CN110866902A - Detection method for cigarette pack warping deformation - Google Patents
Detection method for cigarette pack warping deformation Download PDFInfo
- Publication number
- CN110866902A CN110866902A CN201911075531.6A CN201911075531A CN110866902A CN 110866902 A CN110866902 A CN 110866902A CN 201911075531 A CN201911075531 A CN 201911075531A CN 110866902 A CN110866902 A CN 110866902A
- Authority
- CN
- China
- Prior art keywords
- image
- cigarette
- label paper
- value
- gray
- 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
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 114
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 235000002566 Capsicum Nutrition 0.000 claims abstract description 11
- 239000006002 Pepper Substances 0.000 claims abstract description 11
- 235000016761 Piper aduncum Nutrition 0.000 claims abstract description 11
- 235000017804 Piper guineense Nutrition 0.000 claims abstract description 11
- 235000008184 Piper nigrum Nutrition 0.000 claims abstract description 11
- 150000003839 salts Chemical class 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 28
- 241000722363 Piper Species 0.000 claims description 10
- 230000002146 bilateral effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000007639 printing Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 244000061176 Nicotiana tabacum Species 0.000 description 2
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000002788 crimping Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000006467 substitution reaction 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
-
- 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 by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
Abstract
The invention provides a detection method of cigarette pack warping deformation, which comprises the following key steps of S4, respectively filtering salt and pepper noises in a first gray level image and a second gray level image; s5, converting the first gray image and the second gray image into a first two-value image and a second two-value image respectively; s6, extracting, corroding and filling the edges of the cigarette label paper in the first two-value graph and the second two-value graph respectively to obtain a first contour graph and a second contour graph of the cigarette label paper respectively; s7, obtaining the first round of the cigarette label paperThe area A of the outline graph in the first binary graph1(ii) a S8, acquiring the area A occupied by the second contour map of the flattened cigarette label paper in the second binary map2(ii) a S9 according to area A1And area A2The buckling deformation degree of the cigarette label paper is judged according to a certain standard. The invention determines whether the cigarette label paper is deformed or not by changing the area occupied by the cigarette label paper in the image with fixed size after the cigarette label paper is printed and in a flat state, thereby obtaining the distortion and deformation degree of the cigarette label paper in time.
Description
Technical Field
The invention relates to the field of machine vision and image processing, in particular to a detection method for cigarette pack warping deformation.
Background
Nowadays, with the rapid development of computer science technologies, image recognition and machine vision technologies are beginning to be applied in various fields. The coming of the information age, the popularization of big data and the accumulation of massive video image data enable a machine vision technology to acquire more key pictures, and the condition of a product or production equipment is analyzed through the product pictures by matching with an image recognition technology and a machine learning technology.
At present, the cigarette pack has different flatness of final products due to different positions of a crimping mechanism of a printing machine or changes of environmental temperature and humidity in the production process, and poor flatness of the cigarette pack can seriously affect the production efficiency and the packaging and forming effect of the cigarette pack after the cigarette pack is mounted on a machine. If the cigarette label, especially the cigarette case, has serious warping deformation, the smooth paper feeding of the cigarette packaging machine is seriously influenced, tearing and traffic jam occur, even the cigarette is blocked, and the cigarette is not square after being packaged and formed, thereby influencing the appearance quality of finished cigarette packets.
Most of the existing methods for detecting the cigarette pack buckling deformation are used for detecting the height of the paper buckling deformation, the buckling deformation degree is usually evaluated by a height difference (the difference between a low point and a high point of the paper surface) through laser positioning equipment, the method is still suitable for regular longitudinal buckling or transverse buckling, but the method is lack of operability and accuracy for the conditions of the buckling deformation or irregular deformation and the like, and in the actual condition, the regular symmetric deformation is few conditions, so the method has obvious limitation. Meanwhile, the cigarette label produced by a common printing machine has smaller warping degree and cigarette label paper has certain reflective property, so that the existing infrared height detection or laser detection still has the problem of large detection error. In addition, certain deviation can occur along the two sides of the conveying direction when the cigarette label paper is conveyed, so that the measuring position of the infrared height detection or laser detection head is deviated, and the warping height of the cigarette label paper is seriously influenced.
Therefore, a method for detecting the cigarette pack warping deformation according to the machine vision and image processing technology with high detection precision, convenient operation, high detection speed and high detection accuracy becomes necessary.
Disclosure of Invention
In order to solve the technical problem, the invention provides a detection method for the cigarette pack warping deformation.
