CN113829673B

CN113829673B - Honeycomb paper core stretching control method and system based on Hough transform

Info

Publication number: CN113829673B
Application number: CN202111423879.7A
Authority: CN
Inventors: 邱金洲
Original assignee: Wuhan Hongbo Paper Packaging Co ltd
Current assignee: Wuhan Hongbo Paper Packaging Co ltd
Priority date: 2021-11-26
Filing date: 2021-11-26
Publication date: 2022-03-18
Anticipated expiration: 2041-11-26
Also published as: CN113829673A

Abstract

The invention relates to the technical field of image detection, in particular to a honeycomb paper core stretching control method and system based on Hough transform. The method comprises the steps of respectively obtaining a first rotating speed of a first pull-open roller and a second rotating speed of a second pull-open roller; obtaining the speed ratio of the second rotating speed and the first rotating speed; acquiring a stretched image of a stretched paper core between a first stretching roller and a second stretching roller, and carrying out Hough transformation on an edge image of the stretched image to obtain a Hough space image; identifying highlight points in the Hough space image, and accumulating the pixel values of the highlight points at each angle to obtain corresponding accumulated values; screening the accumulated values corresponding to all the angles to obtain three maximum accumulated values; obtaining the stretching degree according to the difference between the average included angle and the standard included angle based on the average included angle among the three screened accumulated values; and adjusting the preset adjustment amount according to the product of the speed ratio and the stretching degree to obtain an updated adjustment amount so as to adjust the rotating speed of the second pull-off roller and achieve the aim of controlling stretching.

Description

Honeycomb paper core stretching control method and system based on Hough transform

Technical Field

The invention relates to the technical field of image detection, in particular to a honeycomb paper core stretching control method and system based on Hough transform.

Background

In the production process of the honeycomb paperboard, the stretching process greatly influences the stressed quality of the paperboard. That is, the continuous paper core needs to be pulled open into honeycomb paper core, and then the upper and lower surfaces of the honeycomb paper core are covered with face paper. The honeycomb paperboard can meet the isotropic requirement and reach the quality standard by ensuring that each honeycomb is uniformly stretched into a regular hexagon. At present, the process is mostly completed by a honeycomb paper core drawing machine.

In practice, the inventors found that the above prior art has the following disadvantages:

because the speed of the pull-off roller in the stretching machine is difficult to accurately control, the paper core is often under-stretched or over-stretched, so that the quality of a finished product is low, the utilization rate of the paper core is low, and the paper core is easy to damage.

Disclosure of Invention

In order to solve the technical problems, the invention aims to provide a honeycomb paper core stretching control method and a honeycomb paper core stretching control system based on Hough transform, and the adopted technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a hough transform-based honeycomb paper core stretching control method, which is characterized by including the following steps: respectively acquiring a first rotating speed of a first pull-open roller and a second rotating speed of a second pull-open roller, wherein the first pull-open roller and the second pull-open roller are used for stretching a paper core of the honeycomb paper; obtaining a speed ratio according to a ratio between the second rotation speed and the first rotation speed; acquiring a stretched image of the paper core stretched between the first stretching roller and the second stretching roller, and performing Hough transform on an edge image of the stretched image to obtain a Hough space image; identifying highlight points in the Hough space image, and accumulating pixel values of the highlight points at each angle to obtain corresponding accumulated values; screening the accumulated values corresponding to all the angles to obtain three maximum accumulated values; acquiring corresponding included angles based on angles respectively corresponding to the three screened accumulated values, acquiring average included angles adjacent to the included angles, and acquiring stretching degree according to the difference between the average included angles and a standard included angle; and adjusting a preset adjustment amount according to the product of the speed ratio and the stretching degree to obtain an updated adjustment amount, and adjusting the rotating speed of the second pull-off roller according to the updated adjustment amount.

Preferably, the updated adjustment amount is: and the result of multiplying the product by the preset adjustment amount is the updated adjustment amount.

