CN114742757A - Non-blind-area visual detection method for glue line of filter rod forming paper - Google Patents
Non-blind-area visual detection method for glue line of filter rod forming paper Download PDFInfo
- Publication number
- CN114742757A CN114742757A CN202210221634.4A CN202210221634A CN114742757A CN 114742757 A CN114742757 A CN 114742757A CN 202210221634 A CN202210221634 A CN 202210221634A CN 114742757 A CN114742757 A CN 114742757A
- Authority
- CN
- China
- Prior art keywords
- glue
- line
- image
- glue line
- coordinate
- 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.)
- Pending
Links
- 239000003292 glue Substances 0.000 title claims abstract description 119
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 230000000007 visual effect Effects 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 230000007547 defect Effects 0.000 claims abstract description 5
- 230000006740 morphological transformation Effects 0.000 claims abstract description 5
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 7
- 230000002950 deficient Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 239000000853 adhesive Substances 0.000 description 3
- 230000001070 adhesive effect Effects 0.000 description 3
- 230000000670 limiting effect Effects 0.000 description 3
- 238000005507 spraying Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011897 real-time detection Methods 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a filter stick forming paper glue line non-blind area visual detection method, which comprises the steps of collecting glue line images by using a high frame rate industrial camera, carrying out graying and histogram equalization processing on the collected original images in an industrial computer, further smoothing the images by using a mean value filtering technology, further enabling the images to form clear glue line characteristics by using a morphological transformation technology, identifying all glue lines meeting a set threshold value in the images by using Hough line transformation, and judging whether the glue lines have defects or not according to glue line parameters and further processing the glue lines.
Description
Technical Field
The invention belongs to the field of machine vision image detection and identification, and particularly relates to a non-blind-area vision detection method for a filter stick forming paper glue line.
Background
At present, the original machines of the filter rod forming equipment at early domestic do not have corresponding filter rod internal glue detection systems, when the filter rod is produced, the internal glue spraying condition is completely observed by low-frequency naked eyes of operators, the production speed of 600m/min enables the internal glue spraying condition to be completely in an uncontrolled state, and the low-frequency manual naked eye observation can not meet the requirement of real-time monitoring of the internal glue spraying quality.
With the rapid development of image processing and recognition technology, some filter rod forming equipment in China is modified and provided with corresponding inner glue detection systems, but due to the limitation of image processing speed or image transmission speed, most inner glue detection systems in the prior art in China all use low-speed industrial cameras with pixels of 30 thousands and maximum frame rate of 30 FPS. Because the maximum frame rate is only 30FPS, the maximum inner glue detection speed of the system is about 33 pieces per second without considering the influence of image processing speed, the moving speed of glue coating paper of a filter rod forming machine is at most 1000 centimeters per second, if the actual length of the formed paper obtained by each image is 5 centimeters, but because the existing inner glue detection system adopts local image detection, the actual detection length is 1 centimeter, the detection system can only detect whether the 33 centimeters of formed paper has glue per second, the effective detection area is only 33 centimeters per second, but the equipment actually runs through the 1000 centimeters of formed paper, the detection coverage rate per second is only 3.3 percent, the rest 967 centimeters of formed paper is not in the detection range of the detection system, the detection blind area is as high as 967 centimeters per second, the detection blind area accounts for about 96.7 percent per second, therefore, the detection speed of the filter rod inner glue detection system in China is generally low, and still have great detection blind area, in detecting real-time, still can not satisfy the online real-time detection demand of high-speed filter rod make-up machine completely.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a non-blind area visual detection method for a filter rod forming paper glue line, and solves the problems of low detection speed, large blind area, low real-time performance and the like of an inner glue detection system of a filter rod forming machine in the background technology.
