CN110930381A - Tobacco flake shape determination method for improving production quality of fine cigarettes - Google Patents
Tobacco flake shape determination method for improving production quality of fine cigarettes Download PDFInfo
- Publication number
- CN110930381A CN110930381A CN201911134561.XA CN201911134561A CN110930381A CN 110930381 A CN110930381 A CN 110930381A CN 201911134561 A CN201911134561 A CN 201911134561A CN 110930381 A CN110930381 A CN 110930381A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- image
- leaf
- calculating
- target
- 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
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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
-
- 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
- G06T2207/10024—Color 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
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention relates to a tobacco flake shape measuring method for improving the production quality of fine cigarettes, which comprises the following steps: step 1: tobacco leaf pretreatment: dispersing the tobacco leaves subjected to smoking on a transmission belt; step 2: image acquisition: arranging a camera above the conveyor belt, and continuously collecting sample images; and step 3: image processing: segmenting the image, extracting a tobacco target and removing interference; and 4, step 4: and (3) calculating: calculating the area of the tobacco target and the length-width ratio of the minimum circumscribed rectangle; and 5: and (4) classification: classifying according to the area size, and calculating the leaf profile coefficient of the tobacco leaves; step 6: conversion: and calculating the mean value and distribution of the leaf-shaped coefficients. The method can intuitively calculate the leaf profile coefficient of the tobacco leaves, realize the conversion from image to digitization, and intuitively embody the overall shape coefficient mean value, variance and distribution condition of the tobacco leaves through big data statistics and analysis, thereby facilitating the realization of data management and classification and screening use, and helping the realization of quality refinement management and control in the process of producing the slim cigarettes.
Description
Technical Field
The invention relates to a tobacco flake shape measuring method for improving the production quality of fine cigarettes, belongs to the technical field of detection of tobacco, and can be used as an evaluation and control means for optimizing the production quality of the fine cigarettes.
Background
The tobacco leaves are used as important raw materials for cigarette production, and the physical properties of the tobacco leaves have great influence on the cigarette processing quality. The shape of the tobacco fragments can be used as one of the quality statistical indexes of tobacco processing, the tobacco processing process pursues the large size and integrity of the tobacco fragments, and the more serious the tobacco fragment lumping fragments are, the worse the processing quality is. The thin cigarette refers to various new cigarette varieties with the cigarette diameter obviously smaller than that of a standard cigarette, and along with the rapid development of the thin cigarette in recent years, the requirements on the raw material of the sheet cigarette and the structure of the cut tobacco are higher and higher, the traditional tobacco sheet and the structure of the cut tobacco are difficult to adapt to the quality requirements of the thin cigarette, and defective cigarettes are easy to appear in the production process. In the rolling process of the fine cigarette, the distribution nonuniformity and the like in the axial direction of the tobacco shreds are easier to be superposed and amplified, the great fluctuation of the cigarette suction resistance, tar and sensory quality is caused, the difficulty of quality control of the fine cigarette product is increased, the shutdown times of the fine cigarette in the rolling and connecting process are more due to the fact that the tobacco shred structure of the conventional fine cigarette cannot be effectively controlled and the tobacco shred stem content is relatively high, and the production efficiency of equipment is generally lower than that of standard cigarette production.
In order to solve the problems and enable quality control in the production process to be more refined, the invention constructs a sheet tobacco shape characterization index and a determination method, so as to measure and evaluate the geometric characteristics of the sheet tobacco structure and the influence on the subsequent cut tobacco and rolling quality, and help to solve the quality optimization problem in the production process of the fine cigarette. The specific technical scheme is as follows:
a tobacco flake shape measuring method for improving the production quality of fine cigarettes comprises the following operation steps:
step 1: tobacco leaf pretreatment: dispersing the tobacco leaves subjected to smoking on a transmission belt;
step 2: image acquisition: arranging a camera above the conveyor belt, and continuously collecting sample images;
and step 3: image processing: segmenting the image, extracting a tobacco target and removing interference;
and 4, step 4: and (3) calculating: calculating the area of the tobacco target and the length-width ratio of the minimum circumscribed rectangle;
and 5: and (4) classification: classifying according to the area size, and calculating the leaf profile coefficient of the tobacco leaves;
step 6: conversion: and calculating the mean value and distribution of the leaf-shaped coefficients.