Preferably, before the screening of the accumulated values corresponding to all the angles, the method further includes: acquiring a variance between the accumulated value and the average accumulated value; the average accumulated value is the average value of accumulated values in a set range; and selecting the accumulated value with the largest variance in the set range as the accumulated value to be screened.

Preferably, the setting range is obtained by obtaining the range of all the accumulated values, and obtaining the range according to the product of the ratio of the difference between the current accumulated value and all the accumulated values and the range and the ideal angle.

Preferably, before the step of accumulating the pixel values of the highlight at each angle to obtain a corresponding accumulated value, the method further includes: and filtering the highlight points to obtain filtered highlight points, wherein the accumulated value is obtained according to the filtered highlight points.

Preferably, the step of filtering the highlight point includes: obtaining the noise degree of the highlight according to the product of the pixel difference ratio and the parallel number ratio of the highlight; the pixel difference ratio is a pixel difference ratio between the largest pixel of all highlight dots and the highlight dot, the largest parallel number of all highlight dots and the number ratio of highlight dots with the same angle as the highlight dot; and screening the noise degree by using a threshold value, and filtering the highlight points belonging to the noise.

In a second aspect, another embodiment of the present invention further provides a hough transform-based cellular paper core stretching control system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements any one of the steps of the method when executing the computer program.

The invention has the following beneficial effects:

according to the embodiment of the invention, the image processing is carried out on the stretching image of the paper core, the image interference is avoided by converting the airspace image into the Hough space, the stretching degree of the paper core is judged according to the characteristics of the Hough space, and the feedback adjustment is carried out according to the speed ratio of the current pull-off roller and the corresponding stretching degree, so that the stretching control purpose is achieved, the intelligent control of the stretcher and the quality of producing the honeycomb paperboard are improved, and the cost of the paper core is saved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a flowchart of a honeycomb paper core stretching control method based on hough transform according to an embodiment of the present invention;

FIG. 2 is a schematic view of a camera and light source installed in a honeycomb core stretcher;

FIG. 3 is a comparison of an image of a honeycomb core and its corresponding edge detection image;

FIG. 4 is a reference map before and after filtering;

fig. 5 is a schematic diagram of a hough space image corresponding to a space domain image before and after filtering;

FIG. 6 is a comparison of an under-stretched and an over-stretched condition;

fig. 7 is a schematic diagram of hough space images corresponding to the spatial domain images in the understretched and overstretched states in fig. 6;

FIG. 8 is a schematic angle comparison of three sets of lines in deformation at different degrees of stretching;

fig. 9 is a schematic view of a 5 x 5 sliding window.

Detailed Description

To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined object, the following detailed description of the method and system for controlling stretching of a honeycomb paper core based on hough transform in accordance with the present invention, with reference to the accompanying drawings and preferred embodiments, describes the features and effects thereof. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

The honeycomb paper core stretcher needs to stretch the compacted paper core strips into a honeycomb shape, dry and solidify the honeycomb paper core strips, perform a gluing process after the honeycomb paper core is shaped, and stick upper and lower surface paper to finally obtain the honeycomb paperboard. The embodiment of the invention aims to solve the technical problem that the speed ratio difference of the pull rollers in the stretcher influences the stretching quality of a paper core, and the technical problem that the rotating speed of the pull rollers with different speed ratios in the stretcher is difficult to accurately control.

The following specifically describes a specific scheme of a honeycomb paper core stretching control method and system based on hough transform in combination with the accompanying drawings.

Referring to fig. 1, a flowchart of a cellular paper core stretching control method based on hough transform according to an embodiment of the present invention is shown, where the control method includes the following steps:

step S001, respectively acquiring a first rotating speed of a first pull-open roller and a second rotating speed of a second pull-open roller, wherein the first pull-open roller and the second pull-open roller are used for stretching the honeycomb paper; and obtaining a speed ratio according to the ratio between the second rotating speed and the first rotating speed.