The invention provides a detection method of cigarette pack warping deformation, which comprises the following steps: s1, acquiring a first image of the cigarette label paper in the first target area; s2, stretching the paper to be in a flat state from the non-shooting end of the cigarette label paper through external force, and further acquiring a second image of the flat cigarette label paper; s3, converting the first image and the second image into a first gray image and a second gray image respectively; s4, filtering salt and pepper noises in the first gray level image and the second gray level image respectively; s5, converting the first gray image and the second gray image into a first two-value image and a second two-value image respectively; s6, extracting, corroding and filling the edges of the cigarette label paper in the first two-value graph and the second two-value graph respectively to obtain a first contour graph and a second contour graph of the cigarette label paper respectively; s7, acquiring the area A of the first contour map of the cigarette label paper in the first two-value map1(ii) a S8, acquiring the area A occupied by the second contour map of the flattened cigarette label paper in the second binary map2(ii) a S9 according to area A1And area A2The buckling deformation degree of the cigarette label paper is judged according to a certain standard.
Further, the first image and the second image have the same size and pixels.
Further, the step S3 of "respectively converting the first image and the second image into the first grayscale image and the second grayscale image" specifically includes: s31, respectively obtaining RGB attribute values of each pixel point in the first image and the second image; s32, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; 33. and taking the average value as the chromatic values of all the pixel points, thereby respectively obtaining a first gray image and a second gray image.
Further, "filtering salt and pepper noise in the first gray level image and the second gray level image" specifically includes: and removing salt and pepper noises at the edges of the cigarette label paper in the first gray level image and the second gray level image by a bilateral filtering method, thereby realizing the smooth processing of the edges of the cigarette label paper.
Further, the step S5 of "respectively converting the first gray scale image and the second gray scale image into the first binary image and the second binary image" specifically includes: s51, specifying an optimal pixel value threshold C, and comparing the pixel values of the pixel points in the first gray level image and the second gray level image with the optimal pixel value threshold C respectively; and S52, assigning the pixel points with the pixel values larger than the threshold value C as 255, and assigning the pixel points with the pixel values smaller than the threshold value C as 0, thereby respectively obtaining a first binary image and a second binary image.
Further, the step S6 of "extracting the edge of the cigarette label paper" specifically includes: s61, calculating gradient values of pixel areas of the horizontal edges and the vertical edges of the cigarette label paper through a sobel operator; s62, determining a gray abrupt change point according to the gradient values of the pixel regions of the flat edge and the vertical edge; s63, determining the edge points of the cigarette label paper according to the gray-scale mutation points of the first-value second-value image and the second-value image, and accordingly extracting the edge sections of the cigarette label paper in the first-value second-value image and the second-value image respectively; and S64, performing straight line fitting on each section of edge by using a least square method, thereby respectively obtaining the outline of the cigarette mark paper in the first binary image and the outline of the cigarette mark paper in the second binary image.
Further, "according to area A1And area A2The buckling deformation degree of the cigarette label paper is judged according to a certain standard, and the method specifically comprises the following steps: s91, obtaining the area A1And area A2The magnitude of the ratio of (A) to (B); s92,Determination of the area A1And area A2Whether the ratio of (a) to (b) is within a first interval, specifically 0.95 to 1.0; s93, determining the area A1And area A2The value of the ratio is not in the first interval end, and the cigarette label paper is determined to be warped and deformed.
As described above, the method for detecting the cigarette pack warping deformation of the present invention has the following beneficial effects:
the method removes salt and pepper noises at the edges of the cigarette label paper in the first gray level image and the second gray level image by a bilateral filtering method, thereby effectively ensuring the smoothness of the edges of the cigarette label paper in the images. The method extracts and determines the edge contour of the cigarette label paper in the binary image through the sobel operator, and further realizes the accurate confirmation of the contour of the cigarette label paper in the binary image by matching with the corrosion and filling operations.
The method determines whether the cigarette label paper is deformed or not through the change of the area occupied by the cigarette label paper in the image with the fixed size after the cigarette label paper is printed and in the flat state, so that the degree of distortion or irregular deformation of the cigarette label paper can be obtained in time. Meanwhile, machine vision judgment is used for replacing manual judgment, so that the detection efficiency and accuracy are improved.
Drawings
FIG. 1 is a general flowchart of a method for detecting the warpage of a cigarette pack according to the present invention;
FIG. 2 is a flowchart of step S3 of the method for detecting the warpage of a cigarette pack according to the present invention;
fig. 3 is a flowchart of step S9 of the method for detecting the cigarette pack warping deformation according to the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention and/or the technical solutions in the prior art, the following description will explain specific embodiments of the present invention with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort. In addition, the term "orientation" merely indicates a relative positional relationship between the respective members, not an absolute positional relationship.