The invention provides a filter stick forming paper glue line non-blind area visual detection method, which comprises the following steps:
s1, carrying out high-frequency acquisition on the rubber line image by using a high-frame-rate industrial camera and transmitting the rubber line image to an industrial computer in real time;
s2, carrying out gray processing on the image acquired in S1;
s3, carrying out histogram equalization on the image processed in the S2;
s4, further smoothing the image processed in the S3 by using a mean value filtering algorithm;
s5, performing morphological transformation on the image processed in the S4;
s6, identifying the characteristics of the glue line by using Hough line transformation on the image processed in the S5, and outputting a coordinate set of the glue line containing a start coordinate and an end coordinate in a two-dimensional coordinate system of the image;
and S7, calculating the positions of the glue lines, the quantity of the glue lines and the length of the glue lines according to the glue line coordinate set obtained in the step S6, and comparing the positions with set values to judge whether the glue lines of the formed paper are defective or not.
Further, in S1, a high-frame-rate industrial camera is used to perform high-frequency acquisition on the glue line image and transmit the glue line image to an industrial computer in real time, and it is necessary to meet the requirement of no blind area, a GigE interface is used for the industrial camera, and the frame rate of the industrial camera needs to be matched with the linear velocity of the glue line movement, so that the frame rate of the camera should be greater than or equal to v/m, where v is the linear velocity of the glue line movement, and m is the actual target length corresponding to one target image;
further, the convolution kernel in the mean filtering algorithm in S4 is
Further, the method for processing the mathematical morphology in S5 includes the following steps:
s5.1, transforming the image processed in the S4 according to the following formula:
where T is the transformed image, f is the processed image of S4, b is the structural element,
it is shown that the corrosion operation is performed,
represents a dilation operation, "-" represents an image subtraction operation;
and S5.2, performing binarization transformation on the T image in the S5.1.
Further, in S6, identifying the glue line features and outputting a coordinate set of the glue line containing a start coordinate and an end coordinate in the two-dimensional coordinate system of the image by using hough line transformation on the image processed in S5, including the following steps:
s6.1, traversing all non-0 pixel points in the binarized image output in the S5 from top to bottom from left to right, and obtaining coordinates of the points to form a coordinate set A;
s6.2, for each coordinate (x, y) in the coordinate set a, calculating p values when θ takes all values in the parameter set B { -90 °, -89 °, -88 °, …,89 ° }, one by one, according to the following formula:
ρ＝x*cos(θ)+y*sin(θ)
deleting the coordinates from the coordinate set A after the calculation is finished until the coordinate set is an empty set;
s6.3, for each set of parameters rho and theta in S6.2, rounding and rounding are carried out on an accumulator matrix
adding 1 to the corresponding position of acc (rho, theta);
s6.4, finding out line segments corresponding to the parameters (rho, theta) corresponding to all the numerical values of the accumulator matrix acc (rho, theta) larger than 80 to obtain a line segment coordinate set B.
S6.5, deleting line segments with the length less than 150 from the B, and combining the line segments with the distance less than 20
Further, in the step S7, the positions, the number and the lengths of the glue lines are calculated according to the glue line coordinate set obtained in the step S6 and compared with set values to judge whether the glue lines of the formed paper are defective or not, and the method includes the following steps:
s7.1, setting an abscissa interval [ Xmin, Xmax ] in which the glue line exists, traversing the line segment coordinate set B in the S6, checking whether the line segment in the coordinate set B exists in the set interval [ Xmin, Xmax ], and judging whether the glue line is in a glue shortage state or not;
s7.2, calculating the lengths of all line segments in the coordinate set B, finding the longest line segment to obtain the length Lmax, and judging whether the glue line has the condition of partial glue breaking or not according to 1/2n that whether the number of the line segments in the coordinate set B, of which the length of the line segment is less than the Lmax/2, is greater than the number of the bus segments in the coordinate set B, wherein n is the number of the detected glue lines.
The non-blind-area visual detection method for the glue line of the filter stick forming paper has the following beneficial effects:
(1) by adopting the detection method, the glue line images are acquired in real time by using the high-frame-rate industrial camera, technical means such as graying processing, histogram equalization processing, mean value filtering processing, image morphology transformation processing, Hough line transformation feature extraction and the like are simultaneously used for each acquired original image in the industrial computer, characteristic parameters of the glue lines of the formed paper can be rapidly generated, and whether the glue lines have defects or not can be rapidly judged according to the characteristic parameters of the glue lines and the set constraint conditions of the quality of the glue lines and further processed.