Referring to fig. 2, in order to realize the intelligent control of the honeycomb paper core drawing machine, a corresponding image acquisition device is required to be installed inside the drawing machine, and the image acquisition device includes a camera and a stable light source. The drawing roller close to the feeding hole is a first drawing roller, the drawing roller close to the discharging hole is a second drawing roller, the honeycomb paper core is drawn under the action of the first drawing roller and the second drawing roller, the drawing degree of the honeycomb paper core depends on the speed ratio between the first drawing roller and the second drawing roller, and the speed ratio between the first drawing roller and the second drawing roller is adjusted by controlling the rotating speed of the second drawing roller.

Step S002, obtaining a stretched image of the honeycomb paper stretched between the first pull-open roller and the second pull-open roller, and performing hough transform on an edge image of the stretched image to obtain a hough space image.

The stable light source and the corresponding camera are installed in the closed stretcher casing, so that interference caused by external light and the like can be avoided. And after the stretching image is acquired, carrying out edge detection on the stretching image to obtain an edge image. An image of the honeycomb core and its corresponding edge detection image are collected as shown in fig. 3.

Due to the three-dimensional nature of the honeycomb paper core, the resulting stretched image still has a light and shadow effect and cannot achieve the ideal image with only the edges of the honeycomb opening. In order to remove the edge influence caused by light and shadow and judge the tensile deformation of the paper core so as to judge the tensile degree, the embodiment of the invention carries out Hough transformation on the edge image, and then the image characteristics in Hough space represent different deformation information of the honeycomb.

The method for obtaining the Hough space image by carrying out Hough transformation on the edge image of the honeycomb paper core stretching image comprises the following steps: firstly, traversing pixel point by pixel point, and calculating the parameters corresponding to the possible straight lines in the range of 360 degrees of each edge point

From

Image space go to

Hough space, the linear equation for the conversion between parameters is:

wherein, in the step (A),

is the coordinate value of the edge point in the edge image,

at [0 °,360 ° ]]The range is traversed to obtain multiple groups of corresponding

. Then, the sum is performed in Hough space, and each is

The data may be incremented by 1 at the pixel at the corresponding location. Finally, after all the edge points are traversed, corresponding matrix information, namely Hough space image information, can be obtained according to the accumulation result, and the method is used for solving the problems that the traditional method is not suitable for the traditional method, and the cost is lowThe image is composed of a plurality of curves, each curve represents an edge point in an original airspace, local highlight points are generated by intersecting the curves, and the pixel values at the intersection points are the number of the local highlight points. One pixel point in the image space corresponds to a curve in the Hough space, and one pixel point in the Hough space corresponds to a straight line in the image space. The image after hough-converting the edge image in fig. 3 is shown as I-diagram in fig. 4.

And S003, identifying highlight points in the Hough space image, and accumulating the pixel values of the highlight points at each angle to obtain corresponding accumulated values.

The value of the bright point corresponding to each angle in the Hough space image

Accumulating to obtain the accumulated value corresponding to the angle

。

Wherein the content of the first and second substances,

indicating angle

The corresponding accumulated value is added to the corresponding value,

indicating an angle of

To (1) a

Pixel values of the individual highlight points.

Due to the collected honeycomb paper core stretching imageThe image is provided with perspective distortion to a certain degree, the identification precision of the Hough transform on the angle of a straight line is limited, and in practice, parallel straight lines are partially not parallel in the image but have small angle deviation. Therefore, in the embodiment of the invention, curves need to be integrated, and the variance between the accumulated value and the average accumulated value is obtained; the average accumulated value is the average value of accumulated values in a set range; and selecting the accumulated value with the largest variance in the set range as the accumulated value to be screened. The setting range is obtained by obtaining the range of all accumulated values and multiplying the ratio of the difference between the current accumulated value and all accumulated values and the range by an ideal angle. Accumulated value

Integrated value of

Comprises the following steps:

in the formula (I), the compound is shown in the specification,

indicates the accumulated value

The integrated value of (a) is determined,

is an accumulated value

ZD is the variance between the current angle value and the mean value in the range,

is the size of the error range and is,

in order to deviate the angle of the angle,

representing the maximum of all accumulated values in the image,

representing the minimum of all accumulated values in the image.

