CN115256900B - Plastic protection film production parameter control method based on image processing - Google Patents

Plastic protection film production parameter control method based on image processing Download PDF

Info

Publication number
CN115256900B
CN115256900B CN202210852366.6A CN202210852366A CN115256900B CN 115256900 B CN115256900 B CN 115256900B CN 202210852366 A CN202210852366 A CN 202210852366A CN 115256900 B CN115256900 B CN 115256900B
Authority
CN
China
Prior art keywords
degree
image
acquiring
area
defect
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210852366.6A
Other languages
Chinese (zh)
Other versions
CN115256900A (en
Inventor
周健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Feifan New Materials Technology Co ltd
Original Assignee
Deqing Feifan Plastic Adhesive Products Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Deqing Feifan Plastic Adhesive Products Co ltd filed Critical Deqing Feifan Plastic Adhesive Products Co ltd
Priority to CN202210852366.6A priority Critical patent/CN115256900B/en
Publication of CN115256900A publication Critical patent/CN115256900A/en
Application granted granted Critical
Publication of CN115256900B publication Critical patent/CN115256900B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C55/00—Shaping by stretching, e.g. drawing through a die; Apparatus therefor
    • B29C55/28—Shaping by stretching, e.g. drawing through a die; Apparatus therefor of blown tubular films, e.g. by inflation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C48/00—Extrusion moulding, i.e. expressing the moulding material through a die or nozzle which imparts the desired form; Apparatus therefor
    • B29C48/25—Component parts, details or accessories; Auxiliary operations
    • B29C48/92—Measuring, controlling or regulating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C2948/00—Indexing scheme relating to extrusion moulding
    • B29C2948/92—Measuring, controlling or regulating
    • B29C2948/92504—Controlled parameter
    • B29C2948/92704—Temperature

Abstract

The invention relates to the technical field of intelligent temperature control, in particular to a plastic protection film production parameter control method based on image processing, which comprises the following steps: acquiring a first gradient image and a first edge point of a reference image, and a second gradient image and a second edge point of a surface image; acquiring the blurring degree of each second edge point; screening standard edge points overlapped with the first edge points from the second gradient image to form a first group, and forming the rest second edge points into a second group; acquiring the degree of abnormality of the second gradient image; acquiring normal average ambiguity of all standard edge points; acquiring a defect type index of the surface image; the extruder temperature was adjusted according to the defect type index, degree of anomaly, and normal average ambiguity. The invention can realize the automatic control of the temperature in the production process of the plastic protective film and improve the production quality.

