CN111815603A - Method for detecting curvature of tipping paper for flexography by using image recognition - Google Patents
Method for detecting curvature of tipping paper for flexography by using image recognition Download PDFInfo
- Publication number
- CN111815603A CN111815603A CN202010646742.7A CN202010646742A CN111815603A CN 111815603 A CN111815603 A CN 111815603A CN 202010646742 A CN202010646742 A CN 202010646742A CN 111815603 A CN111815603 A CN 111815603A
- Authority
- CN
- China
- Prior art keywords
- image
- tipping paper
- flexography
- pixel
- detecting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000007647 flexography Methods 0.000 title claims abstract description 19
- 239000006002 Pepper Substances 0.000 claims abstract description 11
- 235000002566 Capsicum Nutrition 0.000 claims abstract description 10
- 235000016761 Piper aduncum Nutrition 0.000 claims abstract description 10
- 235000017804 Piper guineense Nutrition 0.000 claims abstract description 10
- 235000008184 Piper nigrum Nutrition 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 150000003839 salts Chemical class 0.000 claims abstract description 10
- 238000005260 corrosion Methods 0.000 claims abstract description 3
- 230000007797 corrosion Effects 0.000 claims abstract description 3
- 241000722363 Piper Species 0.000 claims description 9
- 230000003628 erosive effect Effects 0.000 claims description 6
- 230000002146 bilateral effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 abstract 1
- 238000007639 printing Methods 0.000 description 19
- 238000001514 detection method Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 7
- 235000019504 cigarettes Nutrition 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000005452 bending Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000037303 wrinkles Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 231100000956 nontoxicity Toxicity 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000002788 crimping Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000005096 rolling 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
- 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
- G06T5/20—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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/136—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
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/30144—Printing quality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for detecting the curvature of a tipping paper for flexography by using image recognition, which comprises the following steps: s1, acquiring a first image of the tipping paper in the designated area; s2, converting the first image of the tipping paper into a gray value image; s3, filtering salt and pepper noise in the grey value graph, and converting the grey value graph into a binary value graph; s4, carrying out corrosion, expansion and connected component processing on the binary image; s5, acquiring a first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image; s6, acquiring the length of each first built-in line segment, and adding the lengths of the first built-in line segments to obtain a first total length; and S7, comparing the first total length with a first preset length, and if the length of the first total length is greater than the first preset length, indicating that the warping degree of the tipping paper exceeds the standard.
Description
Technical Field
The invention relates to the field of paper detection and image processing, in particular to a method for detecting the curvature of tipping paper for flexography by using image recognition.
Background
Since the beginning of the last century, Japan used the tipping paper technology for cigarette manufacture, tipping paper was also used as paper for cigarette holders of modern cigarettes because of its beautiful texture, high air permeability, safety and non-toxicity. With the remarkable development of printing technology, flexographic printing is gradually used in the fields of food, cigarette holders and the like because of environmental protection, no toxicity, bright printing pattern effect and high printing efficiency of the ink.
At present, in order to improve the printing effect of the tipping paper for cigarettes, a large number of flexo printing devices are produced, and part of the flexo printing devices are also modified to carry out flexo printing on the tipping paper. Tipping paper can cause the tipping paper to wrinkle and even edge buckling deformation due to the difference of the position of a crimping mechanism of a printing machine or the change of the temperature and humidity of the environment in the production process, the printing effect of the tipping paper is seriously affected, and meanwhile, the probability of the conditions of tearing, traffic jam, card jamming and the like during rolling after the printing of the tipping paper can be caused. Therefore, a method for detecting warping degree of tipping paper during printing is needed.
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 is analyzed through the product picture by matching with an image recognition technology and a machine learning technology. Most of the existing methods for detecting the warping deformation of the tipping paper detect the height of the warping deformation of the paper, and the warping deformation degree is often evaluated by a height difference (the difference between a low point and a high point of the paper) through a laser positioning device. However, since the flexible printing process of the tipping paper is completed by matching the paper release roll and the paper collection roll with the printing mechanism, the tipping paper is straightened by the device in the longitudinal direction, and the detection target is also changed into detection of the longitudinal warping degree of the tipping paper and the wrinkle degree of the tipping paper. The existing detection equipment is lack of the detection function for the target. Meanwhile, because the tipping paper produced by a common printing machine has small warping degree and certain reflective property, the laser detection is difficult to detect the small changes, thereby causing the problems of large detection error and low detection precision. Because the printed tipping paper is rolled, the fine crease deformation and paper warping can be accumulated, thereby influencing the processes of printing the tipping paper in the early stage and manufacturing the cigarette holder in the later stage.