Further, the formula for calculating the leaf profile coefficient of the tobacco leaf in the step 4 is as follows:
wherein a represents the minimum circumscribed rectangle length of the tobacco leaf, b represents the minimum circumscribed rectangle width and a>B. The intuitive meaning of the coefficient represents that the shape of the tobacco leaves tends to be square (leaf form coefficient is 1) or slender (leaf form coefficient)<1) And the degree of elongation.
Further, the tobacco leaf target extraction in the step 3 is to separate the true tobacco leaf target in the collected image from the background conveyor belt, the specific method is based on the color difference, RGB represents the three colors of red, green and blue in the collected image, the conveyor belt color is pure green, ideally, R is 0, G is Gx, B is 0, through practical analysis, the tobacco leaf color is R, G is G, B is B, wherein R, G, B are not zero, and the R, G value of the tobacco leaf is closer, the B value of the tobacco leaf is far less than R, G value, the B value is subtracted from all pixels of the image in sequence, the result is used as the processed image, so that the tobacco leaf on the image is more obviously compared with the conveyor belt, assuming that the value of the corresponding pixel point of the processed image is P (x, y), the tobacco leaf and the background of the conveyor belt can be separated by setting a threshold value for P (x, y), marking the target pixel of the tobacco leaf as 1 and marking the background pixel as 0, finishing the binarization process of the image for subsequent image analysis processing.
Further, in step 3, the specific process of image segmentation processing is as follows: firstly, threshold segmentation and area screening are carried out on the enhanced image, whether tobacco leaves exist on the image or not is judged, and if yes, connected domains are carried out, so that each tobacco leaf is independent.
Further, the specific method of the connected domain is as follows: in a binary image, the background region pixels have a value of 0 and the target region pixels have a value of 1, and assuming an image is scanned from left to right and from top to bottom, marking the pixel currently being scanned requires checking its connectivity to the several neighbor pixels scanned before it.
Further, before the area of the tobacco leaf target and the minimum circumscribed rectangle are calculated in the step 4, each tobacco leaf on the image is numbered, and then the ratio of the area to the length to the width of the minimum circumscribed rectangle is obtained one by one.
The invention has the beneficial effects that:
according to the invention, through image acquisition and image processing and analysis, the shape data of the tobacco leaves can be obtained through calculation intuitively, the conversion from the image to the digitization is realized, the leaf form coefficients of the tobacco leaves can be reflected intuitively through big data statistics and analysis, the data management and classification and screening use are realized, and the quality refinement management and control in the production process of the thin cigarette is realized.
Drawings
Figure 1 is an artwork captured in an embodiment of the present invention,
figure 2 is an image after image processing according to the invention,
figure 3 is a graph of labeled tobacco leaves and their calculated results in an embodiment of the present invention,
FIG. 4 is a schematic diagram of the rates of large, medium and small tobacco leaves in the embodiment of the invention,
FIG. 5 is a distribution diagram of leaf profile coefficients of large, medium and small tobacco leaves in the embodiment of the invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
As shown in figure 1, the method for determining the shape of the tobacco flake for improving the production quality of the fine cigarette comprises the following operation steps:
step 1: tobacco leaf pretreatment: dispersing the tobacco leaves subjected to smoking on a transmission belt;
step 2: image acquisition: arranging a camera above the conveyor belt, and continuously collecting sample images;
and step 3: image processing: segmenting the image, extracting a tobacco target and removing interference;
the specific process of image segmentation processing is as follows: firstly, threshold segmentation and area screening are carried out on the enhanced image, whether tobacco leaves exist on the image or not is judged, and if yes, connected domains are carried out, so that each tobacco leaf is independent.
The specific method of the connected domain is as follows: in a binary image, the background region pixels have a value of 0 and the target region pixels have a value of 1, and assuming an image is scanned from left to right and from top to bottom, marking the pixel currently being scanned requires checking its connectivity to the several neighbor pixels scanned before it.