(2) By adopting the detection method, the average processing speed of the images can reach 0.015 millisecond/piece, the extremely fast image processing speed is benefited, the quick collection and transmission of the glue line images are carried out by combining a high frame rate GigE industrial camera, the identification and detection of the glue in the filter stick with the moving linear speed of 10 meters/second can be accurately finished, the detection coverage rate of the formed paper glue line per second reaches 100%, the detection blind area ratio per second is 0%, and the effect of non-blind area detection is achieved.
(3) Because the full-image detection is realized, but not the local detection, the lens visual field range is the effective detection range, the glue line is positioned in a tiny detection area without adjusting a camera, the glue coating surface of the forming paper is just opposite to the camera, and the glue line is positioned in the lens visual field range, so that the glue line characteristic can be quickly and stably captured, and the vibration resistance and the interference resistance are extremely strong.
Drawings
For a better understanding of the above and other objects, features, advantages and functions of the present invention, reference should be made to the embodiments illustrated in the drawings. Like reference numerals in the drawings refer to like parts. It will be appreciated by persons skilled in the art that the drawings are intended to illustrate preferred embodiments of the invention without any limiting effect on the scope of the invention, and that the various components in the drawings are not drawn to scale.
Fig. 1 shows a flow chart of a glue line blind-area-free visual inspection method for filter plug paper according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". Unless specifically stated otherwise, the term "or" means "and/or". The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same object. Other explicit and implicit definitions are also possible below.
To at least partially address one or more of the above issues and other potential issues, one embodiment of the present disclosure provides a method for blind area-free visual inspection of plug wrap glue lines, comprising the steps of:
s1, using the industrial camera with high frame rate to acquire the rubber line image for high frequency and transmitting the rubber line image to an industrial computer in real time;
s2, carrying out gray processing on the image acquired in S1;
s3, carrying out histogram equalization on the image processed in the S2;
s4, further smoothing the image processed in the S3 by using a mean value filtering algorithm;
s5, performing morphological transformation on the image processed in the S4;
s6, identifying the characteristics of the glue line by using Hough line transformation on the image processed in the S5, and outputting a coordinate set of the glue line containing a start coordinate and an end coordinate in a two-dimensional coordinate system of the image;
and S7, calculating the positions of the glue lines, the quantity of the glue lines and the length of the glue lines according to the glue line coordinate set obtained in the step S6, and comparing the positions with set values to judge whether the glue lines of the formed paper are defective or not.
In particular, as shown in figure 1,
s1, using the high frame rate industrial camera to collect the glue line image in high frequency and transmit the image to the industrial computer through a GigE (Gigabit Ethernet protocol) interface in real time, in order to meet the requirement of non-blind area detection, firstly calculating the required industrial camera frame rate to make the camera frame rate match with the glue line moving linear speed, the camera frame rate should be greater than or equal to v/m, wherein v is the glue line moving linear speed, m is the actual target length corresponding to a target image. For example: the linear velocity of the movement of the filter rod forming paper adhesive line is up to 1000 cm/s, the real length of the adhesive line corresponding to a clear adhesive line image shot by a short-focus lens is 5 cm, and the effect of non-blind area image acquisition can be realized by using an industrial camera with the frame rate of more than or equal to 200 FPS;
s2, carrying out gray processing on the image acquired by the S1 in the industrial computer;
s3, histogram equalization processing is carried out on the image processed through the S2 in the industrial computer, and the texture characteristics of the glue lines are highlighted;
s4, performing convolution kernel and two-dimensional pixel matrix of the processed image S3 in the industrial computer
Performing filtering operation to remove image noise caused by the surface texture of the formed paper;
wherein, in some embodiments, the convolution kernel can be
Where m is equal to n, and m and n are both positive odd numbers greater than 1, all elements in the matrix are 1.