Therefore, a method for detecting the curvature of the tipping paper for flexo printing using image recognition with high detection accuracy, easy operation, and high detection speed is required.
Disclosure of Invention
In order to solve the above technical problem, the present invention provides a method of detecting a curvature of a tipping paper for flexography using image recognition.
The invention provides a method for detecting the bending degree of a tipping paper for flexography by using image recognition, which is used for detecting the wrinkle and the warping degree of the tipping paper. The method comprises the following steps: s1, acquiring a first image of the tipping paper in the designated area; s2, converting the first image of the tipping paper into a gray value image; s3, filtering salt and pepper noise in the grey value graph, and converting the grey value graph into a binary value graph; s4, carrying out corrosion, expansion and connected component processing on the binary image; s5, acquiring a first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image; s6, acquiring the length of each first built-in line segment, and adding the lengths of the first built-in line segments to obtain a first total length; and S7, comparing the first total length with a first preset length, and if the length of the first total length is greater than the first preset length, indicating that the warping degree of the tipping paper exceeds the standard.
Further, the step S2 specifically includes: s21, acquiring RGB attribute values of all pixel points in the first image; s22, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; and S23, taking the average value as the chromatic value of all the pixel points, thereby obtaining a gray value map of the first image.
Further, the step S3 "converting the gray-value map into the binary map" specifically includes: threshold segmentation is carried out on each pixel point of the gray value image by adopting a maximum inter-class variance method, a preset constant c is designated as an optimal threshold, and if the pixel value of the pixel point in the gray value image is smaller than the constant c, the original pixel is assigned to be 0; if the pixel value is larger than the constant c, the original pixel value is assigned to 255, so that a binary image with only two pixel values is obtained.
Further, the constant c is preferably 60.
Further, the step S4 of "performing erosion, expansion, and connected component processing on the binary image" specifically includes: performing erosion processing on the binary image by using an imode function, removing fine protruding parts in the binary image, performing expansion processing on the eroded image by using an imode function, and properly expanding the image of each continuous line segment in the binary image; and performing 8-connected component extraction on the expanded image.
Further, the step S3 of "filtering salt and pepper noise in gray value map" specifically includes: and removing discrete salt and pepper noise points in the gray value graph by a bilateral filtering method, thereby realizing the smooth processing of the edge of the tipping paper.
Further, in step S5, "acquiring the first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image" specifically includes: s51, calculating gradient values of pixel regions of the horizontal edges of the packaging paper through a sobel operator; s52, determining a gray-level abrupt change point according to the gradient value of the pixel region with the flat edge; s53, determining the edge point of the tipping paper according to the gray-scale catastrophe point of the binary image, thereby extracting the edge segment of the tipping paper in the binary image; s54, performing straight line fitting on each edge section by using a least square method to further obtain a first edge contour image of the tipping paper; and S55, performing straight line fitting on the gray-scale catastrophe points in the first edge contour image to obtain each first built-in line segment.
Further, in step S5, when the length of any one of the obtained first built-in line segments is greater than a second preset length, it is determined that the warping degree of the target tipping paper exceeds the standard, and the second preset length is smaller than the first preset length.
As described above, the method for detecting the curvature of the tipping paper for flexography using image recognition according to the present invention has the following advantageous effects:
the method removes salt and pepper noise at the edge of the gray image tipping paper by a bilateral filtering method, thereby effectively ensuring the smoothness of the edge of the tipping paper in the image. According to the method, the first edge contour image of the tipping paper is obtained through the sobel operator, and each first built-in line segment in the first edge contour image is obtained by matching with a least square method, so that the position of each crease line in the tipping paper is accurately obtained. The invention judges whether the tipping paper in the first image has a crease caused by bending or not by comparing the length of the single first built-in line segment with the second preset length. According to the invention, whether the crease degree of the tipping paper exceeds the standard or not is determined by comparing the first total length with the first preset length. Meanwhile, the image recognition is used for replacing the manual judgment, so that the detection efficiency and the accuracy are improved.