Taking the 4-pass case as an example, the image is scanned pixel by pixel, and if the current pixel value is 0, it is moved to the next scanning position, and if the current pixel value is 1, it is checked for two adjacent pixels to its left and top (these two pixels must be scanned before the current pixel). There are four cases of combinations of these two pixel values and labels to consider,
1. their pixel values are all 0. At which time the pixel is given a new label (indicating the start of a new connected domain),
2. only one pixel value in between them is 1. The label of the current pixel at this time is the label of the pixel value of 1,
3. they all have a pixel value of 1 and are labeled the same. The label of the current pixel is the label,
4. they have a pixel value of 1 and are labeled differently. The smaller value of which is assigned to the current pixel. And then back from the other edge to the starting pixel of the region. And executing the four judging steps respectively every time of backtracking.
This ensures that all connected domains are marked. And then different colors are given to different marks or the marks are added with frames to finish the marking, the same mark is the same connected domain, and the different marks are different connected domains. The number of labels is the number of connected domains. Generally, a connected domain represents an independent tobacco target.
The specific process for extracting the tobacco target comprises the following steps: separating a real tobacco leaf target from a background conveyor belt in an acquired image, specifically, based on color difference, representing colors of red, green and blue in the acquired image by RGB, wherein the colors of the conveyor belt are pure green, ideally, R is 0, G is Gx, B is 0, through practical analysis, the colors of the tobacco leaves are R, G is G, and B is B, wherein R, G, and B are not zero, R, G values of the tobacco leaves are closer, the B value of the tobacco leaves is far less than R, G values, subtracting the B value from all pixels of the image in sequence by the R value, and using the result as a processed image to obtain an enhanced image, so that the tobacco leaves on the image are more obviously compared with the conveyor belt, assuming that the value of a pixel point corresponding to the processed image is P (x, y), the tobacco leaves and the background of the conveyor belt can be separated by setting a threshold value for P (x, y), and the tobacco leaf target pixel is marked as 1, and marking the background pixel as 0, finishing the binarization process of the image and using the binarization process for subsequent image analysis processing.
And 4, step 4: and (3) calculating: calculating the area of the tobacco target and the length-width ratio of the minimum circumscribed rectangle;
the formula for calculating the leaf shape coefficient of the tobacco leaves is as follows:
wherein a represents the minimum circumscribed rectangle length of the tobacco leaf, b represents the minimum circumscribed rectangle width and a>＝b。
And numbering each tobacco leaf on the image before calculating the area of the tobacco leaf target and the minimum circumscribed rectangle, and then obtaining each area and the length-width ratio of the minimum circumscribed rectangle one by one.
And 5: and (4) classification: classifying according to the area size, and calculating the leaf profile coefficient of the tobacco leaves;
step 6: conversion: and calculating the mean value and distribution of the leaf-shaped coefficients.
A specific example is given below, the collected original distribution image of the tobacco leaves is shown in fig. 1, the original distribution image of the tobacco leaves is subjected to image processing to obtain images which are shown in fig. 2 and have clear tobacco leaf outlines and are respectively and independently obtained, the tobacco leaves in the images are numbered, then the areas of the tobacco leaves are calculated one by one, and classification is performed according to the areas of the tobacco leaves, wherein the classification is performed according to 5 classes, and the classification is shown in fig. 3 and is respectively larger than 25.40 × 25.40mm2、12.70X12.70mm2—25.40X25.40mm2、6.35X6.35mm2—12.70X12.70mm2、6.35X6.35mm2—2.36X2.36mm2、2.36X2.36mm2In the following, taking some tobacco leaves in fig. 3 as an example, the area of No. 2 and No. 3 tobacco leaves is 6.35X6.35mm2—12.70X12.70mm2In the range of lobules, the area of No. 1 and No. 4 tobacco leaves is 12.70X12.70mm2—25.40X25.40mm2In the range of the medium leaf, the area of No. 5, No. 6 and No. 7 tobacco leaves is more than 25.40X25.40mm2For large leaves, the leaf form factor, i.e. the precision, of each leaf is then calculated. Fig. 4 is a graph showing statistics of the area of tobacco leaves and the number of the tobacco leaves distributed on the large, medium and small leaves, and fig. 5 is a graph showing the distribution of the leaf profile coefficients of the large, medium and small leaves after calculation one by one.