Description

Plastic protection film production parameter control method based on image processing
Technical Field
The invention relates to the technical field of intelligent temperature control, in particular to a plastic protection film production parameter control method based on image processing.
Background
The technical process for industrially producing plastic protective films generally comprises: film blowing, coating, printing, detection, rewinding, slitting, packaging and the like. The performance of the blown protective film has a great relation with the production process parameters, so that the control of the process parameters during the film blowing process is required to be enhanced, the process operation is standardized, the smooth production is ensured, and a high-quality protective film product is obtained.
Wherein temperature is one of the important parameters affecting whether plasticization is complete and uniform and whether foam shape is stable. If the temperature of the plastic extruder is low, the viscosity of the plastic is high, the transparency of the film is poor, unplasticized crystal points are easy to appear, the film is easy to break, and the elongation at break of the film is reduced. If the temperature of the plastic extruder is higher, the viscosity of the plastic is reduced, the opening property of the film is poor, but the transparency is improved, and the material is overheated and decomposed, so that a 'scorching' focus appears, the quality of the product is affected by unstable temperature, and even defective products are caused.
In the production process, the temperature setting of the plastic extruder is adjusted according to the production condition, and the temperature is not accurate, so that an experienced operator is required to control the temperature of the plastic protective film for production, but different raw materials and different product specifications are required to select different production temperatures, and the temperature value of the extruder is complicated and easy to error due to manual setting.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a plastic protection film production parameter control method based on image processing, which adopts the following technical scheme:
an embodiment of the present invention provides a method for controlling parameters of plastic protective film production based on image processing, which is provided with a fluorescent screen, so that after the plastic protective film is stretched, the fluorescent screen is positioned below a stretching area of the plastic protective film, and the surface of the fluorescent screen is parallel to a stretching surface of the plastic protective film, the method comprising the following steps:
collecting a overlook image of a fluorescent screen when the plastic protective film is not stretched as a reference image, and taking the overlook image of the plastic protective film after the plastic protective film is stretched as a surface image;
respectively carrying out gradient detection on the reference image and the surface image to obtain a first gradient image and a first edge point of the reference image, and a second gradient image and a second edge point of the surface image; acquiring the blurring degree of each second edge point according to the second edge point and the gray value of the neighborhood pixel point of the second edge point;
acquiring the blurring uniformity degree of the second gradient image based on all blurring degrees, and when the blurring uniformity degree is not zero, comparing the reference image with the surface image, screening out standard edge points overlapped with the first edge points in the second gradient image to form a first group, and forming a second group by the rest second edge points;
dividing all points in the second group into a plurality of categories based on the coordinates of the second edge points in the second group, forming a defect area by each category, and obtaining the abnormality degree of the second gradient image according to the distance between every two defect areas and the area of the defect area;
acquiring normal average ambiguity of all standard edge points; acquiring a defect type index of the surface image based on vectors, blurring degree, gradient directions and normal average blurring degree formed by each point in each category and the category center; the extruder temperature was adjusted according to the defect type index, degree of anomaly, and normal average ambiguity.
Preferably, the collecting the surface image of the plastic protective film in the stretching area further includes:
and determining the sampling frequency of the camera according to the moving speed of the plastic protective film in the cooling process, and acquiring the surface image at the sampling frequency.
Preferably, the method for obtaining the blurring degree comprises the following steps:
setting a sliding window with a preset size by taking each second edge point as a center, and calculating the gray level difference value between the sliding window center point and each neighborhood pixel point; acquiring a relative gray difference value of each second edge point and a corresponding position point in a reference image, and acquiring the blurring degree of each second edge point according to the gray difference value and the relative gray difference value; the relative gray difference value and the blurring degree are in positive correlation.
Preferably, the method for obtaining the blur uniformity degree comprises the following steps: the degree of dispersion of the degree of blurring is obtained as the degree of blurring uniformity.
Preferably, the process of obtaining the defect area includes:
dividing the coordinates of the second edge points in the second group into a plurality of categories through clustering, wherein all the second edge points in each category form a defect area; taking the average value of the abscissa of all edge points in the defect area and the average value of the ordinate as the center point coordinate of the defect area; the defect area is defined as a minimum bounding box, and the area of the minimum bounding box is defined as the area of the defect area.
Preferably, the method for obtaining the abnormality degree comprises the following steps:
and taking each defect area as a target area, calculating the distance between the target area and each other defect area, taking each distance as a negative index of a preset value to obtain an index function result, summing all index function results corresponding to the target area, multiplying the sum by the area of the target area to obtain the area abnormality degree, and taking the average value of the area abnormality degrees of all the defect areas as the abnormality degree.
Preferably, the method for acquiring the normal average ambiguity comprises the following steps:
and taking the change amount of the gradient direction of each standard edge point in the first gradient image and the second gradient image as the weight of the corresponding standard edge point, and acquiring the normal average ambiguity of the standard edge point by combining the corresponding ambiguity.
Preferably, the obtaining process of the defect type index includes:
for each category, acquiring a vector formed from a central point to each second edge point as a first vector corresponding to the second edge point, acquiring a corresponding sine value and a corresponding cosine value based on the gradient direction of the second edge point, forming a second vector, and calculating an included angle cosine value between the first vector and the second vector;
and obtaining the square of the difference value between the blurring degree of each second edge point and the normal average blurring degree as the blurring difference, calculating the product of the blurring difference and the cosine value of the included angle, obtaining the average value of all products in each category as the defect degree of the corresponding category, and taking the sum of all defect degrees in the surface image as the defect type index.
Preferably, the adjusting process of the temperature of the extruder comprises:
obtaining the ratio of the defect type index to the absolute value of the defect type index, taking the ratio as the negative index of the normal average ambiguity, and multiplying the obtained result by the abnormality degree to obtain the temperature adjustment degree;
and adjusting the current temperature based on the temperature adjustment degree to obtain the adjusted temperature.
The embodiment of the invention has at least the following beneficial effects:
1. the defects generated by the abnormal temperature of the extruder are evaluated by calculating the blurring degree of the edge points in the gradient image, the temperature adjustment direction is determined according to the defect type, and the temperature adjustment amplitude is determined according to the abnormal degree, so that the automatic control of the temperature in the production process of the plastic protective film is realized, and the manual intervention is reduced.
2. The fluorescent screen is arranged below the expansion area in the cooling process of the plastic protective film, and the defect area on the surface of the protective film is extracted according to the characteristic that the protective film has the same blurring degree to the edge points of the pattern in the fluorescent screen, so that the interference of complex processing environment caused by certain transparency of the plastic protective film is avoided, and the detection accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an image acquisition position according to an embodiment of the present invention;
fig. 2 is a flowchart of steps of a method for controlling parameters of plastic protective film production based on image processing according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the plastic protection film production parameter control method based on image processing according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 application scene of the invention is as follows: in the plastic protective film blowing process, the plastic protective film is evenly plasticized by intelligently adjusting the temperature of the plastic extruder.
As shown in fig. 1, the plastic protective film is blown out from the plastic protective film outlet 101, the screen 102 is arranged such that after the plastic protective film is stretched, the screen 102 is under the plastic protective film stretching region 103, and the screen surface is parallel to the plastic protective film stretching surface, the camera 104 is fixed directly above the plastic protective film stretching surface, the dotted line portion is the camera view angle, and the screen surface displays a pattern.
The following specifically describes a specific scheme of the plastic protective film production parameter control method based on image processing.
Referring to fig. 2, a flowchart of a method for controlling parameters of plastic protective film production based on image processing according to an embodiment of the invention is shown, the method comprises the following steps:
and S001, collecting a top view image of the fluorescent screen when the plastic protective film is not stretched as a reference image, and taking the top view image of the plastic protective film after the plastic protective film is stretched as a surface image.
The method comprises the following specific steps of:
1. and determining the sampling frequency of the camera according to the moving speed of the plastic protective film in the cooling process, and acquiring the surface image at the sampling frequency.
And determining the sampling rate of the camera based on the moving speed of the plastic protective film, so that the camera can continuously acquire the surface images of the plastic protective film under the moving speed of the plastic protective film.
2. And (5) image acquisition.
And collecting a top view image of the fluorescent screen when the plastic protective film is not stretched as a reference image, and taking the top view image of the plastic protective film after the plastic protective film is stretched as a surface image.
The screen displays a pattern, which in the embodiments of the invention is displayed as a black and white textured image, in other embodiments may be other patterns, or may be a color pattern, and the captured image may be grayed.
Because the plastic protective film has certain transparency, the plastic protective film is directly subjected to image processing and is easy to be interfered by surrounding complex processing environments, and when the defect exists on the surface of the protective film in consideration of the single-color background, the defect contrast is possibly lower, so that the fluorescent screen is arranged below the protective film, and black-and-white texture patterns are displayed on the fluorescent screen, so that the interference of the processing environments is avoided.