Positive and negative representation of (b) expands to the left and right, respectively

。

Is the magnitude of the error range, also called the set range, and is actually the accumulated value

The larger the corresponding judgment range, the larger the range, and the standard range is that the hexagonal honeycomb ideally consists of three groups of straight lines

。

The larger the variance, the more the accumulated value is

The more prominent the selection variance is

As the object of the screening in step S004. The integration mode can highlight the position of the extreme point and expand the influence of a high accumulated value.

Preferably, in order to eliminate noise interference in the hough space image, filtering is performed on highlight points in the hough space image to obtain filtered highlight points, and the accumulated value is obtained according to the filtered highlight points. The filtering step is to obtain the noise degree of the highlight according to the product of the pixel difference ratio and the parallel number ratio of the highlight; the pixel difference ratio is a pixel difference ratio between the largest pixel of all highlight dots and the highlight dot, the largest parallel number of all highlight dots and the number ratio of highlight dots with the same angle as the highlight dot; and screening the noise degree by using a threshold value, and filtering the highlight points belonging to the noise.

Specifically, the filtering step includes:

step one, obtaining local highlight points by using a filtering and filtering mode. Referring to fig. 9, a window with a size of 5 × 5 is set to perform a sliding window operation, if the average value of the peripheral 16 pixels is smaller than the average value of the inner 8 pixels, and the average value of the inner 8 pixels is smaller than the value of the pixel at the center, it can be determined that the center point of the window is a local highlight, otherwise, it is not a local highlight.

And step two, calculating the noise degree of the highlight. The noise edge direction is changeable and irregular and the length is shorter, namely the number of parallel line segments is small, the pixel quantity on each line segment is also small, so the noise edge direction is expressed on the Hough space image as follows: the point values are lower and the number of points in the vertical direction on the abscissa is smaller.

Noise level of highlight

The calculation formula is as follows:

in the formula (I), the compound is shown in the specification,

is shown as

The degree of noise of the individual highlight dots,

is shown as

The pixel values of the individual highlight points,

representing the maximum pixel value among all the highlights,

representing the minimum pixel value among all highlight points. In the same way, the method for preparing the composite material,

is shown with

The number of highlight points with the same abscissa of each highlight point,

indicating the maximum number of parallels in all highlight points,

representing the minimum number of parallels in all highlight points.

According to the degree of noise

The highlight is filtered. When the degree of noise

Greater than a set threshold

In time, the edge corresponding to the highlight point is a noise edge, and the point needs to be removed. And only retaining non-noise local highlight points in the Hough space image to obtain a filtered highlight point image. And accumulating the filtered bright points at each angle to obtain a corresponding accumulated value.

Referring to fig. 4, I is a spatial domain image obtained before filtering, and ii is a spatial domain image in an ideal state after filtering. Referring to fig. 5, a diagram iii in fig. 5 is a hough space image corresponding to a diagram I, and a diagram iv is a hough space image corresponding to a diagram ii, so that bright spots of the filtered image in the hough space are more prominent.

S004, screening the accumulated values corresponding to all the angles to obtain three maximum accumulated values; and acquiring corresponding included angles based on the angles respectively corresponding to the three screened accumulated values, acquiring average included angles adjacent to the included angles, and acquiring the stretching degree according to the difference between the average included angles and the standard included angles.

The standard and ideal honeycomb is a regular hexagon, with isotropic characteristics, i.e., six sides of the regular hexagon are equal in length and each side is equal in direction to the center. The embodiment of the invention judges the difference between the honeycomb and the ideal honeycomb in the image, namely the difference in all directions, through the accumulated value of the midpoint in the Hough space and the corresponding position.

As shown in fig. 6, it shows a deformation diagram of the paper core in different states under different stretching degrees of the honeycomb paper core. In the figure a, the hexagonal shape corresponding to the understretched state is observed to be compressed in the transverse direction, and in the figure b, the hexagonal shape corresponding to the overstretched state is observed to be elongated in the transverse direction. The hexagon in fig. ii is a hexagon in an ideal stretched state. Referring to fig. 7, a diagram v in fig. 7 is the hough space image of a diagram in fig. 6, and a diagram vi is the hough space image of b diagram in fig. 6, and it can be known from the diagrams v and vi that the angular interval in the hough space of the under-stretched image is relatively large, and the angular interval in the hough space of the over-stretched image is relatively small.