The applied range of the picture is a high-definition picture, and the picture applied by the invention is not suitable for shooting pictures with dark environment and serious shadow overlapping of foreign objects.
As shown in fig. 1, the detection method for the cigarette pack warping deformation of the invention comprises the following steps:
and S1, acquiring a first image of the cigarette label paper of the first target area.
S2, stretching the paper to a flat state from the non-shooting end of the cigarette label paper through external force, and further obtaining a second image of the cigarette label paper after being flat.
In the method, the first image and the second image are both obtained by arranging an industrial camera at a certain position of a material receiving conveyor belt of a printing device. Because the pixels required by the invention are high, an MV-XG4300GM type industrial camera with 4300 ten thousand pixels can be selected. Since the camera position is not changed when the first image and the second image are captured, the first image and the second image can be set to be the same size and pixel. The background area of the cigarette label paper is the same, plus the first target area setting is the same.
S3, converting the first image and the second image into a first gray scale image and a second gray scale image, respectively.
As shown in fig. 2, S3 may specifically be: s31, respectively obtaining RGB attribute values of each pixel point in the first image and the second image; s32, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; 33. the average value is used as the chromatic value of all the pixel points, so that a first gray image and a second gray image are respectively obtained, and the difference between the cigarette label paper in the first image and the cigarette label paper in the second image and the background can be deepened.
And S4, filtering the salt and pepper noises in the first gray level image and the second gray level image respectively.
Images tend to produce black or white dots in certain special circumstances, which are known as salt and pepper noises. In step S4, specifically, the salt and pepper noise at the edge of the cigarette label paper in the first gray image and the second gray image is removed by a bilateral filtering method, so as to smooth the edge of the cigarette label paper.
At present, compared with Gaussian filtering, bilateral filtering can better retain edge information of an image, and the principle of bilateral filtering is that a Gaussian kernel function related to spatial distance is multiplied by a Gaussian function related to gray scale distance.
The spatial distance refers to the euclidean distance between the current point and the center point. With a spatial distance ofWhereinIs the coordinate of the central point, and the central point,is the coordinates of the current point and is,is the spatial domain standard deviation.
The gray distance refers to an absolute value of a difference between the current point gray and the center point gray, and is mathematically expressed as:whereinIs the gray value of the current pixel point,is the gray value of the pixel covering the center point of the picture area in the template, i.e. the gray value at (0,0),is the value range standard deviation.
S5, converting the first gray scale image and the second gray scale image into a first binary image and a second binary image respectively. The method specifically comprises the following steps: s51, specifying an optimal pixel value threshold C, and comparing the pixel values of the pixel points in the first gray level image and the second gray level image with the optimal pixel value threshold C respectively; and S52, assigning the pixel points with the pixel values larger than the threshold value C as 255, and assigning the pixel points with the pixel values smaller than the threshold value C as 0, thereby respectively obtaining a first binary image and a second binary image. Wherein the pixel value threshold C can be modified according to the actual demand requirement.
And S6, extracting, corroding and filling the edges of the cigarette label paper in the first two-value graph and the second two-value graph respectively to further obtain a first contour graph and a second contour graph of the cigarette label paper respectively.
Wherein, extracting the edges of the cigarette label paper specifically comprises the following steps: s61, calculating gradient values of pixel areas of the horizontal edges and the vertical edges of the cigarette label paper through a sobel operator; s62, determining a gray abrupt change point according to the gradient values of the pixel regions of the flat edge and the vertical edge; s63, determining the edge points of the cigarette label paper according to the gray-scale mutation points of the first-value second-value image and the second-value image, and accordingly extracting the edge sections of the cigarette label paper in the first-value second-value image and the second-value image respectively; and S64, performing straight line fitting on each section of edge by using a least square method, thereby respectively obtaining the outline of the cigarette mark paper in the first binary image and the outline of the cigarette mark paper in the second binary image.
S7, acquiring the area A of the first contour map of the cigarette label paper in the first two-value map1(ii) a S8, acquiring the area A occupied by the second contour map of the flattened cigarette label paper in the second binary map2(ii) a S9 according to area A1And area A2The buckling deformation degree of the cigarette label paper is judged according to a certain standard.