Step S002, respectively carrying out gradient detection on the reference image and the surface image to obtain a first gradient image and a first edge point of the reference image, and a second gradient image and a second edge point of the surface image; and acquiring the blurring degree of each second edge point according to the second edge point and the gray value of the neighborhood pixel point of the second edge point.
The method comprises the following specific steps of:
1. and (5) gradient detection.
And respectively carrying out gradient detection on the reference image and the surface image by utilizing a Sobel operator to obtain gradient amplitude values of each pixel point in each image, and forming a first gradient image of the reference image and a second gradient image of the surface image.
And extracting edge points in the first gradient image as first edge points, and extracting edge points in the second gradient image as second edge points.
Ideally, the first edge point and the second edge point are completely overlapped, but the transparency of the protective film varies according to the temperature variation, and when the transparency is insufficient or the surface of the protective film is defective, the first edge point and the second edge point are different.
2. And obtaining the blurring degree of each second pixel point.
Setting a sliding window with a preset size by taking each second edge point as a center, and calculating the gray level difference value between the sliding window center point and each neighborhood pixel point; acquiring a relative gray difference value of each second edge point and a corresponding position point in the reference image, and acquiring the blurring degree of each second edge point according to the gray difference value and the relative gray difference value; the relative gray difference value and the blurring degree are in positive correlation.
The nature of the image blurring is due to the reduction of the difference between the gray levels of adjacent pixels, whereas blurring occurs at the edges of the underlying screen that appear in the camera image through the plastic film due to the scattering of light by the plastic film.
Traversing by using each second edge point as a center and using a 3 multiplied by 3 sliding window, and taking the ith second edge point as an example, obtaining the gray level difference degree of the ith second edge point and the neighborhood pixel point:
wherein sigma i 2 Represents the gray level difference degree of the ith second edge point, H i Representing the gray value of the ith second edge point, H ij Representing the gray value of the jth neighborhood pixel point of the ith second edge point, H ij -H i The gray difference value between the ith second edge point and the jth neighborhood pixel point is obtained.
The larger the gray scale difference between the pixel points in the sliding window area, the clearer the edge point is indicated, and the smaller the gray scale difference is, the more blurred the edge point is indicated.
Acquiring gray level difference delta H of ith second edge point at corresponding positions of reference image and surface image i Namely the relative gray difference value, the color of the edge points of the pattern is uniform because the color of the protective film is uniform, so that the influence degree of the protective film on the gray value of the pattern is the same, and when the transparency of the protective film is very low, namely the display screen pattern cannot basically penetrate the protective film, the relative gray difference value delta H of the edge points can be caused i And the blurring degree of the image by the protective film is larger.
Obtaining gray level difference degree sigma of ith second edge point at corresponding position of reference image i 2′ And calculates the difference delta sigma i 2 ＝σ i 2′ -σ i 2 If the relative gray difference delta H of the ith second edge point i Smaller sizeIndicating that the protective film has high transparency and needs to be combined with the difference delta sigma i 2 To determine whether the transmitted portion is clear.
Calculating the blurring degree C of the ith second pixel point i ：
Wherein arctan represents an arctangent function and pi represents 180 degrees.
The relative gray difference delta H at the ith second edge point i Smaller, i.e. higher transparency, difference delta sigma i 2 The larger the difference of the gradation around the ith second edge point is, the larger the difference in the reference image and the surface image is, and the higher the transparency of the protective film is, the less clear the transmitted image is, and the defect may occur in the protective film itself.
The transparency of the protective film can be changed due to abnormal temperature of the plastic protective film, the blurring degree of the pattern in the corresponding lower fluorescent screen in the current image can also be changed correspondingly, when the extrusion temperature is lower, the transparency of the protective film is poorer, and the blurring degree of the pattern on the lower fluorescent screen is greater; when the extrusion temperature is higher, the transparency of the protective film is higher and the blurring degree of the pattern on the underlying phosphor screen is smaller.
Step S003, obtaining the blurring uniformity degree of the second gradient image based on all blurring degrees, when the blurring uniformity degree is not zero, screening out standard edge points overlapped with the first edge points in the second gradient image by comparing the reference image with the surface image to form a first group, and forming the second group by the rest second edge points.
The method comprises the following specific steps of:
1. the degree of dispersion of the degree of blurring is obtained as the degree of blurring uniformity.
There are many methods for expressing the degree of dispersion, and in the embodiment of the present invention, the variance is used as the degree of dispersion, that is, the variance of all the degrees of blurring is calculated as the degree of blurring uniformity of the second gradient image.
Under normal conditions, namely when plasticization is uniform, the blurring degree of the protective film on each pixel point in the reference image is the same, and when plasticization is non-uniform, the blurring degree of different pixel points is different.
