CN115170572A - BOPP composite film surface gluing quality monitoring method - Google Patents
BOPP composite film surface gluing quality monitoring method Download PDFInfo
- Publication number
- CN115170572A CN115170572A CN202211092033.4A CN202211092033A CN115170572A CN 115170572 A CN115170572 A CN 115170572A CN 202211092033 A CN202211092033 A CN 202211092033A CN 115170572 A CN115170572 A CN 115170572A
- Authority
- CN
- China
- Prior art keywords
- gray
- image
- super
- pixel
- index
- 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.)
- Granted
Links
- 239000002131 composite material Substances 0.000 title claims abstract description 144
- 239000011127 biaxially oriented polypropylene Substances 0.000 title claims abstract description 141
- 229920006378 biaxially oriented polypropylene Polymers 0.000 title claims abstract description 141
- 238000004026 adhesive bonding Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000013441 quality evaluation Methods 0.000 claims description 17
- 238000005286 illumination Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 3
- 238000000844 transformation Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 15
- 238000012545 processing Methods 0.000 abstract description 6
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 239000011248 coating agent Substances 0.000 description 19
- 238000000576 coating method Methods 0.000 description 19
- 230000037303 wrinkles Effects 0.000 description 18
- 239000000853 adhesive Substances 0.000 description 8
- 230000001070 adhesive effect Effects 0.000 description 8
- 239000003292 glue Substances 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000013329 compounding Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000003566 sealing material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a method for monitoring the surface gluing quality of a BOPP composite film. The method comprises the following steps: selecting an image to be enhanced according to gray values of pixel points in a gray image of the BOPP composite film under the irradiation of light sources at various angles; dividing the gray level image under each angle to obtain each superpixel block set; obtaining a light source influence degree index according to the gray value of pixel points in each super pixel block set, and performing multi-scale fusion on the image to be enhanced according to the similarity index and the light source influence degree index of any two super pixel blocks in the image to be enhanced to obtain the significance index of each pixel point; enhancing the image to be enhanced based on the significance index; and judging the gluing quality based on the number of the edge lines in the enhanced gray level image and the number of the pixel points on each edge line. The invention improves the detection precision of the BOPP composite film gluing quality.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for monitoring the surface gluing quality of a BOPP composite film.
Background
The common BOPP composite film is compounded by adopting a primer glue layer, but in the compounding process of gluing or coating the composite layer, the coating amount of glue is possibly unstable due to process limitation or the precision problem of a coating assembly, so that the composite layer after compounding has inconsistent thickness. If the coating amount of the glue cannot be controlled before compounding due to process limitation, the compounding operation may generate large quality defects, and the overall quality of the formed sealing material is finally influenced; if the tension degree of the surface of the sheet material is not enough during conveying, the composite film can generate slight wavy fluctuation, so that the operation quality of the coating assembly is negatively influenced, and the use effect of the BOPP composite film is finally influenced. Therefore, after the BOPP composite film is coated with glue, the coating quality of the BOPP composite film needs to be detected so as to improve the qualified rate of products.
In the prior art, an image of a BOPP composite film to be detected is generally input into a neural network, features in the image are extracted by using the neural network, and then the gluing quality of the BOPP composite film to be detected is judged, wherein the gluing quality of the BOPP composite film to be detected is mainly detected based on the gray difference between a fold area and a normal gluing area of the BOPP composite film. However, the coated BOPP composite film has a certain gloss, and is inevitably interfered by a light source when an image is collected, so that the gray scale of a wrinkle area in the collected image is not greatly different from the gray scale of a normal area, and the gluing quality of the BOPP composite film cannot be accurately evaluated.
Disclosure of Invention
The invention aims to provide a method for monitoring the surface gluing quality of a BOPP composite film, which adopts the following technical scheme:
the invention provides a BOPP composite film surface gluing quality monitoring method, which comprises the following steps:
acquiring gray level images of the BOPP composite film to be detected under the irradiation of light sources at different angles;
obtaining quality evaluation indexes of the gray images under the irradiation of the light sources at all angles according to the gray values of all pixel points in the gray images under the irradiation of the light sources at all angles and the gray average values of the pixel points in the gray images under the irradiation of the light sources at all angles, and taking the gray image with the maximum quality evaluation index as an image to be enhanced;
performing superpixel segmentation on the gray image to obtain each superpixel block set corresponding to the BOPP composite film to be detected; obtaining a light source influence degree index corresponding to each super pixel block set according to the gray value of the pixel point in each super pixel block set; calculating the similarity index of any two superpixel blocks in the image to be enhanced according to the light source influence degree index and the gray value of each superpixel block in each superpixel block set; obtaining the overall significance of each super-pixel block in the image to be enhanced according to the similarity index and the light source influence degree index; performing multi-scale fusion on the image to be enhanced based on the overall significance to obtain significance indexes of all pixel points in the image to be enhanced;
performing image enhancement on the image to be enhanced based on the significance index to obtain a target gray image; performing edge detection on the target gray level image to obtain a plurality of edge lines; obtaining a quality index of the BOPP composite film to be detected according to the number of the edge lines and the number of the pixel points on each edge line; and judging the gluing quality of the BOPP composite film to be detected based on the quality index.
Preferably, the obtaining of the quality evaluation index of the grayscale image under the irradiation of the light source at each angle according to the grayscale value of each pixel point in the grayscale image under the irradiation of the light source at each angle and the grayscale mean value of the pixel points in the grayscale image under the irradiation of the light source at each angle includes:
for gray scale images under illumination of any angle of light source:
calculating the quality evaluation index of the gray level image by adopting the following formula:
wherein, the first and the second end of the pipe are connected with each other,
as an index for evaluating the quality of the gradation image,
is an exponential function with a natural constant e as a base number, U is the number of pixel points in the gray level image,
the gray value of the u-th pixel point in the gray image,
the gray average value of the pixel points in the gray image is obtained.
Preferably, the performing super-pixel segmentation on the gray image to obtain each super-pixel block set corresponding to the BOPP composite film to be detected includes:
respectively carrying out superpixel segmentation on the gray level image under the irradiation of the light source at each angle to obtain each superpixel block corresponding to the gray level image under the irradiation of the light source at each angle; the number and the position distribution of initial seed points are the same when the gray level image under the irradiation of the light source of each angle is subjected to superpixel segmentation;
for gray scale images under illumination of any angle of light source: numbering each super-pixel block corresponding to the gray-scale image from left to right and from top to bottom in sequence based on the position of the initial seed point of the gray-scale image during super-pixel segmentation;
and taking the super pixel blocks with the same number in the gray scale image under the irradiation of the light sources with all angles as a super pixel block set to obtain a plurality of super pixel block sets corresponding to the BOPP composite film to be detected.
Preferably, the obtaining of the light source influence degree index corresponding to each super pixel block set according to the gray value of the pixel point in each super pixel block set includes:
for any super pixel block set corresponding to the BOPP composite film to be detected:
calculating the difference value of the gray values of any two superpixels in the superpixel block set, and calculating the average difference value of the gray values of every two superpixels in the superpixel block set according to the difference value of the gray values of any two superpixels in the superpixel block set, wherein the average difference value is used as a light source influence degree index corresponding to the superpixel block set;
the gray values of the super-pixel blocks are: and calculating the average gray value of all pixel points in the superpixel block based on the gray value of each pixel point in the superpixel block, and taking the average gray value as the gray value of the superpixel block.