Because the paper core of the honeycomb paper is hexagonal, and the parallel relation of two parallel edges of the hexagon is unchanged in the stretching process, the image only contains three types of straight lines no matter how the stretching degree of the paper core is, the corresponding angles of the three types of straight lines meet a certain relation, and the number of the three types of straight lines is approximately equal. Therefore, the three highest extreme point positions in the integration curve are selected according to the corresponding angles

The degree of stretching is calculated.

As shown in fig. 8, the three groups of lines have different relationships in deformation with different stretching degrees, the three straight lines are respectively perpendicular to each other, and the three perpendicular lines are sequentially marked as A, B and C, d is a regular hexagon corresponding to an ideal stretching state, each internal angle in the regular hexagon is 120 degrees, and the included angle between the perpendicular lines A, B is

And the angle between vertical line B, C

60 each, the angle between the perpendicular C and the coordinate axis

Is 30 degrees. e-diagram is the angle between the perpendicular bisectors A, B of the corresponding hexagon in the under-stretched state

Is 80 degrees from the perpendicular B, C

Is 80 degrees, and the included angle between the vertical line C and the coordinate axis

Is 10 degrees. f is the angle between the perpendicular bisectors A, B of the corresponding hexagon in the over-stretched state

Is 40 degrees from the perpendicular B, C

Is 40 degrees, and the included angle between the vertical line C and the coordinate axis

Is 50 degrees. As can be seen from fig. 4, the included angle between the three types of straight lines is greater than 60 degrees, and the larger the included angle is, the less stretching is performed; the included angle is less than 60 degrees and the smaller the included angle, the more stretching is crossed. The obtained integration curve reflects the number degree of the straight lines of each angle type. Therefore, according to the numerical value from large to small, the angles corresponding to the three extreme points are obtained first, and then the values of the angles are sequentially from small to large

. Then calculating the stretching degree

：

When in use

When the value of (A) is more than 0, the current paper core is in an understretched state, and when the value of (A) is more than 0, the paper core is in an understretched state

When the value is less than 0, the film is,indicating that the current core is in an over-stretched condition.

When 0 is equal to 0, the ideal state is reached.

And S005, adjusting a preset adjustment amount according to the product of the speed ratio and the stretching degree to obtain an updated adjustment amount, and adjusting the rotating speed of the second pull-off roller according to the updated adjustment amount.

The rotation speed difference between the pulling rollers influences the stretching tension of the honeycomb paper core, and the larger the rotation speed difference of the two groups of roller shafts is, the larger the tension is, and the larger the stretching degree of the paper core is.

First speed of rotation for pulling the first pull-off roller

Second rotation speed of second pull-off roller

Velocity ratio is noted

Then, there are:

to ensure production speed, the first rotational speed may be fixed

Controlling the feed rate by the first rotational speed, and controlling the second rotational speed by adjusting the second rotational speed

To change the force applied to the paper core and thus the stretching effect.

When in use

When the paper core is under-stretched, the speed ratio is smaller; then r2 needsTo adjust up, the updated adjustment amount is therefore: the product of the speed ratio and the stretching degree is multiplied by the preset adjustment amount, and the result is the updated adjustment amount and the corresponding adjustment amount

Comprises the following steps:

wherein

The adjustment is carried out according to the actual production process for the corresponding preset adjustment amount.

When in use

When the paper core is over-stretched, the speed ratio is larger when the paper core is negative; then r2 needs to be adjusted smaller, and the corresponding adjustment amount is the same as:

。

in summary, the embodiment of the invention performs image processing on the stretching image of the paper core, avoids imaging interference by converting the airspace image into the hough space, judges the stretching degree of the paper core according to the characteristics of the hough space, and performs feedback adjustment according to the speed ratio of the current pull-off roller and the corresponding stretching degree to achieve the purpose of controlling stretching, so as to improve the intelligent control of the stretching machine and the quality of producing the honeycomb paperboard and save the cost of the paper core.