Drawings
Fig. 1 is a general flowchart of a method of detecting a curvature of a tipping paper for flexography using image recognition according to the present invention;
fig. 2 is a flowchart of step S2 of a method of detecting the bow of a tipping paper for flexography using image recognition according to the present invention;
fig. 3 is a flowchart of step S5 of a method of detecting the bow of a tipping paper for flexography using image recognition 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 applicable range of the picture acted by the invention is a picture with high brightness and high pixels, a high-light auxiliary lighting device can be used for directly projecting the paper packaging shooting part during shooting, and an industrial camera with high pixels can be used during shooting.
As shown in fig. 1, a method of detecting a curvature of a tipping paper for flexography using image recognition of the present invention includes the following steps S1-S7.
S1, acquiring a first image of the tipping paper in the designated area.
Wherein the appointed region can be for tipping paper body paper unreel the back in the region before getting into printing mechanism, and then can confirm the angularity of tipping paper before the printing to prevent in advance to tear, phenomenon emergence such as traffic congestion.
And S2, converting the first image of the tipping paper into a gray value image.
As shown in fig. 2, step S2 specifically includes: s21, acquiring RGB attribute values of all pixel points in the first image; s22, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; and S23, taking the average value as the chromatic value of all the pixel points, thereby obtaining a gray value map of the first image.
And S3, filtering the salt-pepper noise in the grey value graph, and converting the grey value graph into a binary value graph.
The 'salt and pepper noise in the filtering gray value graph' is specifically as follows: and removing discrete salt and pepper noise points in the gray value graph by a bilateral filtering method, thereby realizing the smooth processing of the edge of the tipping paper. "and convert the gray value map into a binary map" specifically includes: threshold segmentation is carried out on each pixel point of the gray value image by adopting a maximum inter-class variance method, a preset constant c is designated as an optimal threshold, and if the pixel value of the pixel point in the gray value image is smaller than the constant c, the original pixel is assigned to be 0; if the pixel value is larger than the constant c, the original pixel value is assigned to 255, so that a binary image with only two pixel values is obtained. Since the pixel value of the line segment at the fold or crease of the sheet is low, the constant c is preferably 60.
And S4, carrying out erosion, expansion and connected component processing on the binary image.
The present invention can be implemented by MATLAB software, wherein step S4 specifically includes: performing erosion processing on the binary image by using an imode function, removing fine protruding parts in the binary image, performing expansion processing on the eroded image by using an imode function, and properly expanding the image of each continuous line segment in the binary image; and performing 8-connected component extraction on the expanded image.
And S5, acquiring a first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image.
As shown in fig. 3, the step S5, "acquiring the first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image" specifically includes: s51, calculating gradient values of pixel regions of the horizontal edges of the packaging paper through a sobel operator; s52, determining a gray-level abrupt change point according to the gradient value of the pixel region with the flat edge; s53, determining the edge point of the tipping paper according to the gray-scale catastrophe point of the binary image, thereby extracting the edge segment of the tipping paper in the binary image; s54, performing straight line fitting on each edge section by using a least square method to further obtain a first edge contour image of the tipping paper; and S55, performing straight line fitting on the gray-scale catastrophe points in the first edge contour image to obtain each first built-in line segment.
In addition, in step S5, when the length of any one of the acquired first built-in line segments is greater than a second preset length, it is determined that the warping degree of the target tipping paper exceeds the standard, and the second preset length is smaller than the first preset length. Thus, whether the tipping paper in the first image has a crease caused by bending is judged.
And S6, acquiring the lengths of the first built-in line segments, and adding the lengths of the first built-in line segments to obtain a first total length.
And S7, comparing the first total length with a first preset length, and if the length of the first total length is greater than the first preset length, indicating that the warping degree of the tipping paper exceeds the standard.