S5.1, transforming the image processed in the S4 according to the following formula:
where T is the transformed image, f is the processed image of S4, b is the structural element,
it is shown that the corrosion operation is performed,
represents a dilation operation, "-" represents an image subtraction operation;
s5.2, carrying out binarization operation on the T image in the S5.1;
s6.1, traversing all non-0 pixel points of the two-dimensional pixel matrix subjected to the binarization operation in the S5.2 from left to right in sequence from top to bottom and acquiring coordinates to form a non-0 pixel coordinate set A;
s6.2, for each non-0 pixel coordinate (x, y) in the set a, the value of ρ is calculated one by one according to the following formula when θ takes all the values in the set B { -90 °, -89 °, -88 °, …,89 ° }:
ρ＝x*cos(θ)+y*sin(θ)
the result is put into a two-dimensional parameter space H (rho, theta) with theta (-phi is not more than theta and less than phi) as a horizontal coordinate and rho as a vertical coordinate every time the calculation of a non-0 pixel coordinate is finished, and the coordinate is deleted from a coordinate set A until the coordinate set is an empty set;
s6.3, creating an accumulator matrix acc (rho, theta) corresponding to the parameter space H (rho, theta), initializing the matrix to be 0, rounding up each group of parameters rho and theta in the parameter space in S6.2, and adding 1 at the corresponding position of the accumulator matrix acc (rho, theta);
s6.4, finding out line segments corresponding to the parameters (rho, theta) corresponding to all the numerical values of the accumulator matrix acc (rho, theta) larger than 80 to obtain a line segment coordinate set B.
S6.5, deleting line segments with the length less than 150 from the B, and combining the line segments with the distance less than 20
In some embodiments, the length of the deleted line segment may be between 100 and 200, and the line segments with the distance smaller than 20 to 100 may be selected to be merged;
s7.1, setting an abscissa interval [ Xmin, Xmax ] in which the glue line exists, traversing the line segment coordinate set B in the S6, checking whether the line segment in the coordinate set B exists in the set interval [ Xmin, Xmax ], and judging whether the glue line is in a glue shortage state or not;
s7.2, calculating the lengths of all line segments in the coordinate set B, finding the longest line segment to obtain the length Lmax, and judging whether the glue line has the condition of partial glue break or not according to 1/2n, wherein n is the number of the detected glue lines, of whether the number of the line segments in the coordinate set B, of which the length of the line segment is smaller than the Lmax/2, is larger than the number of the bus segments in the coordinate set B or not.
The method comprises the steps of using a high frame rate industrial camera with a frame rate matched with the moving linear speed of a glue line to carry out high-frequency acquisition on glue line images, transmitting the glue line images to an industrial computer through a GigE interface in real time, carrying out gray level processing, histogram equalization processing and mean value filtering processing on the acquired glue line images in the industrial computer, highlighting glue line characteristics of an original image and removing image texture noise points, extracting the glue line characteristics by using a morphological transformation technology, accurately identifying the glue line characteristics by using Hough line transformation and quickly generating forming paper glue line characteristic parameters, and judging whether the glue line has defects or not at an extremely high speed according to the glue line characteristic parameters and set constraint conditions of glue line quality.
Having thus described the embodiments of the present disclosure, the foregoing descriptions are intended to be illustrative, not limiting, and not limiting of the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements to the market, or to enable others of ordinary skill in the art to understand the disclosure.
Claims (6)
1. A non-blind area visual detection method for a filter stick forming paper glue line comprises the following steps:
s1, carrying out high-frequency acquisition on the rubber line image by using a high-frame-rate industrial camera and transmitting the rubber line image to an industrial computer in real time;
s2, carrying out gray processing on the image acquired in the S1;
s3, carrying out histogram equalization on the image processed in the S2;
s4, further smoothing the image processed in the S3 by using a mean value filtering algorithm;
s5, performing morphological transformation on the image processed in the S4;
s6, identifying the characteristics of the glue line by using Hough line transformation on the image processed in the S5, and outputting a coordinate set of the glue line containing a start coordinate and an end coordinate in a two-dimensional coordinate system of the image;
and S7, calculating the positions of the glue lines, the quantity of the glue lines and the length of the glue lines according to the glue line coordinate set obtained in the step S6, and comparing the positions with a set value to judge whether the glue lines of the formed paper are defective or not.