Preferably, the calculating the similarity index of any two super pixel blocks in the image to be enhanced according to the light source influence degree index and the gray value of each super pixel block in each super pixel block set includes:
for any two superpixel blocks in the image to be enhanced:
calculating the square root of the sum of squares of the difference of the light source influence degree indexes corresponding to the super pixel block set where the two super pixel blocks are located and the difference of the gray values of the two super pixel blocks, and recording the square root as a first square root; calculating the reciprocal of the sum of the first square root and the adjustment parameter as the similarity index of the two superpixel blocks.
Preferably, the obtaining the overall significance of each super-pixel block in the image to be enhanced according to the similarity index and the light source influence degree index includes:
for any superpixel block in the image to be enhanced:
selecting any super-pixel block in a super-pixel block set where the super-pixel block is located as a target super-pixel block, recording each super-pixel block in 8 neighborhoods of the target super-pixel block as each neighborhood super-pixel block, respectively calculating an absolute value of a difference value of gray values of the target super-pixel block and each neighborhood super-pixel block, and using the absolute value as a gray difference value of the target super-pixel block and the corresponding neighborhood super-pixel block; calculating the average value of the gray difference values of the target superpixel block and all the neighborhood superpixel blocks as the average gray difference of the target superpixel block and the superpixel blocks in 8 neighborhoods thereof;
according to the similarity index of the super pixel block and each super pixel block in 64 super pixel blocks which are most similar to the super pixel block, the light source influence degree index corresponding to the super pixel block set in which the super pixel block is positioned and the average gray difference between each super pixel block in the super pixel block set in which the super pixel block is positioned and each super pixel block in the 8-neighborhood of the super pixel block, the overall significance of the super pixel block is calculated by adopting the following steps:
wherein the content of the first and second substances,
for the overall significance of the super-pixel block,
for the similarity index of this superpixel block and the h-th superpixel block of the 64 superpixel blocks that are most similar to it,
the index of the influence degree of the light source corresponding to the super pixel block set in which the super pixel block is located,
the average gray difference between the jth super pixel block in the super pixel block set where the super pixel block is located and the super pixel block in the 8 adjacent region,
is an exponential function with a natural constant e as a base number, and J is the number of the superpixels in the superpixel block set in which the superpixel block is positioned.
Preferably, the significance index of any pixel point in the image to be enhanced is as follows: calculating the ratio of the side length of a pre-partition of a gray image of the BOPP composite film to be detected under the irradiation of light sources at various angles to the number of times corresponding to each scale transformation of the pixel point, and recording as a first ratio; taking the integral significance of the super pixel block where the pixel point is positioned as a base number, and taking the value of an exponential function taking the first ratio as an index as a significance value of the corresponding scale transformation; and calculating the mean value of the significance values of all the secondary scale transformations as the significance index of the pixel point.
Preferably, the method for acquiring the gray value of any pixel point in the target gray image comprises the following steps: calculating the sum of 1 and the significance index of the pixel point as a first index; calculating the product of the first index and the gray value of the pixel point before enhancement to serve as a target gray value corresponding to the pixel point; if the target gray value is larger than 255, taking 255 as the gray value of the pixel point; and if the target gray value corresponding to the pixel point is smaller than or equal to 255, taking the target gray value corresponding to the pixel point as the gray value of the pixel point.
Preferably, the obtaining of the quality index of the BOPP composite film to be detected according to the number of the edge lines and the number of the pixel points on each edge line includes:
counting the total number of pixel points on all edge lines in the target gray-scale image, calculating the product of the total number and the number of the edge lines in the target gray-scale image, and recording the product as a second product;
and taking the natural constant e as a base number, and taking the value of the exponential function taking the negative second product as an index as the quality index of the BOPP composite film to be detected.
Preferably, the determining the gluing quality of the BOPP composite film to be detected based on the quality index includes:
and judging whether the quality index is larger than a quality index threshold value, if so, judging that the gluing quality of the BOPP composite film to be detected reaches the standard, and if not, judging that the gluing quality of the BOPP composite film to be detected does not reach the standard.
The invention has the following beneficial effects:
1. because the existing method for detecting the surface gluing quality of the BOPP composite film based on image processing does not consider that the BOPP composite film is possibly interfered by illumination when an image is collected, and further the detection precision of the gluing quality is influenced, the method selects an optimal gray image from the collected images as an image to be enhanced based on the gray values of pixel points in the gray image of the BOPP composite film to be detected under the irradiation of light sources at different angles, performs multi-scale fusion on the image to be enhanced subsequently, obtains the significance index of each pixel point in the image to be enhanced, further performs image enhancement on the image to be enhanced, judges the gluing quality of the BOPP composite film to be detected based on the enhanced image, reduces the calculated amount, and simultaneously improves the detection precision of the gluing quality of the BOPP composite film to be detected.
2. When an image to be enhanced is subjected to multi-scale fusion, the overall significance of each super-pixel block in the image to be enhanced is obtained based on the light source influence degree index corresponding to each super-pixel block set corresponding to the BOPP composite film to be detected and the similarity index of any two super-pixel blocks in the image to be enhanced, and the significance index of each pixel point in the image to be enhanced is obtained based on the overall significance of each super-pixel block in the image to be enhanced; according to the method, the similarity between the gray values of the pixel blocks is considered, the influence degree of the pixel blocks by the light source is also considered, and the significance is given according to the influence degree, so that the significance index of the pixel points in the image to be enhanced can reflect the significance of the wrinkle area in the BOPP composite film to be detected, the accuracy of subsequent gluing quality detection is improved, and the rejection rate of products when leaving a factory is reduced.
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 flow chart of a method for monitoring the surface gluing quality of a BOPP composite film provided by the invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the method for monitoring the surface gluing quality of the BOPP composite film according to the present invention is provided with the accompanying drawings and the preferred 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 following specifically describes a specific scheme of the method for monitoring the surface gluing quality of the BOPP composite film, which is provided by the invention, with reference to the accompanying drawings.
The embodiment of the method for monitoring the surface gluing quality of the BOPP composite film comprises the following steps:
the embodiment provides a method for monitoring the surface gluing quality of a BOPP composite film, and as shown in fig. 1, the method for monitoring the surface gluing quality of the BOPP composite film comprises the following steps:
s1, obtaining gray level images of the BOPP composite film to be detected under the irradiation of light sources at different angles.
In the process of coating the surface of the BOPP composite film, the situation that the glue coating distribution on the surface of the BOPP composite film is uneven may exist, so that the obtained image on the surface of the film may have wrinkles, and therefore the obtained image needs to be enhanced firstly when the surface glue coating quality of the BOPP composite film is detected, so that a more accurate detection result can be obtained, and the rejection rate of products when leaving a factory is reduced.
In the embodiment, the BOPP composite film to be detected (the BOPP composite film with the surface coated with the glue) is placed on the conveyor belt, and the industrial camera is used for collecting the surface image of the BOPP composite film, but the coating material is transparent, and the coating material is also transparent, so that when the image is collected, if only one image is collected, part of wrinkles can not be displayed, the detection precision of the surface coated glue quality of the follow-up BOPP composite film is further reduced, and the main reason that the wrinkles can be displayed is that the protruding parts of the wrinkles reflect light, so that human eyes can observe the wrinkles. Therefore, in the embodiment, when the surface image of the BOPP composite film to be detected is collected, the multi-angle light source is adopted to irradiate the BOPP composite film to be detected, the camera is used to collect the image of the BOPP composite film to be detected, when the image of the BOPP composite film to be detected is collected, the position and the visual field of the camera are unchanged, the image of the BOPP composite film to be detected is always shot at an overlook angle, one image is obtained under the light source of each angle, and the size of the images obtained under the light sources of each angle is the same. In the embodiment, four light sources are arranged and uniformly distributed around the industrial camera, that is, images of the BOPP composite film to be detected under the irradiation of the light sources at four angles are acquired. In a specific application, the number of angles of the light source and the position of the light source can be set by an implementer. It should be noted that: the distances between the light sources at all angles and the central point of the BOPP composite film to be detected are equal, the light sources at all angles are the same except for different positions, and for example, the illumination brightness, the color tone and the like are the same.