2. And when the blurring uniformity degree is not zero, screening and grouping the second edge points.
When the blurring uniformity degree is equal to zero, the blurring uniformity in the image is indicated, and no defect exists; otherwise, the blurring degree of the current image is not uniform, and the defect type of the area with the non-uniform blurring needs to be further judged.
Since the positions and the number of the edge points of the screen pattern are fixed, the plastic protective film normally only has a blurring effect on the original image, so that when additional edge points are generated in the image, it is indicated that other edge points are generated at this time, and the protective film may have defects.
Overlapping and comparing the reference image and the surface image, screening out second edge points which are overlapped with the first edge points of the reference image from the second gradient image to serve as standard edge points, forming a first group, and fixing the number as M; the remaining second edge points are redundant edge points, most likely defect points, constituting a second group.
And S004, dividing all points in the second group into a plurality of categories based on the coordinates of the second edge points in the second group, forming a defect area by each category, and obtaining the abnormality degree of the second gradient image according to the distance between every two defect areas and the area of the defect area.
The method comprises the following specific steps of:
1. and acquiring a defect area.
Dividing the coordinates of the second edge points in the second group into a plurality of categories through clustering, wherein all the second edge points in each category form a defect area; taking the average value of the abscissa of all edge points in the defect area and the average value of the ordinate as the center point coordinate of the defect area; the defect area is defined as a minimum bounding box, and the area of the minimum bounding box is defined as the area of the defect area.
Clustering the coordinates of the second edge points in the second group by using a DBSCAN clustering algorithm to obtain N clustering results, wherein each clustering result corresponds to a defect area, and the average value of the horizontal coordinates and the average value of the vertical coordinates of all the edge points in the defect area are used as the center point coordinates of the defect area; the defect area is defined as a minimum bounding box, and the area of the minimum bounding box is defined as the area of the defect area.
2. The degree of abnormality of the second gradient image is acquired.
And taking each defect area as a target area, calculating the distance between the target area and each other defect area, taking each distance as a negative index of a preset value to obtain an index function result, summing all index function results corresponding to the target area, multiplying the sum by the area of the target area to obtain the area abnormality degree, and taking the average value of the area abnormality degrees of all the defect areas as the abnormality degree.
As an example, taking the mth defective area as the target area, a specific calculation formula of the area abnormality degree y is:
wherein S is m Represents the mth defective area, d mn Representing the distance between the mth defective area and the nth defective area.
Distance d mn Is the euclidean distance between the m-th defect region center point and the n-th defect region center point.
Degree of abnormality of the second gradient imageSince the abnormality in the image is caused by the temperature, or the abnormality is caused by the too high temperature or the abnormality is caused by the too low temperature, the whole image has only one abnormality problem, and the calculated abnormality degree is the whole second gradient image.
Step S005, obtaining normal average ambiguity of all standard edge points; acquiring a defect type index of the surface image based on vectors, the degree of blurring, the gradient direction and the normal average degree of blurring formed by each point in each category and the center of the category; the extruder temperature was adjusted according to the defect type index, degree of anomaly, and normal average ambiguity.
The method comprises the following specific steps of:
1. and obtaining the normal average ambiguity of the standard edge points.
And taking the change amount of the gradient direction of each standard edge point in the first gradient image and the second gradient image as the weight of the corresponding standard edge point, and acquiring the normal average ambiguity of the standard edge point by combining the corresponding ambiguity.
For the area with uneven blurring, the standard edge point can represent the blurring degree of the normal area, but the position of the defect is random, and there may be a position where part of edge points belonging to the pattern intersect with the edge points of the defect area, the protective film can blur the edge points, but the blurring effect of the protective film on the pattern does not change the direction of the original edge point of the pattern greatly, so the change delta theta of the gradient direction of the standard edge point in the first gradient image and the second gradient image is used r As a weight, a normal average ambiguity characterizing a normal region is obtained in combination with the corresponding ambiguity
Wherein C is r Represents the degree of blurring of the r-th standard edge point, and M represents the number of standard edge points.
When the gradient direction changes by delta theta r The larger the probability that the r standard edge point is the edge point generated by the influence of the defect area is, the lower the reference weight of the blurring degree of the edge point is; when the gradient direction changes by delta theta r The smaller the probability that the r-th standard edge point is the edge point of the normal region is, the higher the reference weight for the degree of blurring of the edge point is, therebyAnd obtaining the normal average ambiguity.
2. And obtaining a defect type index.