2. The filter stick forming paper glue line blind area-free visual detection method according to claim 1, characterized in that: in S1, the high-frame-rate industrial camera is used to acquire the glue line image in high frequency and transmit the glue line image to the industrial computer in real time, and it is necessary to meet the requirement of no blind area, the industrial camera data interface uses GigE, and the industrial camera frame rate needs to be matched with the linear velocity of glue line movement, and the camera frame rate should be greater than or equal to v/m, where v is the linear velocity of glue line movement, and m is the actual target length corresponding to one target image.
3. The filter stick forming paper glue line blind area-free visual detection method according to claim 1, characterized in that: the convolution kernel in the mean filtering algorithm in the S4 is
4. The filter stick forming paper glue line blind area-free visual detection method according to claim 1, characterized in that: the method for processing the mathematical morphology in S5 comprises the following steps:
s5.1, transforming the image processed in the S4 according to the following formula:
where T is the transformed image, f is the processed image of S4, b is the structural element,
it is shown that the corrosion operation is performed,
represents a dilation operation, "-" represents an image subtraction operation;
and S5.2, performing binarization transformation on the T image in the S5.1.
5. The filter stick forming paper glue line blind area-free visual detection method according to claim 1, characterized in that: in the step S6, the hough line transformation is used for identifying the glue line characteristics of the image processed in the step S5, and a coordinate set of the glue line containing a start coordinate and an end coordinate in a two-dimensional coordinate system of the image is output, including the following steps:
s6.1, traversing all non-0 pixel points in the binarized image output in the S5 from top to bottom from left to right, and obtaining coordinates of the points to form a coordinate set A;
s6.2, for each coordinate (x, y) in the set a, the value of ρ is calculated one by one according to the following formula when θ takes each value of the set B { -90 °, -89 °, -88 °, …,89 ° }:
ρ＝x*cos(θ)+y*sin(θ)；
deleting the coordinates from the coordinate set A after the calculation is finished until the coordinate set is an empty set;
s6.3, for each set of parameters rho and theta in S6.2, rounding and rounding are carried out on an accumulator matrix
adding 1 to the corresponding position of acc (rho, theta);
s6.4, finding out line segments corresponding to the parameters (rho, theta) corresponding to all values of the accumulator matrix acc (rho, theta) larger than 80 to obtain a line segment coordinate set B;
and S6.5, deleting line segments with the length less than 150 from the B, and combining the line segments with the distance less than 20.
6. The filter stick forming paper glue line blind area-free visual detection method according to claim 1, characterized in that: in the step S7, the positions of the glue lines, the number of the glue lines, and the lengths of the glue lines are calculated according to the glue line coordinate set obtained in the step S6, and compared with a set value to judge whether the glue lines of the formed paper have defects, the method includes the following steps:
s7.1, setting an abscissa interval [ Xmin, Xmax ] in which the glue line exists, traversing the line segment coordinate set B in the S6, checking whether the line segment in the coordinate set B exists in the set interval [ Xmin, Xmax ], and judging whether the glue line is in a glue shortage state or not;
s7.2, calculating the lengths of all line segments in the coordinate set B, finding the longest line segment to obtain the length Lmax, and judging whether the glue line has the condition of partial glue breaking or not according to 1/2n that whether the number of the line segments in the coordinate set B, of which the length of the line segment is less than the Lmax/2, is greater than the number of the bus segments in the coordinate set B, wherein n is the number of the detected glue lines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210221634.4A CN114742757A (en) | 2022-03-09 | 2022-03-09 | Non-blind-area visual detection method for glue line of filter rod forming paper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210221634.4A CN114742757A (en) | 2022-03-09 | 2022-03-09 | Non-blind-area visual detection method for glue line of filter rod forming paper |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114742757A true CN114742757A (en) | 2022-07-12 |