Preprocessing such as graying and denoising is carried out on the acquired BOPP composite film image to be detected, the preprocessed image is recorded as an initial grayscale image, graying uses an average weighted graying formula, denoising uses Gaussian filtering to carry out denoising, and graying processing and denoising processing are known technologies and are not described herein again.
In consideration of the fact that when an image is acquired, in order to ensure that all positions on the BOPP composite film to be detected can be completely presented in the image, the visual field of the camera is set to be large, and therefore the initial gray-scale image not only contains the image of the BOPP composite film to be detected, but also contains a complex background. In order to avoid the influence of other noises on the detection of the surface gluing quality of the BOPP composite film to be detected, the ResNet neural network is adopted in the embodiment to identify the BOPP composite film in the initial gray level image.
The specific content of the ResNet neural network is as follows:
the training set of the ResNet neural network is gray level images of various BOPP composite films obtained through collection; the task of the ResNet neural network is classification, pixels needing to be segmented are divided into two types, and the label labeling process corresponding to the training set is as follows: the semantic label of a single channel marks 0 for the pixel point belonging to the background and marks 1 for the pixel point belonging to the BOPP composite film; the loss function used by the network is a cross-entropy loss function. The training process of the network is the prior art, and is not described in detail here.
And respectively inputting each initial image into the trained ResNet neural network to obtain gray level images of the BOPP composite film to be detected under the irradiation of light sources at all angles, wherein the gray level images are used for detecting the gluing quality, the interference of irrelevant factors is eliminated, the calculated amount is reduced, and the detection efficiency of the gluing quality is improved.
And S2, obtaining the quality evaluation index of the gray image under the irradiation of the light source at each angle according to the gray value of each pixel point in the gray image under the irradiation of the light source at each angle and the gray average value of the pixel points in the gray image under the irradiation of the light source at each angle, and taking the gray image with the maximum quality evaluation index as the image to be enhanced.
In this embodiment, based on the gray values of the pixels in the gray image irradiated by the light source at each angle, the gray image irradiated by the light source at the optimal angle is selected as the image to be enhanced.
For gray scale images under illumination of any angle of light source:
firstly, calculating the average gray value of all pixel points in the gray image based on the gray value of each pixel point in the gray image, and recording the average gray value as the gray average value of the pixel points in the gray image; if the difference between the gray values of all the pixel points in the gray image and the gray average value of the pixel points in the gray image is small, the contrast of the gray image is low, the difference between a wrinkle region and a non-wrinkle region is not obvious, and the gray image is not selected to be used as a detection image in gluing quality detection in order to accurately detect the quality of the BOPP composite film to be detected; based on the above, calculating the quality evaluation index of the gray image according to the gray value of each pixel point in the gray image and the gray average value of the pixel points in the gray image, namely:
wherein the content of the first and second substances,
as an index for evaluating the quality of the gradation image,
is an exponential function with a natural constant e as a base number, U is the number of pixel points in the gray level image,
is the gray value of the u-th pixel point in the gray image,
the gray average value of the pixel points in the gray image is obtained.
The representation is the difference between the gray value of the pixel point in the gray image and the average gray value of the pixel point in the gray image, the smaller the difference is, the closer the gray value of the pixel point in the gray image is to the average gray value of the pixel point in the gray image, the lower the contrast of the gray image is, the worse the quality of the gray image is, namely, the quality evaluation index
The smaller; the larger the difference between the gray value of the pixel point in the gray image and the average gray value of the pixel point in the gray image is, the higher the contrast of the gray image is, the more the gray image is used for detecting the gluing quality, namely, the quality evaluation index
The larger.
By adopting the method, the quality evaluation indexes of the gray-scale images under the irradiation of the light sources at all angles can be obtained, the larger the quality evaluation index is, the larger the contrast of the image is, namely, the image is more suitable for the detection of the gluing quality, and in order to reduce the calculation amount, the image with the best quality is selected for enhancement, so that the gray-scale image with the largest quality evaluation index is selected as the image to be enhanced in the embodiment.
S3, performing superpixel segmentation on the gray image to obtain each superpixel block set corresponding to the BOPP composite film to be detected; obtaining a light source influence degree index corresponding to each super pixel block set according to the gray value of the pixel point in each super pixel block set; calculating the similarity index of any two superpixel blocks in the image to be enhanced according to the light source influence degree index and the gray value of each superpixel block in each superpixel block set; obtaining the overall significance of each super-pixel block in the image to be enhanced according to the similarity index and the light source influence degree index; and performing multi-scale fusion on the image to be enhanced based on the overall significance to obtain the significance index of each pixel point in the image to be enhanced.
In this embodiment, the gray images of the BOPP composite film to be detected under the irradiation of the light sources at various angles are subjected to superpixel segmentation, the pre-segmentation block size of each gray image is N × N, the number of initial seed points in each gray image is K, and the distribution of the initial seed points in each gray image is the same, that is, the position of the 1 st initial seed point in each gray image is the same, the position of the 2 nd initial seed point in each gray image is the same, and so on, the position of the K th initial seed point in each gray image is the same, so that each superpixel block corresponding to the gray image under the irradiation of the light source at various angles is obtained, and each gray image has K superpixel blocks. In this embodiment, the value of N is set to 200, which can be set by the implementer in a specific application.
For any super pixel block in any gray image, acquiring the gray value of each pixel point in the super pixel block, calculating the average gray value of all pixel points in the super pixel block based on the gray value of each pixel point in the super pixel block, and taking the average gray value as the gray value of the super pixel block. By adopting the method, the gray values of all the superpixel blocks in the gray image can be obtained.
When wrinkles exist in the BOPP composite film to be detected, if the wrinkles do not suffer from light source interference, the difference between the gray value of the pixel points in the wrinkle area in the gray image and the gray value of the pixel points in the normal area is larger.
In this embodiment, the superpixel blocks with the same initial seed point position in the gray image irradiated by the light sources at all angles are used as a superpixel block set to obtain K superpixel block sets corresponding to the BOPP composite film to be detected, since the embodiment has 4 light sources, that is, gray images irradiated by the light sources at 4 angles are total, each superpixel block set is composed of 4 superpixel blocks, that is, the BOPP composite film to be detectedThe kth set of superpixels corresponding to the merged film can be represented as
Wherein D is the kth super pixel block set corresponding to the BOPP composite film to be detected,
is a superpixel block where the kth initial seed point in the gray image under the illumination of the light source with the angle of 1 st is located,
is the superpixel block where the kth initial seed point is located in the gray scale image under the illumination of the light source with the angle of 2,
is the superpixel block where the kth initial seed point is located in the gray scale image under the illumination of the light source with the 3 rd angle,
the initial seed point is a superpixel block where the kth initial seed point in the gray image under the illumination of the light source with the 4 th angle is located. If there is no interference of the light source, the positions of the 4 superpixel blocks in each superpixel block set in the corresponding grayscale image should be highly overlapped, but in the process of actually acquiring the image, the interference degrees of the light source on different areas of the BOPP composite film to be detected are different, so that the influence degree of the light source on each area of the BOPP composite film to be detected is analyzed in the following embodiment, if the grayscale difference of the same area of the BOPP composite film to be detected under the irradiation of the light sources at different angles is smaller, it is indicated that the interference of the light source on the area of the BOPP composite film to be detected is smaller, otherwise, it is indicated that the interference of the light source on the area of the BOPP composite film to be detected is larger. Based on the above, for any super pixel block set corresponding to the BOPP composite film to be detected: calculating the difference value of the gray values of any two superpixel blocks in the superpixel block set, and calculating the gray value difference value of any two superpixel blocks in the superpixel block setAnd calculating the average difference value of the gray values of every two superpixel blocks in the superpixel block set as the light source influence degree index corresponding to the superpixel block set. The larger the gray difference of a certain area on the BOPP composite film to be detected in the collected images is, the larger the influence degree of the area on illumination is, namely, the larger the light source influence degree index corresponding to the area is.