For each category, acquiring a vector formed from a central point to each second edge point as a first vector corresponding to the second edge point, acquiring a corresponding sine value and a corresponding cosine value based on the gradient direction of the second edge point, forming a second vector, and calculating an included angle cosine value between the first vector and the second vector; and obtaining the square of the difference value between the blurring degree of each second edge point and the normal average blurring degree as a blurring difference, calculating the product of the blurring difference and the cosine value of the included angle, obtaining the average value of all products in each category as the defect degree of the corresponding category, and taking the sum of all defect degrees in the surface image as a defect type index.
The low temperature of the extruder can cause crystallization points on the surface of the protective film, and the too high temperature can cause focus on the surface of the protective film. The crystal points are plastic particles with poor plasticization, and the gray value of the crystal points is larger than that of the pixel points in the normal area; and the focus is blackened so that the gray value formed by the focus is lower than that of the normal region, so that the specific type of defect can be judged according to the gray value of the defective region.
The blurring degree of the g second edge point in the k-th category is marked as C kg The first vector formed by the center point and the g second edge point isAcquiring a corresponding sine value sin theta based on gradient direction of the second edge point kg And cosine value cos theta kg Constitutes a second vector (cos theta kg ,sinθ kg ) Calculating cosine value of included angle between first vector and second vector
Since the gray value of the crystal point is larger than that of the plastic film, and the gradient direction points to the direction of the fastest gray growth, the vector formed by the center point of the crystal point area and the edge point and the gradient direction of the edge point have the same direction component, and the cosine value of the included angle between the center point of the crystal point area and the edge point is positive, namely cos theta is more than 0; the gray value of the center point of the focal area is lower than the gray value of the plastic film, so that the cosine value of the included angle is negative, and the cosine value of the included angle is mapped to positive and negative to be expressed:
the defect type index is calculated as:
wherein n is k Representing the number of second edge points in the kth category.
Judging the defect type based on the positive and negative of the defect type index: when P <0, the region belongs to the crystal point region; when P >0, this area is the focal area.
3. And (5) adjusting the temperature.
Obtaining the ratio of the defect type index to the absolute value of the defect type index, taking the ratio as the negative index of the normal average ambiguity, and multiplying the obtained result by the abnormal degree to obtain the temperature adjustment degree; and adjusting the current temperature based on the temperature adjustment degree to obtain the adjusted temperature.
The current temperature is T, the temperature is adjusted according to the defect type and the abnormality degree, and the adjusted temperature T ′ Can be expressed as:
wherein by means ofJudging the temperature adjustment direction, and when the defect area in the image is a crystal point area, P<0, wherein the temperature of the extruder is too low, and the temperature of the extruder needs to be regulated up; when the defective area is the focus area, P>0, at this time, the extruder temperature is too high, and it is necessary to makeThe temperature of the extruder was lowered.
The degree of temperature adjustment of the current temperature is shown, and when the defects are more densely present and the influence range is wider, the degree of abnormality is larger, the current temperature is more unsuitable, and the amplitude of temperature adjustment is larger. When the current temperature is lower, the average blurring degree is higher, which indicates that the thicker the protective film is, the worse the quality of the protective film is; similarly, when the current temperature is higher, the lower the average degree of blurring is, the worse the quality is.
In summary, in the embodiment of the invention, the top view image of the fluorescent screen when the plastic protective film is not stretched is collected as the reference image, and the top view image of the plastic protective film after the plastic protective film is stretched is taken as the surface image; respectively carrying out gradient detection on the reference image and the surface image to obtain a first gradient image and a first edge point of the reference image, and a second gradient image and a second edge point of the surface image; acquiring the blurring degree of each second edge point according to the second edge point and the gray value of the neighborhood pixel point of the second edge point; acquiring the blurring uniformity degree of the second gradient image based on all blurring degrees, and when the blurring uniformity degree is not zero, comparing the reference image with the surface image, screening out standard edge points overlapped with the first edge points in the second gradient image to form a first group, and forming a second group by the rest second edge points; dividing all points in the second group into a plurality of categories based on the coordinates of the second edge points in the second group, forming a defect area by each category, and obtaining the abnormality degree of the second gradient image according to the distance between every two defect areas and the area of the defect area; acquiring normal average ambiguity of all standard edge points; acquiring a defect type index of the surface image based on vectors, the degree of blurring, the gradient direction and the normal average degree of blurring formed by each point in each category and the center of the category; the extruder temperature was adjusted according to the defect type index, degree of anomaly, and normal average ambiguity. According to the embodiment of the invention, the temperature adjustment direction can be determined according to the defect type, and the temperature adjustment amplitude can be determined according to the defect degree, so that the automatic control of the temperature in the production process of the plastic protective film is realized, and the manual intervention is reduced.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. 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 are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.