Based on the same inventive concept as the method, the embodiment of the invention further provides a cellular paper core stretching control system based on hough transform, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize the steps of the method according to any one of claims 1 to 6.

It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. A honeycomb paper core stretching control method based on Hough transform is characterized by comprising the following steps:

respectively acquiring a first rotating speed of a first pull-open roller and a second rotating speed of a second pull-open roller, wherein the first pull-open roller and the second pull-open roller are used for stretching a paper core of the honeycomb paper; obtaining a speed ratio according to the ratio of the second rotating speed to the first rotating speed;

acquiring a stretched image of the paper core stretched between the first stretching roller and the second stretching roller, and performing Hough transform on an edge image of the stretched image to obtain a Hough space image;

identifying highlight points in the Hough space image, and accumulating pixel values of the highlight points at each angle to obtain corresponding accumulated values;

screening the accumulated values corresponding to all the angles to obtain three maximum accumulated values; acquiring corresponding included angles based on angles respectively corresponding to the three screened accumulated values, acquiring average included angles adjacent to the included angles, and acquiring stretching degree according to the difference between the average included angles and a standard included angle;

and adjusting a preset adjustment amount according to the product of the speed ratio and the stretching degree to obtain an updated adjustment amount, and adjusting the rotating speed of the second pull-off roller according to the updated adjustment amount.

2. The Hough transform-based honeycomb paper core stretching control method according to claim 1, wherein the updated adjustment amount is: and the result of multiplying the product by the preset adjustment amount is the updated adjustment amount.

3. The honeycomb paper core stretching control method based on Hough transform as claimed in claim 1, wherein before the step of screening the accumulated values corresponding to all angles, the method further comprises:

acquiring a variance between the accumulated value and the average accumulated value; the average accumulated value is the average value of accumulated values in a set range;

and selecting the accumulated value with the largest variance in the set range as the accumulated value to be screened.

4. The Hough transform-based honeycomb paper core stretching control method according to claim 3, wherein the setting range is obtained by obtaining the range of all accumulated values, obtaining the difference between the current accumulated value and the minimum value of all accumulated values, calculating the ratio between the difference and the range, and obtaining the setting range according to the product of the ratio and an ideal angle, wherein the calculation formula of the setting range is as follows:

wherein the content of the first and second substances,

in order to set the range of the optical fiber,

in order to add the value to the memory,

representing the maximum of all accumulated values in the image,

representing the minimum of all accumulated values in the image.

5. The method for controlling stretching of a honeycomb paper core based on hough transform as claimed in claim 1, wherein before the step of accumulating the pixel values of the highlight at each angle to obtain a corresponding accumulated value, the method further comprises:

and filtering the highlight points to obtain filtered highlight points, wherein the accumulated value is obtained according to the filtered highlight points.

6. The Hough transform-based honeycomb paper core stretching control method according to claim 5, wherein the step of filtering the highlight comprises:

obtaining the noise degree of the highlight according to the product of the pixel difference ratio and the parallel number ratio of the highlight; the pixel difference ratio is a ratio of pixel difference to pixel range difference of highlight points, wherein the pixel difference is a pixel difference between the largest pixel of all highlight points and the current highlight point, the parallel number ratio is a ratio of the difference of the largest parallel number to the range difference of the number of highlight points, and the difference of the largest parallel number is the difference of the largest parallel number of all highlight points and the number of highlight points with the same angle; the calculation formula of the noise level is:

wherein, in the step (A),

is shown as

The degree of noise of the individual highlight dots,

is shown as

The pixel values of the individual highlight points,

representing the maximum pixel value among all the highlights,

is shown with

The number of highlight points with the same abscissa of each highlight point,

indicating the maximum number of parallels in all highlight points,

represents the minimum number of parallels in all highlight points;

and screening the noise degree by using a threshold value, and filtering the highlight points belonging to the noise.

7. A hough transform-based cellular paper core stretch control system comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor when executing the computer program implements the steps of the method of any one of claims 1-6.