In the embodiment, the saliency of each pixel block is obtained by considering the distance between each pixel block and the pixel block around the pixel block under the irradiation of light sources at different angles, so that the gray difference obtained by the pixel block and the pixel block around the pixel block under the irradiation of the light sources at different angles and the gray difference of the pixel block under the irradiation of the light sources at different angles are required to be calculated. Specifically, according to the light source influence degree index corresponding to the super pixel block set where each super pixel block in the image to be enhanced is located and the gray value of each super pixel block, the similarity index of any two super pixel blocks in the image to be enhanced is calculated, that is:
wherein, the first and the second end of the pipe are connected with each other,
for the similarity indicator of any two superpixel blocks in the image to be enhanced,
the index of the influence degree of the light source corresponding to the super pixel block set where the first super pixel block of the arbitrary two super pixel blocks is located,
is the first of the arbitrary two superpixel blocksA gray value of a super-pixel block;
the index of the influence degree of the light source corresponding to the super pixel block set where the second super pixel block of the arbitrary two super pixel blocks is located,
is the gray value of the second of said arbitrary two super-pixel blocks,
to adjust the parameters; introduction of
In order to ensure that the denominator is not 0, the present embodiment sets
The value of (b) is 0.01, which can be set by the practitioner in a particular application; the larger the light source influence degree index corresponding to the super pixel block set where the two super pixel blocks are located in the image to be enhanced is, the larger the characteristic difference of the two positions in the BOPP composite film to be detected is, namely the more dissimilar the two super pixel blocks are; the larger the gray difference value of the two super-pixel blocks in the image to be enhanced is, the larger the gray difference value of the two super-pixel blocks is, namely the more dissimilar the two super-pixel blocks are; when the light source influence degree index corresponding to the super pixel block set where the two super pixel blocks are located in the image to be enhanced is smaller and the gray difference of the two super pixel blocks in the image to be enhanced is smaller, the difference of the two super pixel blocks is smaller, namely the similarity index of the two super pixel blocks is smaller
The larger. By adopting the method, the similarity index of any two super pixel blocks in the image to be enhanced can be obtained.
For any super-pixel block in the image to be enhanced:
the similarity index reflects the similarity degree of the super-pixel block and other super-pixel blocks, if the similarity index of the super-pixel block and the nearest super-pixel block is smaller, the similarity degree of the super-pixel block and other super-pixel blocks is smaller, and the smaller the similarity index is, the larger the difference between the super-pixel block and other super-pixel blocks is, namely the larger the overall significance of the super-pixel block should be; the light source influence degree index reflects the interference degree of the position on the BOPP composite film to be detected by the light source during image acquisition, and the larger the interference degree is, the larger the integral significance of the superpixel block is; the larger the gray difference between the super pixel block and its neighborhood super pixel block is, the larger the difference between the characteristics of the super pixel block and its neighborhood super pixel block is, i.e. the larger the overall significance of the super pixel block should be. Based on this, the present embodiment obtains the similarity index of the super pixel block and each super pixel block in the 64 super pixel blocks most similar to the super pixel block, and calculates the overall saliency of the super pixel block according to the similarity index of the super pixel block and each super pixel block in the 64 super pixel blocks most similar to the super pixel block, the light source influence degree index corresponding to the super pixel block set where the super pixel block is located, and the average gray difference between each super pixel block in the super pixel block set where the super pixel block is located and the super pixel block in the 8-neighborhood thereof, that is:
wherein the content of the first and second substances,
for the overall significance of the super pixel block,
for the similarity index of this superpixel block and the h-th superpixel block of the 64 superpixel blocks that are most similar to it,
the index of the influence degree of the light source corresponding to the super pixel block set in which the super pixel block is located,
the average gray difference between the jth super-pixel block in the super-pixel block set in which the super-pixel block is positioned and the super-pixel block in the 8 adjacent region,
in the embodiment, since four images of the BOPP composite film to be detected are acquired in total, the value of J in the embodiment is 4. The average gray difference between the jth superpixel block in the superpixel block set and the superpixel block in the 8 neighborhood thereof
The acquisition method comprises the following steps: obtaining each super-pixel block in 8 neighborhoods of the jth super-pixel block in the super-pixel block set where the super-pixel block is located, recording the super-pixel blocks as the neighborhood super-pixel blocks, respectively calculating the absolute value of the gray value difference between the jth super-pixel block and each neighborhood super-pixel block, using the absolute value as the gray value difference between the target super-pixel block and the corresponding neighborhood super-pixel block, further calculating the average value of the gray value difference between the jth super-pixel block and all the neighborhood super-pixel blocks, and using the average value as the average gray value difference between the jth super-pixel block in the super-pixel block set where the super-pixel block is located and the super-pixel block in 8 neighborhoods thereof.
If the greater the similarity between the block and the 64 super-blocks most similar to it, the greater the similarity between the block and the super-blocks
The larger the more significant the super pixel block is; if the average gray difference between the jth super-pixel block in the super-pixel block set where the super-pixel block is located and the super-pixel block in the 8-neighborhood of the jth super-pixel block is larger, the significance of the super-pixel block is larger; the larger the influence degree of each pixel block in the super pixel block set in which the super pixel block is positioned by the light source is, namely the larger the significance of the super pixel block is; when the degree of similarity between the super-pixel block and the 64 super-pixel blocks which are most similar to the super-pixel block is smaller, the super-pixel blockWhen the average gray difference between the jth super pixel block in the super pixel block set and the super pixel block in the 8 adjacent region is larger and the influence degree index corresponding to the super pixel block set in which the super pixel block is positioned is larger, the overall significance of the super pixel block is higher
The larger.
By adopting the method, the overall significance of each super pixel block in the image to be enhanced is obtained.
Next, in this embodiment, multi-scale fusion is performed on the image to be enhanced by combining the overall significance of each super-pixel block in the image to be enhanced, so as to obtain the significance index of each pixel point in the image to be enhanced, the number of times of scale transformation has a certain influence on the significance value of the pixel point in the fused image, the greater the number of times of scale transformation is, the smaller the significance index of the pixel point in the image is, the overall significance of the super-pixel block in which the pixel point is located can reflect the significance value of the pixel point after multi-scale fusion, and if the overall significance of the super-pixel block in which a certain pixel point is located is larger, the larger the significance index of the pixel point after multi-scale fusion is. Therefore, the significance index of the pixel point in the image to be enhanced is as follows:
wherein the content of the first and second substances,
is the significance index of any pixel point in the image to be enhanced,
is the overall significance of the superpixel block in which the pixel point is located,
in order to scale the number of times,
performing m-time scale transformation, wherein N is the side length of a pre-partition of a gray image of the BOPP composite film to be detected under the irradiation of light sources at various angles; the larger the overall significance of the super-pixel block where the pixel point is located is, the larger the significance index of the pixel point is when multi-scale fusion is carried out; the more the scale transformation times are, the smaller the significance index of the pixel point is; the more the pixel points in the superpixel block in which the pixel point is located, the greater the significance index of the pixel point is when multi-scale transformation is carried out; when the whole significance of the super pixel block where the pixel point is positioned
The larger the number of scale changes
The smaller the number of the pixels in the superpixel block where the pixel is located is, the larger the significance index A of the pixel is.