Claims (3)

1. The method for controlling the production parameters of the plastic protective film based on image processing is characterized in that a fluorescent screen is arranged, so that after the plastic protective film is stretched, the fluorescent screen is positioned below a stretching area of the plastic protective film, and the surface of the fluorescent screen is parallel to a stretching surface of the plastic protective film, and the method comprises the following steps:
collecting a overlook image of a fluorescent screen when the plastic protective film is not stretched as a reference image, and taking the overlook image of the plastic protective film after the plastic protective film is stretched as a surface image;
respectively carrying out gradient detection on the reference image and the surface image to obtain a first gradient image and a first edge point of the reference image, and a second gradient image and a second edge point of the surface image; acquiring the blurring degree of each second edge point according to the second edge point and the gray value of the neighborhood pixel point of the second edge point;
acquiring the blurring uniformity degree of the second gradient image based on all blurring degrees, and when the blurring uniformity degree is not zero, comparing the reference image with the surface image, screening out standard edge points overlapped with the first edge points in the second gradient image to form a first group, and forming a second group by the rest second edge points;
dividing all points in the second group into a plurality of categories based on the coordinates of the second edge points in the second group, forming a defect area by each category, and obtaining the abnormality degree of the second gradient image according to the distance between every two defect areas and the area of the defect area;
acquiring normal average ambiguity of all standard edge points; acquiring a defect type index of the surface image based on vectors, blurring degree, gradient directions and normal average blurring degree formed by each point in each category and the category center; adjusting the temperature of the extruder according to the defect type index, the abnormality degree and the normal average ambiguity;
the method for acquiring the blurring degree comprises the following steps:
setting a sliding window with a preset size by taking each second edge point as a center, and calculating the gray level difference value between the sliding window center point and each neighborhood pixel point; acquiring a relative gray difference value of each second edge point and a corresponding position point in a reference image, and acquiring the blurring degree of each second edge point according to the gray difference value and the relative gray difference value; the relative gray difference value and the blurring degree form a positive correlation relation;
the method for acquiring the fuzzy uniformity degree comprises the following steps: acquiring the discrete degree of the fuzzy degree as the fuzzy uniformity degree;
the method for acquiring the abnormality degree comprises the following steps:
taking each defect area as a target area, calculating the distance between the target area and each other defect area, taking each distance as a negative index of a preset value to obtain an index function result, summing all index function results corresponding to the target area, multiplying the sum by the area of the target area to obtain the area abnormality degree, and taking the average value of the area abnormality degrees of all the defect areas as the abnormality degree;
the method for acquiring the normal average ambiguity comprises the following steps:
taking the change amount of each standard edge point in the gradient directions of the first gradient image and the second gradient image as the weight of the corresponding standard edge point, and acquiring the normal average ambiguity of the standard edge point by combining the corresponding ambiguity;
the defect type index obtaining process comprises the following steps:
for each category, acquiring a vector formed from a central point to each second edge point as a first vector corresponding to the second edge point, acquiring a corresponding sine value and a corresponding cosine value based on the gradient direction of the second edge point, forming a second vector, and calculating an included angle cosine value between the first vector and the second vector;
obtaining the square of the difference value between the fuzzy degree of each second edge point and the normal average fuzzy degree as the fuzzy difference, calculating the product of the fuzzy difference and the cosine value of the included angle, obtaining the average value of all products in each category as the defect degree of the corresponding category, and taking the sum of all defect degrees in the surface image as the defect type index;
the adjusting process of the temperature of the extruder comprises the following steps:
obtaining the ratio of the defect type index to the absolute value of the defect type index, taking the ratio as the negative index of the normal average ambiguity, and multiplying the obtained result by the abnormality degree to obtain the temperature adjustment degree;
and adjusting the current temperature based on the temperature adjustment degree to obtain the adjusted temperature.
2. The method for controlling production parameters of plastic protective films based on image processing according to claim 1, wherein the capturing the surface image of the plastic protective film in the stretching area further comprises:
and determining the sampling frequency of the camera according to the moving speed of the plastic protective film in the cooling process, and acquiring the surface image at the sampling frequency.
3. The image processing-based plastic protective film production parameter control method according to claim 1, wherein the acquisition process of the defective region comprises:
dividing the coordinates of the second edge points in the second group into a plurality of categories through clustering, wherein all the second edge points in each category form a defect area; taking the average value of the abscissa of all edge points in the defect area and the average value of the ordinate as the center point coordinate of the defect area; the defect area is defined as a minimum bounding box, and the area of the minimum bounding box is defined as the area of the defect area.
CN202210852366.6A 2022-07-20 2022-07-20 Plastic protection film production parameter control method based on image processing Active CN115256900B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210852366.6A CN115256900B (en) 2022-07-20 2022-07-20 Plastic protection film production parameter control method based on image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210852366.6A CN115256900B (en) 2022-07-20 2022-07-20 Plastic protection film production parameter control method based on image processing