FIG. 5 shows that the large statistical cardinality is about 1200, the medium statistical cardinality is about 5500, and the small statistical cardinality is 11000; FIG. 4 shows the large and medium flake rates of another index, and FIG. 5 shows the corresponding leaf profile coefficient indexes, which all show the data distribution during the measurement process.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (6)
1. The tobacco flake shape measuring method for improving the production quality of the fine cigarettes is characterized by comprising the following steps of: the method comprises the following operation steps:
step 1: tobacco leaf pretreatment: dispersing the tobacco leaves subjected to smoking on a transmission belt;
step 2: image acquisition: arranging a camera above the conveyor belt, and continuously collecting sample images;
and step 3: image processing: segmenting the image, extracting a tobacco target and removing interference;
and 4, step 4: and (3) calculating: calculating the area of the tobacco target and the length-width ratio of the minimum circumscribed rectangle;
and 5: and (4) classification: and classifying according to the area size, and calculating the leaf profile coefficient of the tobacco leaves.
Step 6: conversion: and calculating the mean value and distribution of the leaf-shaped coefficients.
2. The method for measuring a shape of a tobacco sheet for improving the quality of production of a fine cigarette according to claim 1, wherein: the formula for calculating the leaf profile coefficient of the tobacco leaf in the step 4 is as follows:
wherein a represents the minimum circumscribed rectangle length of the tobacco leaf, b represents the minimum circumscribed rectangle width and a>＝b。
3. The method for measuring a shape of a tobacco sheet for improving the quality of production of a fine cigarette according to claim 1, wherein: the method for extracting the tobacco leaf target in the step 3 is to separate the true tobacco leaf target in the collected image from the background conveyor belt, and specifically includes that based on color difference, RGB represents colors of red, green and blue in the collected image, the conveyor belt color is pure green, ideally, R is 0, G is Gx, and B is 0, through practical analysis, the tobacco leaf color is R, G is G, and B is B, wherein R, G, and B are not zero, and R, G values of the tobacco leaves are closer, the B value of the tobacco leaves is far smaller than R, G values, the B values are sequentially subtracted from all pixels of the image, and the result is used as the processed image, so that the tobacco leaves on the image are more obvious in comparison with the conveyor belt, assuming that the value of the corresponding pixel point of the processed image is P (x, y), and the tobacco leaves and the conveyor belt background can be separated by setting a threshold value for P (x, y), marking the target pixel of the tobacco leaf as 1 and marking the background pixel as 0, finishing the binarization process of the image for subsequent image analysis processing.
4. The method for measuring the shape of a tobacco sheet for improving the quality of production of fine cigarettes according to claim 3, wherein: in step 3, the specific process of image segmentation processing is as follows: firstly, threshold segmentation and area screening are carried out on the enhanced image, whether tobacco leaves exist on the image or not is judged, and if yes, connected domains are carried out, so that each tobacco leaf is independent.
5. The method for measuring the shape of a tobacco sheet for improving the quality of production of fine cigarettes according to claim 4, wherein: the specific method of the connected domain is as follows: in a binary image, the background region pixels have a value of 0 and the target region pixels have a value of 1, and assuming an image is scanned from left to right and from top to bottom, marking the pixel currently being scanned requires checking its connectivity to the several neighbor pixels scanned before it.
6. The method for measuring a shape of a tobacco sheet for improving the quality of production of a fine cigarette according to claim 1, wherein: and 4, numbering each tobacco leaf on the image before calculating the area of the tobacco leaf target and the minimum circumscribed rectangle in the step 4, and then obtaining the length, width and ratio of each area and the minimum circumscribed rectangle one by one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911134561.XA CN110930381A (en) | 2019-11-19 | 2019-11-19 | Tobacco flake shape determination method for improving production quality of fine cigarettes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911134561.XA CN110930381A (en) | 2019-11-19 | 2019-11-19 | Tobacco flake shape determination method for improving production quality of fine cigarettes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110930381A true CN110930381A (en) | 2020-03-27 |
Family