By adopting the method, the significance index of each pixel point in the image to be enhanced is obtained.
S4, performing image enhancement on the image to be enhanced based on the significance index to obtain a target gray image; performing edge detection on the target gray level image to obtain a plurality of edge lines; obtaining the quality index of the BOPP composite film to be detected according to the number of the edge lines and the number of the pixel points on each edge line; and judging the gluing quality of the BOPP composite film to be detected based on the quality index.
In this embodiment, image enhancement is performed on the image to be enhanced by combining with the significance index of each pixel point in the image to be enhanced, and the enhanced image is obtained by combining with linear gray scale conversion and is recorded as a target gray scale image. The change of the gray value of the pixel point in the enhanced image depends on the gray value before enhancement and the significance index, and if the gray value of the pixel point before enhancement is larger and the significance index is also larger, the gray value after enhancement is also larger. The gray value before the image enhancement is larger and the significance index of the pixel point is larger, then the gray value after the pixel point enhancement is also larger. Therefore, the target gray value corresponding to any pixel point in the target gray image is:
wherein, F is a target gray value corresponding to the pixel point, g is a gray value (a gray value before enhancement) of each pixel point in the image to be enhanced, and a is a significance index of the pixel point. If the gray value of the pixel point before image enhancement is larger and the significance index of the pixel point is larger, the gray value of the pixel point after enhancement is also larger, namely the value of F is larger; if the gray value of the pixel point before image enhancement is smaller and the significance index of the pixel point is smaller, the gray value of the pixel point after enhancement is also smaller, namely the value of F is smaller. If the target gray value F corresponding to the pixel point is greater than 255, then 255 is taken as the gray value of the pixel point (after enhancement); and if the target gray value F corresponding to the pixel point is less than or equal to 255, taking the target gray value corresponding to the pixel point as the gray value of the pixel point (after enhancement).
Considering that if the gluing quality of the BOPP composite film to be detected is good, no wrinkle area appears in the surface image of the BOPP composite film to be detected, namely the number of edge lines in the surface image of the BOPP composite film to be detected is small; if the gluing quality of the BOPP composite film to be detected is poor, a plurality of wrinkle areas appear on the surface of the BOPP composite film, namely a plurality of edge lines appear in the surface image of the BOPP composite film to be detected; the more the number of the edge lines is, the more the wrinkle area is indicated; the longer the edge line, the larger the area of the wrinkled region. Therefore, in this embodiment, a canny operator is used to perform edge detection on the target gray image to obtain a plurality of edge lines, the number of pixel points on each edge line is counted, and based on the number of the edge lines and the number of pixel points on each edge line, the quality index of the BOPP composite film to be detected is calculated, that is:
wherein B is BOPP compound to be detectedThe quality index of the film is measured by the following method,
as to the number of edge lines in the target gray-scale image,
the number of pixel points on the r-th edge line in the target gray scale image. The more the number of the edge lines in the surface image of the BOPP composite film to be detected is and the more the number of the pixel points on the edge lines is, the more the wrinkle area of the BOPP composite film to be detected is, the worse the gluing quality of the BOPP composite film to be detected is, and the smaller the quality index of the BOPP composite film to be detected is; the smaller the number of the edge lines in the surface image of the BOPP composite film to be detected and the smaller the number of the pixel points on the edge lines, the smaller the wrinkle area of the BOPP composite film to be detected, i.e. the better the gluing quality of the BOPP composite film to be detected, i.e. the larger the quality index of the BOPP composite film to be detected.
Since the larger the quality index of the BOPP composite film to be detected is, the better the gluing quality of the BOPP composite film to be detected is, the quality index threshold value is set in this embodiment
Judging whether the quality index of the BOPP composite film to be detected is larger than
And if the adhesive coating quality of the BOPP composite film to be detected is greater than the preset adhesive coating quality, judging that the adhesive coating quality of the BOPP composite film to be detected is up to the preset adhesive coating quality, and if the adhesive coating quality of the BOPP composite film to be detected is less than or equal to the preset adhesive coating quality, judging that the adhesive coating quality of the BOPP composite film to be detected is not up to the preset adhesive coating quality. The quality index threshold is set to be a quality index with a larger numerical value because the quality index threshold is used for judging whether the gluing quality of the BOPP composite film to be detected reaches the standard or not, and the quality index threshold is set in the embodiment
The value of (A) is 0.7, and in a specific application, an implementer can set the value according to actual conditions
The value of (c). And finishing the detection of the gluing quality of the BOPP composite film to be detected.
Because the existing method for detecting the surface gluing quality of the BOPP composite film based on image processing does not consider that the BOPP composite film is possibly interfered by illumination when an image is collected, and further the detection precision of the gluing quality is influenced, in the embodiment, based on the gray values of pixel points in gray images of the BOPP composite film to be detected under the irradiation of light sources at different angles, an optimal gray image is selected from the collected images to be used as an image to be enhanced, multi-scale fusion is subsequently performed on the image to be enhanced, the significance index of each pixel point in the image to be enhanced is obtained, further the image to be enhanced is enhanced, the gluing quality of the BOPP composite film to be detected is judged based on the enhanced image, the calculated amount is reduced, and meanwhile, the detection precision of the gluing quality of the BOPP composite film to be detected is also improved. When the image to be enhanced is subjected to multi-scale fusion, the overall significance of each super-pixel block in the image to be enhanced is obtained based on the light source influence degree index corresponding to each super-pixel block set corresponding to the BOPP composite film to be detected and the similarity index of any two super-pixel blocks in the image to be enhanced, and the significance index of each pixel point in the image to be enhanced is obtained based on the overall significance of each super-pixel block in the image to be enhanced; according to the embodiment, the similarity between the gray values of the pixel blocks is considered, the influence degree of the pixel blocks from the light source is also considered, and the significance is given according to the influence degree, so that the significance index of the pixel points in the image to be enhanced can reflect the significance of the wrinkle area in the BOPP composite film to be detected, the accuracy of subsequent gluing quality detection is improved, and the rejection rate of products when leaving a factory is reduced.
It should be noted that: 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 (10)
1. A BOPP composite film surface gluing quality monitoring method is characterized by comprising the following steps:
acquiring gray images of the BOPP composite film to be detected under the irradiation of light sources at different angles;
obtaining quality evaluation indexes of the gray images under the irradiation of the light sources at all angles according to the gray values of all pixel points in the gray images under the irradiation of the light sources at all angles and the gray average value of the pixel points in the gray images under the irradiation of the light sources at all angles, and taking the gray image with the maximum quality evaluation index as an image to be enhanced;
performing super-pixel segmentation on the gray image to obtain each super-pixel block set corresponding to the BOPP composite film to be detected; obtaining a light source influence degree index corresponding to each super pixel block set according to the gray value of the pixel point in each super pixel block set; calculating the similarity index of any two superpixel blocks in the image to be enhanced according to the light source influence degree index and the gray value of each superpixel block in each superpixel block set; obtaining the overall significance of each superpixel block in the image to be enhanced according to the similarity index and the light source influence degree index; performing multi-scale fusion on the image to be enhanced based on the overall significance to obtain significance indexes of all pixel points in the image to be enhanced;
performing image enhancement on the image to be enhanced based on the significance index to obtain a target gray image; performing edge detection on the target gray level image to obtain a plurality of edge lines; obtaining a quality index of the BOPP composite film to be detected according to the number of the edge lines and the number of the pixel points on each edge line; and judging the gluing quality of the BOPP composite film to be detected based on the quality index.
2. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the quality evaluation index of the gray image under the irradiation of the light source at each angle is obtained according to the gray value of each pixel point in the gray image under the irradiation of the light source at each angle and the gray average value of the pixel points in the gray image under the irradiation of the light source at each angle, and comprises the following steps:
for gray scale images under illumination of any angle of light source:
calculating the quality evaluation index of the gray level image by adopting the following formula:
wherein the content of the first and second substances,
as an index of quality evaluation of the gradation image,
is an exponential function with a natural constant e as a base number, U is the number of pixel points in the gray image,
the gray value of the u-th pixel point in the gray image,
the gray average value of the pixel points in the gray image is obtained.
3. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of performing superpixel segmentation on the gray image to obtain each superpixel block set corresponding to the BOPP composite film to be detected comprises the following steps:
respectively carrying out superpixel segmentation on the gray level image under the irradiation of the light source at each angle to obtain each superpixel block corresponding to the gray level image under the irradiation of the light source at each angle; the number and the position distribution of initial seed points are the same when the gray scale image under the irradiation of the light source of each angle is subjected to super pixel segmentation;
for gray scale images under illumination of any angle of light source: numbering each superpixel block corresponding to the gray image from left to right and from top to bottom in sequence based on the position of the initial seed point when the gray image is subjected to superpixel segmentation;
and taking the super pixel blocks with the same number in the gray scale image under the irradiation of the light sources with all angles as a super pixel block set to obtain a plurality of super pixel block sets corresponding to the BOPP composite film to be detected.
4. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of obtaining the light source influence degree index corresponding to each super-pixel block set according to the gray values of the pixels in each super-pixel block set comprises the following steps:
for any super pixel block set corresponding to the BOPP composite film to be detected:
calculating the difference value of the gray values of any two superpixels in the superpixel block set, and calculating the average difference value of the gray values of every two superpixels in the superpixel block set according to the difference value of the gray values of any two superpixels in the superpixel block set, wherein the average difference value is used as a light source influence degree index corresponding to the superpixel block set;
the gray values of the superpixel blocks are: and calculating the average gray value of all the pixel points in the super pixel block based on the gray value of each pixel point in the super pixel block, and taking the average gray value as the gray value of the super pixel block.
5. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of calculating the similarity index of any two superpixel blocks in the image to be enhanced according to the light source influence degree index and the gray value of each superpixel block in each superpixel block set comprises the following steps:
for any two super-pixel blocks in the image to be enhanced:
calculating the square root of the sum of squares of the difference of the light source influence degree indexes corresponding to the super pixel block set where the two super pixel blocks are located and the difference of the gray values of the two super pixel blocks, and recording the square root as a first square root; calculating the reciprocal of the sum of the first square root and the adjustment parameter as the similarity index of the two superpixel blocks.
6. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of obtaining the overall significance of each superpixel block in the image to be enhanced according to the similarity index and the light source influence degree index comprises the following steps:
for any super-pixel block in the image to be enhanced:
selecting any superpixel block in a superpixel block set where the superpixel block is located as a target superpixel block, recording each superpixel block in 8 neighborhoods of the target superpixel block as each neighborhood superpixel block, respectively calculating the absolute value of the gray value difference value between the target superpixel block and each neighborhood superpixel block, and taking the absolute value as the gray value difference value between the target superpixel block and the corresponding neighborhood superpixel block; calculating the average value of the gray difference values of the target superpixel block and all the neighborhood superpixel blocks as the average gray difference of the target superpixel block and the superpixel blocks in 8 neighborhoods thereof;
according to the similarity index of the super pixel block and each super pixel block in 64 super pixel blocks which are most similar to the super pixel block, the light source influence degree index corresponding to the super pixel block set in which the super pixel block is positioned and the average gray difference between each super pixel block in the super pixel block set in which the super pixel block is positioned and each super pixel block in the 8-neighborhood of the super pixel block, the overall significance of the super pixel block is calculated by adopting the following steps:
wherein the content of the first and second substances,
for the overall significance of the super-pixel block,
for the similarity index of this superpixel block and the h-th superpixel block of the 64 superpixel blocks that are most similar to it,
the index of the influence degree of the light source corresponding to the super pixel block set in which the super pixel block is located,
the average gray difference between the jth super-pixel block in the super-pixel block set in which the super-pixel block is positioned and the super-pixel block in the 8 adjacent region,
is an exponential function with a natural constant e as a base number, and J is the number of the superpixels in the superpixel block set in which the superpixel block is positioned.
7. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the significance index of any pixel point in the image to be enhanced is as follows: calculating the ratio of the side length of a pre-partition block of a gray level image of the BOPP composite film to be detected under the irradiation of light sources at all angles to the number of times corresponding to each scale transformation of the pixel point, and recording as a first ratio; taking the integral significance of the super-pixel block where the pixel point is located as a base number, and taking the value of an exponential function taking the first ratio as an index as a significance value of the corresponding scale transformation; and calculating the mean value of the significant values of all the secondary scale transformations as the significance index of the pixel point.
8. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the method for acquiring the gray value of any pixel point in the target gray image comprises the following steps: calculating the sum of 1 and the significance index of the pixel point as a first index; calculating the product of the first index and the gray value of the pixel point before enhancement to serve as a target gray value corresponding to the pixel point; if the target gray value is larger than 255, taking 255 as the gray value of the pixel point; and if the target gray value corresponding to the pixel point is smaller than or equal to 255, taking the target gray value corresponding to the pixel point as the gray value of the pixel point.
9. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of obtaining the quality index of the BOPP composite film to be detected according to the number of the edge lines and the number of the pixel points on each edge line comprises the following steps:
counting the total number of pixel points on all edge lines in the target gray-scale image, calculating the product of the total number and the number of the edge lines in the target gray-scale image, and recording the product as a second product;
and taking the natural constant e as a base number, and taking the value of the negative second product as the exponential function of the index as the quality index of the BOPP composite film to be detected.