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 (8)
1. A method of detecting the bow of a tipping paper for flexography using image recognition, for detecting the degree of creasing and warping of the tipping paper, comprising the steps of: s1, acquiring a first image of the tipping paper in the designated area; s2, converting the first image of the tipping paper into a gray value image; s3, filtering salt and pepper noise in the grey value graph, and converting the grey value graph into a binary value graph; s4, carrying out corrosion, expansion and connected component processing on the binary image; s5, acquiring a first edge contour image of the tipping paper from the binary image, and extracting each first built-in line segment in the first edge contour image; s6, acquiring the length of each first built-in line segment, and adding the lengths of the first built-in line segments to obtain a first total length; and S7, comparing the first total length with a first preset length, and if the length of the first total length is greater than the first preset length, indicating that the warping degree of the tipping paper exceeds the standard.
2. The method for detecting the curvature of a tipping paper for flexography using image recognition according to claim 1, wherein the step S2 is embodied as: s21, acquiring RGB attribute values of all pixel points in the first image; s22, adding the values of the three superposed color channels of red, green and blue of each pixel point to obtain an average value; and S23, taking the average value as the chromatic value of all the pixel points, thereby obtaining a gray value map of the first image.
3. The method for detecting the curvature of a tipping paper for flexography using image recognition according to claim 1, wherein the step of S3 "and converting the gray value map into a binary map" is embodied as follows: threshold segmentation is carried out on each pixel point of the gray value image by adopting a maximum inter-class variance method, a preset constant c is designated as an optimal threshold, and if the pixel value of the pixel point in the gray value image is smaller than the constant c, the original pixel is assigned to be 0; if the pixel value is larger than the constant c, the original pixel value is assigned to 255, so that a binary image with only two pixel values is obtained.
4. A method of detecting the bow of a tipping paper for flexography using image recognition according to claim 3, wherein: the constant c is preferably 60.
5. The method for detecting the curvature of the tipping paper for flexography using image recognition according to claim 1, wherein the "subjecting the binary image to erosion, expansion, connected component processing" in the step S4 is specifically: performing erosion processing on the binary image by using an imode function, removing fine protruding parts in the binary image, performing expansion processing on the eroded image by using an imode function, and properly expanding the image of each continuous line segment in the binary image; and performing 8-connected component extraction on the expanded image.
6. The method for detecting the curvature of the tipping paper for flexography using image recognition according to claim 1, wherein the "salt and pepper noise in the filtered gray value map" in the step S3 is specifically: and removing discrete salt and pepper noise points in the gray value graph by a bilateral filtering method, thereby realizing the smooth processing of the edge of the tipping paper.
7. The method for detecting the curvature of the tipping paper for flexography according to claim 1, wherein the step S5 of acquiring the first edge contour image of the tipping paper from the binary image and extracting each first built-in line segment in the first edge contour image is specifically as follows: s51, calculating gradient values of pixel regions of the horizontal edges of the packaging paper through a sobel operator; s52, determining a gray-level abrupt change point according to the gradient value of the pixel region with the flat edge; s53, determining the edge point of the tipping paper according to the gray-scale catastrophe point of the binary image, thereby extracting the edge segment of the tipping paper in the binary image; s54, performing straight line fitting on each edge section by using a least square method to further obtain a first edge contour image of the tipping paper; and S55, performing straight line fitting on the gray-scale catastrophe points in the first edge contour image to obtain each first built-in line segment.