ID=69853594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911134561.XA Pending CN110930381A (en) | 2019-11-19 | 2019-11-19 | Tobacco flake shape determination method for improving production quality of fine cigarettes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930381A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050211257A1 (en) * | 2004-03-26 | 2005-09-29 | Hauni Primary Gmbh | Method and device for the separation of foreign bodies |
| CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
| CN105424709A (en) * | 2015-11-20 | 2016-03-23 | 陕西科技大学 | Fruit surface defect detection method based on image marking |
| CN105242568B (en) * | 2015-10-09 | 2018-02-13 | 东南大学 | Tobacco leaf based on Digital Image Processing accurately rejects control method |
| CN107991303A (en) * | 2017-12-18 | 2018-05-04 | 云南烟叶复烤有限责任公司 | A kind of leaf of beating based on double spectral techniques goes stalk quality detection device and detection method |
| CN109214397A (en) * | 2018-09-14 | 2019-01-15 | 郑州大学 | The dividing method of Lung neoplasm in a kind of lung CT image |
| CN110415181A (en) * | 2019-06-12 | 2019-11-05 | 勤耕仁现代农业科技发展(淮安)有限责任公司 | Flue-cured tobacco RGB image intelligent recognition and grade determination method under a kind of open environment |
-
2019
- 2019-11-19 CN CN201911134561.XA patent/CN110930381A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050211257A1 (en) * | 2004-03-26 | 2005-09-29 | Hauni Primary Gmbh | Method and device for the separation of foreign bodies |
| CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
| CN105242568B (en) * | 2015-10-09 | 2018-02-13 | 东南大学 | Tobacco leaf based on Digital Image Processing accurately rejects control method |
| CN105424709A (en) * | 2015-11-20 | 2016-03-23 | 陕西科技大学 | Fruit surface defect detection method based on image marking |
| CN107991303A (en) * | 2017-12-18 | 2018-05-04 | 云南烟叶复烤有限责任公司 | A kind of leaf of beating based on double spectral techniques goes stalk quality detection device and detection method |
| CN109214397A (en) * | 2018-09-14 | 2019-01-15 | 郑州大学 | The dividing method of Lung neoplasm in a kind of lung CT image |
| CN110415181A (en) * | 2019-06-12 | 2019-11-05 | 勤耕仁现代农业科技发展(淮安)有限责任公司 | Flue-cured tobacco RGB image intelligent recognition and grade determination method under a kind of open environment |
Non-Patent Citations (1)
| Title |
|---|
| 魏菊 锦郭莹: "重叠西红柿的识别及还原技术研究", 《数字技术与应用》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109269951B (en) | Image-based flotation tailing ash content, concentration and coarse particle content detection method | |
| CN110415181B (en) | Intelligent identification and grade judgment method for RGB (red, green and blue) images of flue-cured tobacco in open environment | |
| CN114549522B (en) | Textile quality detection method based on target detection | |
| CN108181316B (en) | Bamboo strip defect detection method based on machine vision | |
| CN109255757B (en) | Method for segmenting fruit stem region of grape bunch naturally placed by machine vision | |
| CN109712162B (en) | Cable character defect detection method and device based on projection histogram difference | |
| CN111860639B (en) | System and method for judging quantized flue-cured tobacco leaf curing characteristics | |
| CN115457037B (en) | Raw material quality inspection method for donkey-hide gelatin product production | |
| CN110687121B (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
| CN112330663B (en) | Method for detecting width of cut tobacco based on reducing circle by computer vision | |
| CN115994907B (en) | Intelligent processing system and method for comprehensive information of food detection mechanism | |
| Singh et al. | Machine vision system for tea quality determination-Tea Quality Index (TQI) | |
| Yro et al. | Cocoa beans fermentation degree assessment for quality control using machine vision and multiclass svm classifier | |
| CN110930381A (en) | Tobacco flake shape determination method for improving production quality of fine cigarettes | |
| CN112802074A (en) | Textile flaw detection method based on illumination correction and visual saliency characteristics | |
| CN105527241A (en) | Non-destructive method for detecting authenticity of raw cordyceps sinensis | |
| Bermúdez et al. | Image analysis for automatic feature estimation of the Mangifera indica fruit | |
| CN113838123B (en) | Method for measuring appearance characteristics of cut tobacco based on image processing | |
| CN110782453B (en) | Printed matter quality detection method based on image feature matching | |
| CN112529922A (en) | Method for accurately separating RGB image backgrounds of multicolor blades in open environment | |
| CN105466865A (en) | Nondestructive ophiocordyceps sinensis stroma adulteration detection method | |
| CN107403181B (en) | Lean meat and fat meat self-adaptive separation method based on Guangdong style sausage hyperspectral image | |
| CN105548037A (en) | Method for nondestructively detecting raw traditional Chinese medicinal materials | |
| CN112132212B (en) | Abnormal raw material tolerant wood raw material color selection method | |
| CN111563536A (en) | Bamboo strip color self-adaptive classification method based on machine learning |
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: 20200327 |