Family
ID=82275441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210221634.4A Pending CN114742757A (en) | 2022-03-09 | 2022-03-09 | Non-blind-area visual detection method for glue line of filter rod forming paper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114742757A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090245687A1 (en) * | 2008-03-31 | 2009-10-01 | Sungkyunkwan University Foundation For Corporate Collaboration | Image processing method and apparatus for detecting lines of images and start and end points of lines |
| CN203148856U (en) * | 2013-03-12 | 2013-08-21 | 深圳市联君科技有限公司 | Novel glue line detecting device |
| CN205633268U (en) * | 2016-05-09 | 2016-10-12 | 河南省新之林机电设备有限公司 | Cigarette packer wrapping paper tree lace on -line measuring visual system |
| CN108898589A (en) * | 2018-06-19 | 2018-11-27 | 南通大学 | The quick-fried pearl intelligent detecting method of filter stick based on high speed machines vision |
| CN109829876A (en) * | 2018-05-30 | 2019-05-31 | 东南大学 | Carrier bar on-line detection device of defects and method based on machine vision |
| WO2021248554A1 (en) * | 2020-06-11 | 2021-12-16 | 深圳市信宇人科技股份有限公司 | High-speed and high-precision burr detection method and detection system for lithium ion battery electrode sheet |
-
2022
- 2022-03-09 CN CN202210221634.4A patent/CN114742757A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090245687A1 (en) * | 2008-03-31 | 2009-10-01 | Sungkyunkwan University Foundation For Corporate Collaboration | Image processing method and apparatus for detecting lines of images and start and end points of lines |
| CN203148856U (en) * | 2013-03-12 | 2013-08-21 | 深圳市联君科技有限公司 | Novel glue line detecting device |
| CN205633268U (en) * | 2016-05-09 | 2016-10-12 | 河南省新之林机电设备有限公司 | Cigarette packer wrapping paper tree lace on -line measuring visual system |
| CN109829876A (en) * | 2018-05-30 | 2019-05-31 | 东南大学 | Carrier bar on-line detection device of defects and method based on machine vision |
| CN108898589A (en) * | 2018-06-19 | 2018-11-27 | 南通大学 | The quick-fried pearl intelligent detecting method of filter stick based on high speed machines vision |
| WO2021248554A1 (en) * | 2020-06-11 | 2021-12-16 | 深圳市信宇人科技股份有限公司 | High-speed and high-precision burr detection method and detection system for lithium ion battery electrode sheet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829876B (en) | Chain plate defect online detection device and method based on machine vision | |
| CN110163853B (en) | Edge defect detection method | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN102393397B (en) | System and method for detecting surface defects of magnetic shoe | |
| CN111369516B (en) | Transformer bushing heating defect detection method based on infrared image recognition | |
| CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| CN109507192A (en) | A kind of magnetic core detection method of surface flaw based on machine vision | |
| CN111489337B (en) | Automatic optical detection pseudo defect removal method and system | |
| CN105069778B (en) | Based on the industrial products detection method of surface flaw that target signature notable figure builds | |
| CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
| CN108399614B (en) | Fabric defect detection method based on non-sampling wavelet and Gumbel distribution | |
| CN114581805A (en) | Coating roller surface defect detection method adopting 3D line laser profile technology | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN112365448A (en) | Fabric defect detection method in warp knitting process | |
| CN113240668B (en) | Image digital feature distribution-based generated molten pool image quality evaluation method | |
| CN112950594B (en) | Method, device and storage medium for detecting surface defects of product | |
| CN108122209B (en) | License plate deblurring method based on countermeasure generation network | |
| CN114742757A (en) | Non-blind-area visual detection method for glue line of filter rod forming paper | |
| CN115294119B (en) | Machine vision-based method for detecting stains in inner grooves of heads of plum-blossom-shaped threads | |
| CN117036259A (en) | Metal plate surface defect detection method based on deep learning | |
| CN112330633A (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering | |
| Xiao et al. | Spatial-temporal joint zinc flotation froth image denoising based on bubble dynamic features | |
| CN111340802A (en) | Intelligent cloth inspecting machine capable of automatically inspecting cloth by adopting artificial intelligence technology |
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 |