8. A method of detecting the bow of a tipping paper for flexography using image recognition according to claim 1, wherein: in step S5, when the length of any one of the obtained first built-in line segments is greater than a second preset length, it is determined that the warping degree of the target tipping paper exceeds the standard, and the second preset length is smaller than the first preset length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646742.7A CN111815603A (en) | 2020-07-07 | 2020-07-07 | Method for detecting curvature of tipping paper for flexography by using image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646742.7A CN111815603A (en) | 2020-07-07 | 2020-07-07 | Method for detecting curvature of tipping paper for flexography by using image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815603A true CN111815603A (en) | 2020-10-23 |
Family
ID=72843493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010646742.7A Pending CN111815603A (en) | 2020-07-07 | 2020-07-07 | Method for detecting curvature of tipping paper for flexography by using image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815603A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001177728A (en) * | 1999-12-17 | 2001-06-29 | Fuji Photo Film Co Ltd | Edge detection method and image processing method |
| JP2003194734A (en) * | 2002-08-08 | 2003-07-09 | Ngk Spark Plug Co Ltd | Inspection method and device for printing pattern |
| JP2005214734A (en) * | 2004-01-28 | 2005-08-11 | Fuji Xerox Co Ltd | Device for inspecting paper wrinkle, and control device |
| CN110403232A (en) * | 2019-07-24 | 2019-11-05 | 浙江中烟工业有限责任公司 | A kind of cigarette quality detection method based on second level algorithm |
| CN110723342A (en) * | 2019-10-15 | 2020-01-24 | 上海烟草机械有限责任公司 | Cigar quality detection system and detection method |
| US20200048837A1 (en) * | 2018-08-10 | 2020-02-13 | Solenis Technologies, L.P. | Sheet characterization of crepe paper |
| CN110866902A (en) * | 2019-11-06 | 2020-03-06 | 湖北中烟工业有限责任公司 | Detection method for cigarette pack warping deformation |
-
2020
- 2020-07-07 CN CN202010646742.7A patent/CN111815603A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001177728A (en) * | 1999-12-17 | 2001-06-29 | Fuji Photo Film Co Ltd | Edge detection method and image processing method |
| JP2003194734A (en) * | 2002-08-08 | 2003-07-09 | Ngk Spark Plug Co Ltd | Inspection method and device for printing pattern |
| JP2005214734A (en) * | 2004-01-28 | 2005-08-11 | Fuji Xerox Co Ltd | Device for inspecting paper wrinkle, and control device |
| US20200048837A1 (en) * | 2018-08-10 | 2020-02-13 | Solenis Technologies, L.P. | Sheet characterization of crepe paper |
| CN110403232A (en) * | 2019-07-24 | 2019-11-05 | 浙江中烟工业有限责任公司 | A kind of cigarette quality detection method based on second level algorithm |
| CN110723342A (en) * | 2019-10-15 | 2020-01-24 | 上海烟草机械有限责任公司 | Cigar quality detection system and detection method |
| CN110866902A (en) * | 2019-11-06 | 2020-03-06 | 湖北中烟工业有限责任公司 | Detection method for cigarette pack warping deformation |
Non-Patent Citations (2)
| Title |
|---|
| 吴成刚 等: "基于机器视觉的卷接机接装纸图像检测***", 食品与机械, vol. 36, no. 1, pages 150 - 156 * |
| 王晖 等: "基于机器视觉的接装纸缺陷检测装置", 烟草科技, vol. 48, no. 8, pages 88 - 92 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108918526B (en) | Notch defect detection method for flexible IC packaging substrate circuit | |
| US8098933B2 (en) | Method and apparatus for partitioning an object from an image | |
| CN107367241B (en) | Automobile tire pattern recognition method based on machine vision | |
| CN104732231B (en) | A kind of recognition methods of valuable bills | |
| CN110293753B (en) | Method for image detection of printed products by means of a computer | |
| CN115359047A (en) | Abnormal defect detection method for intelligent welding of PCB (printed circuit board) | |
| US8577121B2 (en) | Forged seal imprint inspection method and recording medium | |
| EP2256691B1 (en) | Image processing device for vehicle and image processing program | |
| CN111815603A (en) | Method for detecting curvature of tipping paper for flexography by using image recognition | |
| CN117274291A (en) | Method for detecting mold demolding residues based on computer vision | |
| JP2005181218A (en) | Board inspecting device | |
| JP5010627B2 (en) | Character recognition device and character recognition method | |
| CN110866902A (en) | Detection method for cigarette pack warping deformation | |
| CN114565585A (en) | Image detection method | |
| CN106650719B (en) | Method and device for identifying picture characters | |
| JP5439069B2 (en) | Character recognition device and character recognition method | |
| JP4658779B2 (en) | Haze detection method, apparatus, and computer program | |
| JP5993100B2 (en) | Image processing apparatus and specific figure detection method | |
| JP6665903B2 (en) | Feature image generation device, inspection device, feature image generation method, and feature image generation program | |
| JP3358997B2 (en) | Engraved mark identification device | |
| JP3844594B2 (en) | Industrial character recognition method | |
| CN111311696A (en) | License plate authenticity detection method based on hyperspectral unmixing technology | |
| CN111144218A (en) | Traffic sign identification method and device in vehicle driving process | |
| CN113160181B (en) | Stacking profile counting method based on image recognition | |
| JP3126491B2 (en) | Pattern recognition method |
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 |