10. The method for monitoring the surface gluing quality of the BOPP composite film according to claim 1, wherein the step of judging the gluing quality of the BOPP composite film to be detected based on the quality index comprises the following steps:
and judging whether the quality index is larger than a quality index threshold value, if so, judging that the gluing quality of the BOPP composite film to be detected reaches the standard, and if not, judging that the gluing quality of the BOPP composite film to be detected does not reach the standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092033.4A CN115170572B (en) | 2022-09-08 | 2022-09-08 | BOPP composite film surface gluing quality monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211092033.4A CN115170572B (en) | 2022-09-08 | 2022-09-08 | BOPP composite film surface gluing quality monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115170572A true CN115170572A (en) | 2022-10-11 |
| CN115170572B CN115170572B (en) | 2022-11-08 |
Family
ID=83480399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211092033.4A Active CN115170572B (en) | 2022-09-08 | 2022-09-08 | BOPP composite film surface gluing quality monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115170572B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115631173A (en) * | 2022-10-28 | 2023-01-20 | 兰州理工大学 | Composite film defect identification method |
| CN115861135A (en) * | 2023-03-01 | 2023-03-28 | 铜牛能源科技(山东)有限公司 | Image enhancement and identification method applied to box panoramic detection |
| CN116152247A (en) * | 2023-04-20 | 2023-05-23 | 江苏三纳科技材料有限公司 | Quality evaluation method of polyurethane coating film |
| CN116205919A (en) * | 2023-05-05 | 2023-06-02 | 深圳市智宇精密五金塑胶有限公司 | Hardware part production quality detection method and system based on artificial intelligence |
| CN116485788A (en) * | 2023-06-16 | 2023-07-25 | 东莞市华驰高分子材料有限公司 | Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method |
| CN116665137A (en) * | 2023-08-01 | 2023-08-29 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116934636A (en) * | 2023-09-15 | 2023-10-24 | 济宁港航梁山港有限公司 | Intelligent management system for water quality real-time monitoring data |
| CN117237339A (en) * | 2023-11-10 | 2023-12-15 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1912646A (en) * | 2006-09-01 | 2007-02-14 | 中国科学院上海微系统与信息技术研究所 | MEMS micro high sensitivity magnetic field sensor and manufacturing method |
| CN101051208A (en) * | 2006-04-03 | 2007-10-10 | 夏普株式会社 | Image forming apparatus |
| JP2010223779A (en) * | 2009-03-24 | 2010-10-07 | Toppan Printing Co Ltd | Method of inspecting thin film and thin-film inspection apparatus |
| KR101349447B1 (en) * | 2012-11-05 | 2014-01-16 | 세종대학교산학협력단 | Method for measuring surface roughness of deposition film and apparatus thereof |
| CN203565268U (en) * | 2013-11-28 | 2014-04-30 | 东莞市尼的净化科技有限公司 | Automatic film gluing device |
| JP2014194355A (en) * | 2013-03-28 | 2014-10-09 | Toppan Printing Co Ltd | Thin film evaluation structure and thin film evaluation method |
| CN203917054U (en) * | 2014-04-18 | 2014-11-05 | 苏州怡拓生物传感技术有限公司 | A kind of for carry out the coating mechanism of continuous coating process at substrate surface |
| CN105196569A (en) * | 2015-09-25 | 2015-12-30 | 无锡骐泽机械科技有限公司 | Composite material forming system |
| CN205185493U (en) * | 2015-09-25 | 2016-04-27 | 无锡骐泽机械科技有限公司 | Shred oar machine of spreading drop feed mechanism |
| CN106553430A (en) * | 2015-09-25 | 2017-04-05 | 无锡骐泽机械科技有限公司 | Shredding spreads oar machine discharge mechanism |
| CN106965516A (en) * | 2017-03-27 | 2017-07-21 | 上海斯瑞科技有限公司 | A kind of shellproof Compound Fabric and preparation method thereof |
| CN206560955U (en) * | 2017-03-01 | 2017-10-17 | 常州百佳薄膜科技有限公司 | Aqueous gluing device |
| CN107789726A (en) * | 2017-10-12 | 2018-03-13 | 孙铁凡 | Blunt needle buttonhole puncturing is painless to go scab to paste |
| WO2019062092A1 (en) * | 2017-09-30 | 2019-04-04 | 深圳市颐通科技有限公司 | Superpixel- and multivariate color space-based body outline extraction method |
| CN109647658A (en) * | 2017-10-11 | 2019-04-19 | 浙江欧导自动化设备有限公司 | Glue stick anti-clogging technique in insulating paper production process |
| CN110176574A (en) * | 2019-06-14 | 2019-08-27 | 合肥国轩高科动力能源有限公司 | Lithium pre-preparing method for lithium ion battery negative pole piece |
| CN209666530U (en) * | 2019-03-11 | 2019-11-22 | 河北格林森建材科技开发有限责任公司 | Insulation board one side film machine |
| CN209753251U (en) * | 2018-12-21 | 2019-12-10 | 广东安利华新材料科技有限公司 | Intermittent coating device with good coating effect |
| CN209851767U (en) * | 2019-04-16 | 2019-12-27 | 江苏科睿坦电子科技有限公司 | Double-sided composite device for PC (polycarbonate) film |
| CN110667147A (en) * | 2017-05-28 | 2020-01-10 | 中国计量大学 | Character extraction method for film section image |
| CN111421840A (en) * | 2020-04-01 | 2020-07-17 | 泉州宁遇新材料有限公司 | Plastic film compounding machine |
| CN111798418A (en) * | 2020-06-22 | 2020-10-20 | 电子科技大学 | Wave-absorbing coating speckle defect detection method based on HOG, LBP and GLCM characteristic fusion |
| CN112651923A (en) * | 2020-11-11 | 2021-04-13 | 北京平恒智能科技有限公司 | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio |
| WO2021108844A1 (en) * | 2019-12-05 | 2021-06-10 | Commonwealth Scientific And Industrial Research Organisation | Salient object detection for artificial vision |
| CN113070190A (en) * | 2021-04-30 | 2021-07-06 | 滁州惠科光电科技有限公司 | Glue coating method and glue coating device for display device |
| CN213641260U (en) * | 2020-07-08 | 2021-07-09 | 振德医疗用品股份有限公司 | Operation film for knee |
| CN214188795U (en) * | 2020-12-09 | 2021-09-14 | 江阴通利光电科技有限公司 | Double-sided imageable dynamic film |
| WO2021243948A1 (en) * | 2020-06-01 | 2021-12-09 | 苏州苏大维格科技集团股份有限公司 | System and method for thin film processing |
| CN216573846U (en) * | 2021-12-07 | 2022-05-24 | 嘉兴瑞冠包装材料有限公司 | A rubber coating device for sealing film production |
| CN114894804A (en) * | 2022-04-22 | 2022-08-12 | 江苏名欧精密机械有限公司 | Method for detecting surface cracks of precision standard part |
| CN217190617U (en) * | 2022-04-11 | 2022-08-16 | 山东亚新塑料包装有限公司 | Film rubber coating equipartition device |
| CN114943736A (en) * | 2022-07-21 | 2022-08-26 | 山东嘉翔汽车散热器有限公司 | Production quality detection method and system for automobile radiating fins |
-
2022
- 2022-09-08 CN CN202211092033.4A patent/CN115170572B/en active Active
Patent Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101051208A (en) * | 2006-04-03 | 2007-10-10 | 夏普株式会社 | Image forming apparatus |
| CN1912646A (en) * | 2006-09-01 | 2007-02-14 | 中国科学院上海微系统与信息技术研究所 | MEMS micro high sensitivity magnetic field sensor and manufacturing method |
| JP2010223779A (en) * | 2009-03-24 | 2010-10-07 | Toppan Printing Co Ltd | Method of inspecting thin film and thin-film inspection apparatus |
| KR101349447B1 (en) * | 2012-11-05 | 2014-01-16 | 세종대학교산학협력단 | Method for measuring surface roughness of deposition film and apparatus thereof |
| JP2014194355A (en) * | 2013-03-28 | 2014-10-09 | Toppan Printing Co Ltd | Thin film evaluation structure and thin film evaluation method |
| CN203565268U (en) * | 2013-11-28 | 2014-04-30 | 东莞市尼的净化科技有限公司 | Automatic film gluing device |
| CN203917054U (en) * | 2014-04-18 | 2014-11-05 | 苏州怡拓生物传感技术有限公司 | A kind of for carry out the coating mechanism of continuous coating process at substrate surface |
| CN205185493U (en) * | 2015-09-25 | 2016-04-27 | 无锡骐泽机械科技有限公司 | Shred oar machine of spreading drop feed mechanism |