As shown in fig. 3, the present invention determines whether the cigarette label paper is deformed by the change of the area occupied by the cigarette label paper in the fixed size image after printing and in the flat state. The projection area of the paper is smaller than that of the original flat paper as long as the paper is printed, so that the cigarette label paper is only printed at A1And area A2When the ratio of (A) to (B) is less than a preset value, the warping deformation degree is serious, and the walking of the cigarette packaging machine can be seriously influencedThe paper is smooth and easy, tears, traffic jam appear, even cause the card machine, and the packing shaping back is just, thereby influences finished product tobacco bale appearance quality.
According to the cigarette label paper detection standard of Chinese tobacco, when the first interval is specifically 0.95 to 1.0 at present, the printed cigarette label paper positioned in the interval does not cause adverse effects on subsequent work, and belongs to normal warping of cigarette label paper. Of course, the first interval value can be adjusted according to actual conditions such as actual paper conditions and the installation position of the industrial camera.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (7)
1. A detection method of cigarette pack warping deformation is used for detecting the warping deformation degree of cigarette pack paper, and is characterized by comprising the following steps: s1, acquiring a first image of the cigarette label paper in the first target area; s2, stretching the paper to be in a flat state from the non-shooting end of the cigarette label paper through external force, and further acquiring a second image of the flat cigarette label paper; s3, converting the first image and the second image into a first gray image and a second gray image respectively; s4, filtering salt and pepper noises in the first gray level image and the second gray level image respectively; s5, converting the first gray image and the second gray image into a first two-value image and a second two-value image respectively; s6, extracting, corroding and filling the edges of the cigarette label paper in the first two-value graph and the second two-value graph respectively to obtain a first contour graph and a second contour graph of the cigarette label paper respectively; s7, acquiring the area A1 of the first contour map of the cigarette label paper in the first binary map; s8, acquiring the area A2 of the second contour map of the flattened cigarette label paper in the second numerical map; and S9, judging the buckling deformation degree of the cigarette label paper according to the ratio of the area A1 to the area A2 and a certain standard.
2. The method for detecting the warping deformation of the cigarette pack according to claim 1, wherein: the first image and the second image have the same size and pixels.
3. The method for detecting the cigarette pack warping deformation according to claim 1, wherein in step S3, "respectively converting the first image and the second image into the first gray image and the second gray image" specifically includes: s31, respectively obtaining RGB attribute values of each pixel point in the first image and the second image; s32, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; 33. and taking the average value as the chromatic values of all the pixel points, thereby respectively obtaining a first gray image and a second gray image.
4. The method for detecting the cigarette pack warping deformation according to claim 1, wherein the filtering of salt and pepper noise in the first gray image and the second gray image specifically comprises: and removing salt and pepper noises at the edges of the cigarette label paper in the first gray level image and the second gray level image by a bilateral filtering method, thereby realizing the smooth processing of the edges of the cigarette label paper.
5. The method for detecting the cigarette pack warping deformation according to claim 1, wherein in step S5, "respectively converting the first gray image and the second gray image into a first binary image and a second binary image" specifically includes: s51, specifying an optimal pixel value threshold C, and comparing the pixel values of the pixel points in the first gray level image and the second gray level image with the optimal pixel value threshold C respectively; and S52, assigning the pixel points with the pixel values larger than the threshold value C as 255, and assigning the pixel points with the pixel values smaller than the threshold value C as 0, thereby respectively obtaining a first binary image and a second binary image.
6. The method for detecting the warping deformation of the cigarette pack according to claim 1, wherein the step of "extracting the edge of the cigarette pack paper" in the step S6 specifically includes: s61, calculating gradient values of pixel areas of the horizontal edges and the vertical edges of the cigarette label paper through a sobel operator; s62, determining a gray abrupt change point according to the gradient values of the pixel regions of the flat edge and the vertical edge; s63, determining the edge points of the cigarette label paper according to the gray-scale mutation points of the first-value second-value image and the second-value image, and accordingly extracting the edge sections of the cigarette label paper in the first-value second-value image and the second-value image respectively; and S64, performing straight line fitting on each section of edge by using a least square method, thereby respectively obtaining the outline of the cigarette mark paper in the first binary image and the outline of the cigarette mark paper in the second binary image.