Publications (2)

Publication Number Publication Date
CN115256900A CN115256900A (en) 2022-11-01
CN115256900B true CN115256900B (en) 2023-07-21

Family

ID=83767123

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210852366.6A Active CN115256900B (en) 2022-07-20 2022-07-20 Plastic protection film production parameter control method based on image processing

Country Status (1)

Country Link
CN (1) CN115256900B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116118154B (en) * 2023-04-14 2023-08-22 威海华福轿车内饰有限公司 Extrusion processing control method and system for automotive interior raw materials

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114605687A (en) * 2022-05-13 2022-06-10 河南银金达新材料股份有限公司 Preparation method of anti-aging polyester film material

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2394283A (en) * 2002-10-18 2004-04-21 Beta Lasermike Ltd Optical imaging, and monitoring of exposed cut ends of a product
WO2010005853A1 (en) * 2008-07-10 2010-01-14 Gentex Corporation Rearview mirror assemblies with anisotropic polymer laminates
US9176074B2 (en) * 2013-01-28 2015-11-03 Kabushiki Kaisha Toshiba Pattern inspection method and pattern inspection apparatus
US11953448B2 (en) * 2019-09-27 2024-04-09 Taiwan Semiconductor Manufacturing Company Ltd. Method for defect inspection
CN114670421A (en) * 2022-05-31 2022-06-28 南通净缘塑料制品有限公司 Machine vision-based modified plastic extrusion production control method

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114605687A (en) * 2022-05-13 2022-06-10 河南银金达新材料股份有限公司 Preparation method of anti-aging polyester film material

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机器视觉的多疵点薄膜区分算法研究;张培培;;工业控制计算机(11);第104-106页 *

Also Published As

Publication number Publication date
CN115256900A (en) 2022-11-01

Similar Documents

Publication Publication Date Title
CN111563889B (en) Liquid crystal screen Mura defect detection method based on computer vision
CN115256900B (en) Plastic protection film production parameter control method based on image processing
CN108257185A (en) More checkerboard angle point detection process and camera marking method
CN106851092B (en) A kind of infrared video joining method and device
CN113971670B (en) Thread defect analysis method and system based on computer vision
CN109191429B (en) 3D printing nozzle detection method based on machine vision
CN115294116B (en) Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence
CN112862832B (en) Dirt detection method based on concentric circle segmentation positioning
CN116188468B (en) HDMI cable transmission letter sorting intelligent control system
CN116990993B (en) LCD display panel quality detection method
CN113592911A (en) Apparent enhanced depth target tracking method
CN116012579A (en) Method for detecting abnormal states of parts based on photographed images of intelligent inspection robot of train
KR101905000B1 (en) Method, apparatus and computer program stored in computer readable medium for correction of image data
CN114612441A (en) Plastic bottle defect detection method and system based on artificial intelligence and image processing
CN117495852A (en) Digital printing quality detection method based on image analysis
CN116485788B (en) Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method
CN114998346B (en) Waterproof cloth quality data processing and identifying method
CN114693652B (en) Fabric Defect Detection Method Based on Gaussian Mixture Model
CN115797299A (en) Defect detection method of optical composite film
CN113421248B (en) Substation equipment rotating image numerical value processing method
CN117036354B (en) Intelligent finger ring display screen detection method
CN110993491B (en) Automatic correction method for OED (optical element design) in excimer laser annealing process
CN117061710B (en) System and method for remotely checking conditions in vehicle
CN111182289B (en) Lens cone notch searching method
CN117354630A (en) Multi-camera illumination compensation method for tunnel

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: No. 1588 Gandong Road, Zhongguan Town, Deqing County, Huzhou City, Zhejiang Province, 313000 (self declared)

Patentee after: Zhejiang Feifan New Materials Technology Co.,Ltd.

Address before: No. 1588, Gandong Road, Zhongguan Town, Deqing County, Huzhou City, Zhejiang Province

Patentee before: Deqing Feifan plastic adhesive products Co.,Ltd.

CP03 Change of name, title or address