| CN106553430A (en) * | 2015-09-25 | 2017-04-05 | 无锡骐泽机械科技有限公司 | Shredding spreads oar machine discharge mechanism |
| CN105196569A (en) * | 2015-09-25 | 2015-12-30 | 无锡骐泽机械科技有限公司 | Composite material forming system |
| CN206560955U (en) * | 2017-03-01 | 2017-10-17 | 常州百佳薄膜科技有限公司 | Aqueous gluing device |
| CN106965516A (en) * | 2017-03-27 | 2017-07-21 | 上海斯瑞科技有限公司 | A kind of shellproof Compound Fabric and preparation method thereof |
| CN110667147A (en) * | 2017-05-28 | 2020-01-10 | 中国计量大学 | Character extraction method for film section image |
| WO2019062092A1 (en) * | 2017-09-30 | 2019-04-04 | 深圳市颐通科技有限公司 | Superpixel- and multivariate color space-based body outline extraction method |
| CN109647658A (en) * | 2017-10-11 | 2019-04-19 | 浙江欧导自动化设备有限公司 | Glue stick anti-clogging technique in insulating paper production process |
| CN107789726A (en) * | 2017-10-12 | 2018-03-13 | 孙铁凡 | Blunt needle buttonhole puncturing is painless to go scab to paste |
| CN209753251U (en) * | 2018-12-21 | 2019-12-10 | 广东安利华新材料科技有限公司 | Intermittent coating device with good coating effect |
| CN209666530U (en) * | 2019-03-11 | 2019-11-22 | 河北格林森建材科技开发有限责任公司 | Insulation board one side film machine |
| CN209851767U (en) * | 2019-04-16 | 2019-12-27 | 江苏科睿坦电子科技有限公司 | Double-sided composite device for PC (polycarbonate) film |
| CN110176574A (en) * | 2019-06-14 | 2019-08-27 | 合肥国轩高科动力能源有限公司 | Lithium pre-preparing method for lithium ion battery negative pole piece |
| WO2021108844A1 (en) * | 2019-12-05 | 2021-06-10 | Commonwealth Scientific And Industrial Research Organisation | Salient object detection for artificial vision |
| CN111421840A (en) * | 2020-04-01 | 2020-07-17 | 泉州宁遇新材料有限公司 | Plastic film compounding machine |
| WO2021243948A1 (en) * | 2020-06-01 | 2021-12-09 | 苏州苏大维格科技集团股份有限公司 | System and method for thin film processing |
| CN111798418A (en) * | 2020-06-22 | 2020-10-20 | 电子科技大学 | Wave-absorbing coating speckle defect detection method based on HOG, LBP and GLCM characteristic fusion |
| CN213641260U (en) * | 2020-07-08 | 2021-07-09 | 振德医疗用品股份有限公司 | Operation film for knee |
| CN112651923A (en) * | 2020-11-11 | 2021-04-13 | 北京平恒智能科技有限公司 | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio |
| CN214188795U (en) * | 2020-12-09 | 2021-09-14 | 江阴通利光电科技有限公司 | Double-sided imageable dynamic film |
| CN113070190A (en) * | 2021-04-30 | 2021-07-06 | 滁州惠科光电科技有限公司 | Glue coating method and glue coating device for display device |
| CN216573846U (en) * | 2021-12-07 | 2022-05-24 | 嘉兴瑞冠包装材料有限公司 | A rubber coating device for sealing film production |
| CN217190617U (en) * | 2022-04-11 | 2022-08-16 | 山东亚新塑料包装有限公司 | Film rubber coating equipartition device |
| CN114894804A (en) * | 2022-04-22 | 2022-08-12 | 江苏名欧精密机械有限公司 | Method for detecting surface cracks of precision standard part |
| CN114943736A (en) * | 2022-07-21 | 2022-08-26 | 山东嘉翔汽车散热器有限公司 | Production quality detection method and system for automobile radiating fins |
Non-Patent Citations (6)
| Title |
|---|
| 吴青龙等: "基于视觉中心及超像素空间加权的图像显著性检测", 《云南大学学报(自然科学版)》 * |
| 张旭东等: "结合区域协方差分析的图像显著性检测", 《中国图象图形学报》 * |
| 成培瑞等: "基于多尺度区域对比的显著目标识别", 《中国光学》 * |
| 王海罗等: "基于超像素融合算法的显著区域检测", 《北京理工大学学报》 * |
| 盛蕴霞等: "基于超像素聚类的侧扫声呐图像分割算法", 《计算机工程》 * |
| 祁瑞光等: "结合同异性度量的超像素分割方法", 《遥感信息》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115631173A (en) * | 2022-10-28 | 2023-01-20 | 兰州理工大学 | Composite film defect identification method |
| CN115861135A (en) * | 2023-03-01 | 2023-03-28 | 铜牛能源科技(山东)有限公司 | Image enhancement and identification method applied to box panoramic detection |
| CN116152247B (en) * | 2023-04-20 | 2023-08-25 | 江苏三纳科技材料有限公司 | Quality evaluation method of polyurethane coating film |
| CN116152247A (en) * | 2023-04-20 | 2023-05-23 | 江苏三纳科技材料有限公司 | Quality evaluation method of polyurethane coating film |
| CN116205919A (en) * | 2023-05-05 | 2023-06-02 | 深圳市智宇精密五金塑胶有限公司 | Hardware part production quality detection method and system based on artificial intelligence |
| CN116205919B (en) * | 2023-05-05 | 2023-06-30 | 深圳市智宇精密五金塑胶有限公司 | Hardware part production quality detection method and system based on artificial intelligence |
| CN116485788A (en) * | 2023-06-16 | 2023-07-25 | 东莞市华驰高分子材料有限公司 | Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method |
| CN116485788B (en) * | 2023-06-16 | 2023-08-29 | 东莞市华驰高分子材料有限公司 | Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method |
| CN116665137A (en) * | 2023-08-01 | 2023-08-29 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116665137B (en) * | 2023-08-01 | 2023-10-10 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116934636A (en) * | 2023-09-15 | 2023-10-24 | 济宁港航梁山港有限公司 | Intelligent management system for water quality real-time monitoring data |
| CN116934636B (en) * | 2023-09-15 | 2023-12-08 | 济宁港航梁山港有限公司 | Intelligent management system for water quality real-time monitoring data |
| CN117237339A (en) * | 2023-11-10 | 2023-12-15 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
| CN117237339B (en) * | 2023-11-10 | 2024-02-27 | 山东多沃基础工程有限公司 | Ground screw punching point position selection method and system based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115170572B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115170572B (en) | BOPP composite film surface gluing quality monitoring method | |
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| CN116363133B (en) | Illuminator accessory defect detection method based on machine vision | |
| CN110097034B (en) | Intelligent face health degree identification and evaluation method | |
| CN115294113B (en) | Quality detection method for wood veneer | |
| CN106875381B (en) | Mobile phone shell defect detection method based on deep learning | |
| EP2681715B1 (en) | Method and software for analysing microbial growth | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN114897816B (en) | Mask R-CNN mineral particle identification and particle size detection method based on improved Mask | |
| CN107798679B (en) | Breast region segmentation and calcification detection method for mammary gland molybdenum target image | |
| CN114170208A (en) | Paper product defect detection method based on artificial intelligence | |
| CN108615239B (en) | Tongue image segmentation method based on threshold technology and gray level projection | |
| CN116030060B (en) | Plastic particle quality detection method | |
| CN110298840B (en) | Yarn defect detection method based on image | |
| CN115359053B (en) | Intelligent detection method and system for defects of metal plate | |
| CN114549441B (en) | Straw defect detection method based on image processing | |
| CN113066064A (en) | Cone beam CT image biological structure identification and three-dimensional reconstruction system based on artificial intelligence | |
| CN106340007A (en) | Image processing-based automobile body paint film defect detection and identification method | |
| CN116246174B (en) | Sweet potato variety identification method based on image processing | |
| CN110910367A (en) | Bioreactor cell culture quality evaluation method | |
| CN114445707A (en) | Intelligent visual fine detection method for defects of bottled water labels | |
| CN109993728B (en) | Automatic detection method and system for deviation of thermal transfer glue | |
| CN114092682A (en) | Small hardware fitting defect detection algorithm based on machine learning | |
| CN112396580B (en) | Method for detecting defects of round part | |
| CN117274293A (en) | Accurate bacterial colony dividing method based on image features |
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 |