information of the inner contour line L2 with the aforementioned height value H. This can be obtained by combining pixel information and conventional geometric algorithms. This is not the focus and will not be elaborated on.

[0045] Step S5: obtaining at least two index parameters using the outer contour line, the inner contour line, and the area;

[0046] Step S6: The index parameters are integrated with a preset standard threshold to determine whether the forming paper adhesion of the filter rod to be tested is qualified.

[0047] Here, obtaining at least two index parameters by using the outer contour line, the inner contour line, and the area may include:

[0048] (1) Calculate the delamination coefficient of the non-bonded area based on the length information of the outer contour line and the inner contour line.

[0049] For example, we can calculate the ratio T (T = L2 / L1) of the length of the inner contour line L2 where the forming paper and the tow are not bonded to the total length of the outer contour line L1 of the filter rod end face being tested. This ratio can be used as a delamination coefficient, which can represent the degree of fit from a certain dimension. As can be understood, the closer the T value is to 1, the smaller the gap between the tow and the forming paper, and the better the fit. The closer the T value is to 0, the larger the gap, the more obvious the delamination, and the worse the fit. The good / bad conclusions here can be understood as preliminary judgments.

[0050] (2) According to the area of ​​the non-bonded area and the length of the inner contour line, the average height coefficient of the non-bonded area is calculated.

[0051] For example, the ratio of the area S of the unattached region of the shaping paper to the length of the inner contour line L2 of the unattached region of the shaping paper can be calculated as H. mean (H mean =S / L2), with H mean As the average height of the layers that can represent the degree of fit from a certain dimension, it can be understood that H mean The smaller the value (which can be compared with a certain set value), the less obvious the delamination is and the better the fit is; mean The larger the value, the more obvious the delamination and the relatively poorer the fit. Similarly, the good or bad conclusion here can be understood as a preliminary judgment.

[0052] Regarding the last-mentioned fusion of the indicator parameters, it can be understood that after obtaining the aforementioned at least two indicator parameters, the measurement can be unified through normalization, and the evaluation score can be obtained in combination with the preset weights, and then the preset score standard value can be compared to evaluate the fit; or, the preliminary evaluation results of each of the two can be directly comprehensively re-classified, such as good + good = excellent, good + poor = qualified, poor + poor = unqualified. Of course, if there are more indicator parameters, the levels can be divided more finely, which is not elaborated or limited in the present invention.

[0053] In summary, the main design concept of the present invention is to combine machine vision technology to detect the state of the forming paper of special-shaped filter rods. That is, through the filter rod end face image, a variety of contour-related information is extracted to accurately identify the gap portion where the filter rod forming paper is not bonded to the filter rod tow. Then, the geometric information of the filter rod outer contour and the inner contour generated by the unbonded area is used to obtain parameter indicators for evaluating the degree of fit from different dimensions. Finally, the results corresponding to the multi-dimensional indicators are integrated to determine the quality of the special-shaped filter rod product. The gap detection and indicator determination method proposed by the present invention provides more scientific and accurate data support for the detection of special-shaped filter rods, which is of guiding significance for the production of special-shaped filter rods and also provides a solid foundation for improving the level of cigarette manufacturing.

[0054] In the embodiment of the present invention, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a, b and c, where a, b, c can be single or multiple.

[0055] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred modes can be reasonably combined and matched into a variety of equivalent schemes by those skilled in the art without departing from or changing the design ideas and technical effects of the present invention; therefore, the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. A method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision, characterized in that: include: Acquire an end face image of the filter rod to be tested; Extracting the outer contour line of the filter rod to be tested and the inner contour line of the unattached area of ​​the forming paper based on the end face image; Obtaining the height of the non-attached area according to the outer contour line and the inner contour line; Calculating the area of ​​the non-fitted region according to the outer contour line, the inner contour line, and the height; Obtaining at least two index parameters using the outer contour line, the inner contour line, and the area, including: calculating a delamination coefficient of the non-bonded area based on the length information of the outer contour line and the inner contour line; and calculating an average height coefficient of the non-bonded area based on the area of ​​the non-bonded area and the length of the inner contour line; The delamination coefficient is the ratio of the length of the inner contour line to the length of the outer contour line, and the closer the delamination coefficient is to 1, the better the fit is; the closer the delamination coefficient is to 0, the worse the fit is; the average height coefficient is the ratio of the area to the length of the inner contour line, and the smaller the average height coefficient is, the better the fit is; the larger the average height coefficient is, the worse the fit is. The index parameters are integrated with the preset standard threshold to determine whether the forming paper fit of the filter rod to be tested is qualified.

2. The method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision according to claim 1, characterized in that: The integration of the index parameters and the preset standard threshold to determine whether the forming paper adhesion of the filter rod to be tested is qualified includes: The normalized results of the plurality of indicator parameters are weighted according to preset weights to obtain an evaluation score; Whether the forming paper's lamination degree is qualified is determined based on a comparison result between the evaluation score and a preset standard score.

3. The method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision according to claim 1, characterized in that: The integration of the index parameters and the preset standard threshold to determine whether the forming paper adhesion of the filter rod to be tested is qualified includes: Based on the indicator parameters, obtaining respective preliminary evaluation results; Based on the preliminary evaluation results, the degree of adhesion of the forming paper is determined according to the preset grades.

4. The method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision according to claim 1, characterized in that: The step of extracting the outer contour line of the filter rod to be tested and the inner contour line of the unattached area of ​​the forming paper based on the end face image comprises: Using an edge detection algorithm, obtaining a plurality of image edge information representing the peripheral contour and the hollow contour of the filter rod to be tested in the end face image; The outer contour line and the inner contour line composed of pixel points are extracted based on the mutual position relationship and shape structure characteristics between the edge information of each image.

5. The method for detecting the degree of conformity of special-shaped filter plug forming paper based on machine vision according to any one of claims 1 to 4, characterized in that: The detection method further comprises: Before extracting the contour, filtering and denoising the end face image and removing image distortion are performed; The processed image is converted into a grayscale image, and the grayscale image is converted into a binary image.

Images