7. The method for detecting the cigarette pack warping deformation according to claim 1, wherein in step S9, "determining the warping deformation degree of the cigarette pack paper according to a certain criterion based on the ratio of the area a1 to the area a 2" specifically includes: s91, acquiring the ratio of the area A1 to the area A2; s92, determining whether the ratio of the area A1 to the area A2 is in a first interval, wherein the first interval is specifically 0.95-1.0; s93, when the ratio of the area A1 to the area A2 is determined not to be in the first interval end, determining the cigarette label paper warping deformation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911075531.6A CN110866902A (en) | 2019-11-06 | 2019-11-06 | Detection method for cigarette pack warping deformation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911075531.6A CN110866902A (en) | 2019-11-06 | 2019-11-06 | Detection method for cigarette pack warping deformation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110866902A true CN110866902A (en) | 2020-03-06 |
Family
ID=69653006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911075531.6A Pending CN110866902A (en) | 2019-11-06 | 2019-11-06 | Detection method for cigarette pack warping deformation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110866902A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111815603A (en) * | 2020-07-07 | 2020-10-23 | 湖北中烟工业有限责任公司 | Method for detecting curvature of tipping paper for flexography by using image recognition |
CN114972344A (en) * | 2022-07-29 | 2022-08-30 | 山东聊城中泰表业有限公司 | Production quality defect detection method for watch accessories |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
CN103150735A (en) * | 2013-03-26 | 2013-06-12 | 山东大学 | Gray level difference averaging-based image edge detection method |
CN103760170A (en) * | 2013-12-26 | 2014-04-30 | 中国电子科技集团公司第四十一研究所 | Tobacco bale lining defect detection method based on machine vision technology |
US20150023578A1 (en) * | 2012-03-05 | 2015-01-22 | Hong'en (Hangzhou, China) Medical Technology Inc. | Device and method for determining border of target region of medical images |
-
2019
- 2019-11-06 CN CN201911075531.6A patent/CN110866902A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
US20150023578A1 (en) * | 2012-03-05 | 2015-01-22 | Hong'en (Hangzhou, China) Medical Technology Inc. | Device and method for determining border of target region of medical images |
CN103150735A (en) * | 2013-03-26 | 2013-06-12 | 山东大学 | Gray level difference averaging-based image edge detection method |
CN103760170A (en) * | 2013-12-26 | 2014-04-30 | 中国电子科技集团公司第四十一研究所 | Tobacco bale lining defect detection method based on machine vision technology |
Non-Patent Citations (1)
Title |
---|
刘骊等: "《计算机服装建模及仿真》", 31 December 2018 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111815603A (en) * | 2020-07-07 | 2020-10-23 | 湖北中烟工业有限责任公司 | Method for detecting curvature of tipping paper for flexography by using image recognition |
CN114972344A (en) * | 2022-07-29 | 2022-08-30 | 山东聊城中泰表业有限公司 | Production quality defect detection method for watch accessories |
CN114972344B (en) * | 2022-07-29 | 2022-10-04 | 山东聊城中泰表业有限公司 | Production quality defect detection method for watch accessories |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109636815B (en) | Metal plate strip product label information identification method based on computer vision | |
CN109886896B (en) | Blue license plate segmentation and correction method | |
EP3309703B1 (en) | Method and system for decoding qr code based on weighted average grey method | |
CN109409374B (en) | Joint-based same-batch test paper answer area cutting method | |
CN108345881B (en) | Document quality detection method based on computer vision | |
CN109472271B (en) | Printed circuit board image contour extraction method and device | |
CN104331695B (en) | A kind of circle marker symbol shape quality detection method of robust | |
CN104568986A (en) | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm | |
CN111242896A (en) | Color printing label defect detection and quality rating method | |
JP5830338B2 (en) | Form recognition method and form recognition apparatus | |
CN110866902A (en) | Detection method for cigarette pack warping deformation | |
CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
US20200084320A1 (en) | Print quality diagnosis | |
CN115078365A (en) | Soft package printing quality defect detection method | |
JP4062987B2 (en) | Image area dividing method, image area dividing apparatus, and image area dividing program | |
WO2014063837A1 (en) | Method and device for identifying a two-dimensional barcode | |
CN1898555B (en) | Substrate inspection device | |
CN112419225B (en) | SOP type chip detection method and system based on pin segmentation | |
CN112634259A (en) | Automatic modeling and positioning method for keyboard keycaps | |
CN111967457A (en) | OCR detection method based on deep learning | |
US20030179421A1 (en) | Method for automatically determining document position in a scanner window | |
CN111178210A (en) | Image identification and alignment method for cross mark | |
CN113840135B (en) | Color cast detection method, device, equipment and storage medium | |
CN115984185A (en) | Paper towel package defect detection method, device and system and storage medium | |
CN115170525A (en) | Image difference detection method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |