CN112949663B - Tobacco leaf baking control system and method based on image recognition - Google Patents
Tobacco leaf baking control system and method based on image recognition Download PDFInfo
- Publication number
- CN112949663B CN112949663B CN202110120000.5A CN202110120000A CN112949663B CN 112949663 B CN112949663 B CN 112949663B CN 202110120000 A CN202110120000 A CN 202110120000A CN 112949663 B CN112949663 B CN 112949663B
- Authority
- CN
- China
- Prior art keywords
- tobacco leaf
- image
- tobacco
- stage
- baking
- 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.)
- Active
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 320
- 238000000034 method Methods 0.000 title claims abstract description 58
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 241000208125 Nicotiana Species 0.000 claims abstract description 319
- 210000003462 vein Anatomy 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000004383 yellowing Methods 0.000 claims description 40
- 238000000605 extraction Methods 0.000 claims description 21
- 238000001035 drying Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 14
- 238000012360 testing method Methods 0.000 description 12
- 210000002435 tendon Anatomy 0.000 description 7
- 238000012512 characterization method Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000007791 dehumidification Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000037303 wrinkles Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B3/00—Preparing tobacco in the factory
- A24B3/10—Roasting or cooling tobacco
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Business, Economics & Management (AREA)
- Manufacturing & Machinery (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses a tobacco leaf baking control system and method based on image recognition, wherein the method comprises the following steps: acquiring a cured tobacco leaf image; preprocessing the tobacco leaf image to obtain a preprocessed image; extracting tobacco leaf characteristics from the pretreatment image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values; inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage; comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage. The invention can realize semi-intelligent production of tobacco leaves and reduce cost.
Description
Technical Field
The invention relates to a tobacco leaf baking control system and method based on image recognition, and belongs to the technical field of tobacco leaf baking.
Background
Tobacco curing is an important step in the tobacco production process, with the aim of promoting yellowing and drying of tobacco. The baking process generally divides the baking of tobacco leaves into three stages of yellowing stage, color fixing stage and tendon drying stage, and each stage is subdivided into a plurality of small stages. In the baking process, a baking engineer adjusts the temperature and humidity inside the baking room through observation, so that the baking engineer strictly follows the baking process rules, and the baking quality of tobacco leaves is ensured. However, the baking is performed through the experience of each baking engineer, so that the problems of great control difficulty, time and labor waste, more personnel and uneven baking quality are caused.
Disclosure of Invention
Based on the above, the invention provides an intelligent tobacco leaf baking control system and method based on image recognition.
The technical scheme of the invention is as follows: the tobacco leaf baking control method based on image recognition, wherein the method comprises the following steps:
acquiring a cured tobacco leaf image;
preprocessing the tobacco leaf image to obtain a preprocessed image;
extracting tobacco leaf characteristics from the pretreatment image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values;
inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage;
comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
Optionally, the tobacco leaf baking stage identification model is:
b＝a1*x1+a2*x2+a3*x3+a4*x4
in the formula, b is an actual measurement value of a current tobacco leaf baking stage, a1 is a tobacco leaf color characteristic value, x1 is a current stage tobacco leaf color weight, a2 is a main vein color characteristic value, x2 is a current stage main vein color weight, a3 is a tobacco leaf texture characteristic value, x3 is a current stage tobacco leaf texture characteristic weight, a4 is an area ratio characteristic value, and x4 is a current stage area bit characteristic weight.
Optionally, according to the tobacco leaf baking process curve, the tobacco leaf baking stage is divided into a yellowing initial stage, a yellowing early stage, a yellowing middle stage, a yellowing later stage, a fixation earlier stage, a fixation middle stage, a fixation later stage, a tendon drying earlier stage, a tendon drying middle stage and a tendon drying later stage, and the characteristic weights in the tobacco leaf baking stage identification model in each period are different.
Optionally, the preprocessing includes the steps of:
image denoising is carried out on the tobacco leaf image, so that a denoised image is obtained;
performing color correction on the denoising image to obtain a corrected image;
performing foreground refinement on the corrected image to obtain a refined image;
and carrying out foreground segmentation on the refined image to obtain a foreground image.
Optionally, the extraction method of the tobacco leaf color characteristic value comprises the following steps:
converting the preprocessed image from RGB space into HSV space;
and calculating the average value of each channel in the RGB space and the HSV space to obtain six values of R1, G1, B1, H1, S1 and V1 as the integral tobacco color characteristic value.
Optionally, the extraction method of the characteristic value of the main vein tobacco leaf comprises the following steps:
dividing the preprocessing image to obtain a stem image;
converting the stem image from RGB space to HSV space;
and calculating the average value of all channels of the main vein of the tobacco leaf in the RGB space and the HSV space to obtain six values of R2, G2, B2, H2, S2 and V2, wherein the six values are used as main vein color characteristic values.
Optionally, the extraction method of the tobacco leaf texture features comprises the following steps: and extracting texture characteristic values of tobacco leaves by adopting a gray level co-occurrence matrix algorithm, wherein the texture characteristic values comprise contrast, entropy, autocorrelation and energy.
Optionally, the extraction method of the tobacco leaf area ratio characteristic value comprises the following steps:
calculating the tobacco leaf area value at the current baking time of the tobacco leaves, and taking the tobacco leaf area value as the current tobacco leaf area value;
calculating the tobacco leaf area value at the initial tobacco leaf baking time, wherein the tobacco leaf area value is the initial tobacco leaf area value;
and calculating the ratio of the current tobacco leaf area value to the initial tobacco leaf area value to obtain a tobacco leaf area ratio characteristic value.
The invention also provides a tobacco leaf baking control system based on image recognition, wherein the system comprises:
an image acquisition module for: acquiring a cured tobacco leaf image;
an image processing module for: preprocessing the tobacco leaf image to obtain a preprocessed image;
the feature extraction module is used for: extracting tobacco leaf characteristics from the pretreatment image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values;
a stage calculation module for: inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage;
the control processing module is used for: comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
Optionally, the tobacco leaf baking stage identification model is:
b＝a1*x1+a2*x2+a3*x3+a4*x4
in the formula, b is an actual measurement value of a current tobacco leaf baking stage, a1 is a tobacco leaf color characteristic value, x1 is a current stage tobacco leaf color weight, a2 is a main vein color characteristic value, x2 is a current stage main vein color weight, a3 is a tobacco leaf texture characteristic value, x3 is a current stage tobacco leaf texture characteristic weight, a4 is an area ratio characteristic value, and x4 is a current stage area bit characteristic weight.
The beneficial effects of the invention are as follows: according to the invention, the main characteristics of tobacco leaves such as the color characteristics, the main vein color characteristics, the texture characteristics and the area ratio characteristics of the tobacco leaves are extracted, and the tobacco leaf baking stage identification model in the baking process is established, so that the baking stage of the tobacco leaves is predicted, and a basis is provided for semi-intelligent baking of the tobacco leaves. The invention can effectively solve the problems of the traditional baking method that the operation and control difficulty is high, time and labor are wasted, more personnel are needed and the baking quality is uneven in baking through the experience of each baking engineer.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
fig. 2 is a system configuration diagram of an embodiment of the present invention.
Detailed Description
The following detailed description of the present invention will provide further details in order to make the above-mentioned objects, features and advantages of the present invention more comprehensible. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the invention, which is therefore not limited to the specific embodiments disclosed below.
Example 1
Referring to fig. 1, the tobacco leaf baking control method based on image recognition according to the embodiment of the invention includes:
s1, acquiring a cured tobacco leaf image.
In the tobacco leaf baking process, a baking image of the tobacco leaf can be shot through the camera. Specifically, tobacco leaf images may be acquired every half minute, one minute, etc. After the tobacco leaf image is acquired, the tobacco leaf image can be transmitted to a tobacco leaf baking intelligent terminal.
The intelligent tobacco baking terminal is a control center of tobacco baking equipment, and a tobacco baking process curve can be input into the intelligent tobacco baking terminal, so that the baking of the tobacco is performed according to the tobacco baking process curve. Specifically, in the tobacco leaf baking process, the tobacco leaf baking intelligent terminal can detect actual temperature and humidity in the baking room through the dry and wet balls, can control heating of the baking room through heating equipment, and can control dehumidification of the baking room through dehumidification equipment such as a dehumidification window.
S2, preprocessing the tobacco leaf image to obtain a preprocessed image.
In image analysis, the quality of image directly affects the accuracy of the design and effect of the recognition algorithm, so that preprocessing is required before image analysis (feature extraction, recognition, etc.). The main purpose of image preprocessing is to eliminate irrelevant information in the image, recover useful real information, enhance the detectability of relevant information, simplify data to the maximum extent, and thereby improve the reliability of feature extraction, image segmentation, matching and recognition. Aiming at the field condition of tobacco leaf baking and the acquired real picture data, the embodiment provides an image preprocessing scheme comprising the main steps of image denoising, color correction, foreground refinement and foreground segmentation.
Specifically, the image preprocessing includes the steps of:
s21, carrying out image denoising on the tobacco leaf image to obtain a denoised image.
Image denoising refers to the process of reducing noise in a digital image. In reality, digital images are often affected by interference of imaging equipment and external environment noise and the like in the processes of digitizing and transmitting, and are called noisy images or noise images. Common image denoising algorithms include mean value filtering, median value filtering, and gaussian filtering. According to the embodiment, according to the actual condition of the acquired picture, the spiced salt noise in the tobacco leaf image is removed by using a median filtering algorithm, so that a clearer picture is obtained.
S22, carrying out color correction on the denoising image to obtain a corrected image;
the imaging environment of the curing barn is affected by the factors such as light, a camera and the like and is different, and the same tobacco leaves can have different colors in different curing barns and are obviously different from naked eyes. To prevent the influence of color distortion on image recognition, each curing barn uses standard color card color correction software to perform color correction and obtain correction parameters before use. And correcting the color of the tobacco leaf image by using the correction parameters.
S23, conducting foreground refinement on the corrected image to obtain a refined image;
foreground refinement, namely, foreground region refinement mainly aims at extracting effective regions to perform refined segmentation, and unnecessary interference information in the effective regions, such as some overexposed information, is eliminated. In this embodiment, firstly, difference calculation and statistics are performed on pixel values of each channel, some overexposed pixels are filtered, then, pixel values and pixel differences are counted in a neighborhood by means of LBP algorithm and VIBE algorithm ideas, extreme points in statistical results are filtered according to automatic threshold segmentation, and finally, each Blob is individually analyzed in a corresponding binary image, and small areas and interference areas are filtered.
S24, conducting foreground segmentation on the thinned image to obtain a foreground image.
The key area of the tobacco leaves in the picture is defined as a foreground area, and the interference of the background can be eliminated by extracting the characteristics on the basis of the foreground area, so that the robustness of the algorithm is improved. In the embodiment, the k-means clustering algorithm is used for clustering the pixels of the image, the class with the largest number of the clustered pixels is used as the class to which the foreground image belongs, the pixel segmentation threshold value is dynamically determined according to the differences of a plurality of clustering centers, and the original image pixels are segmented by the segmentation threshold value to obtain the foreground image.
And S3, extracting tobacco leaf characteristics of the preprocessed image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values.
The whole color of the tobacco leaves is changed from blue to yellow in the flue-cured tobacco process, and the whole color value of the tobacco leaves can be extracted as a main characteristic of identification. Specifically, the RGB average value of each channel of the foreground image can be used as the characteristic value of the color of the foreground image, meanwhile, the original image is converted into the HSV space from the RGB space by considering the representation capability of different color spaces on different levels of colors, the average value of each channel in the HSV space is calculated, and the calculated six values of R, G, B, H, S and V are used as the integral color characteristic value of the foreground image.
Optionally, the extraction method of the tobacco leaf color characteristic value comprises the following steps: converting the preprocessed image from RGB space into HSV space; and calculating the average value of each channel in the RGB space and the HSV space to obtain six values of R1, G1, B1, H1, S1 and V1, and taking the six values as the integral tobacco color characteristic value.
The color of the main part of the tobacco leaves is always changed (changed from blue to white to brown) in the flue-cured tobacco process, and the color value of the local position of the tobacco leaves can be extracted as a main characteristic of identification. And dividing each picture subjected to pretreatment operation by using an image semantic segmentation technology to obtain a stem image, and extracting the main vein tobacco leaf characteristics by using a method which is the same as the tobacco leaf color characteristic value.
Optionally, the extraction method of the characteristic value of the main vein tobacco leaf comprises the following steps: dividing the preprocessed image to obtain a stem image; converting the stem image from RGB space to HSV space; and calculating the average value of each channel of the main vein of the tobacco in the RGB space and the HSV space to obtain six values of R2, G2, B2, H2, S2 and V2, and taking the six values as the main vein color characteristic values.
In the tobacco leaf baking process, leaf surface texture is continuously changed due to dehydration and curling. The tobacco leaves are smooth and stretched when the tobacco leaves are baked, the wrinkles in the tobacco leaves are less, the longer the baking time is, the more the leaves are curled, and the more the wrinkles in the leaves are. The above-mentioned change process can be described by using texture features, and the texture feature extraction modes are various, and the embodiment adopts a gray level co-occurrence matrix algorithm to extract the texture feature values of tobacco leaves, wherein the texture feature values comprise contrast, entropy, autocorrelation and energy.
The following describes the gray level co-occurrence matrix:
the joint distribution between pixels having a certain spatial relationship is called a gray level co-occurrence matrix, denoted as pδ, and the gray level is L, and pδ is a matrix of lxl. The spatial positional relationship of a certain element pδ (i, j) is δ= (Dx, dy), and the horizontal direction is selected, i.e., δ=0. A number of parameters describing texture features may be calculated on the gray level co-occurrence matrix.
Contrast ratio: reflecting the sharpness of the image and the degree of texture groove depth. The deeper the texture grooves, the greater the contrast and the clearer the visual effect. The contrast of the target image can be calculated as follows.
Entropy: the information content contained in the image reflects the complexity of the image texture, and the larger the value is, the more complex the texture is.
The entropy of the target image can be calculated as follows.
Autocorrelation: reflecting the consistency of the image texture, the correlation value is large when the matrix element values are uniform.
The autocorrelation of the target image can be calculated as follows.
Energy: the sum of squares of the gray level co-occurrence matrix element values reflects the thickness degree of the image texture, and the larger the value is, the thicker the texture is. The energy of the target image can be calculated as follows.
In the baking process, the moisture in the leaves gradually runs off, and the whole volume of the tobacco leaves is continuously reduced to be stable. The ratio of the area of the current tobacco foreground to the area of the initial time foreground can express the water loss condition and the wrinkling degree of the tobacco. In this embodiment, the extraction method of the characteristic value of the tobacco leaf area ratio comprises the following steps: calculating the tobacco leaf area value at the current baking time of the tobacco leaves, and taking the tobacco leaf area value as the current tobacco leaf area value; calculating the tobacco leaf area value at the initial tobacco leaf baking time, wherein the tobacco leaf area value is the initial tobacco leaf area value; and calculating the ratio of the current tobacco leaf area value to the initial tobacco leaf area value to obtain a tobacco leaf area ratio characteristic value.
S4, inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage.
After the characteristic values of the color characteristic, the main vein color characteristic, the texture characteristic and the area ratio characteristic value of the tobacco are obtained, the characteristic values can be input into a recognition model of the tobacco baking stage, the stage of the current tobacco baking is calculated, and a basis is provided for the action of baking equipment.
The tobacco leaf baking stage identification model in the invention is as follows:
b＝a1*x1+a2*x2+a3*x3+a4*x4
in the formula, b is an actual measurement value of a current tobacco leaf baking stage, a1 is a tobacco leaf color characteristic value, x1 is a current stage tobacco leaf color weight, a2 is a main vein color characteristic value, x2 is a current stage main vein color weight, a3 is a tobacco leaf texture characteristic value, x3 is a current stage tobacco leaf texture characteristic weight, a4 is an area ratio characteristic value, and x4 is a current stage area bit characteristic weight.
In the baking test, the applicant finds that the color features, the main vein color features, the texture features, the shape features (area ratio) and the like of the tobacco leaves can well reflect the baking stage of the tobacco leaves. The construction of the tobacco leaf baking stage identification model is described in detail below:
at the beginning of the experiment, three batches of available data were collected using a simulated curing barn, wherein each batch of data contained 700 Zhang Yanshe images for a total of 2100 tobacco leaf images. The 2100 pictures are divided into 10 types according to actual temperature values, the 10 types correspond to 10 types of final classification, the initial stage of yellowing is 33 degrees, the early stage of yellowing is 38 degrees, the middle stage of yellowing is 40 degrees, the later stage of yellowing is 42 degrees, the earlier stage of fixation is 45 degrees, the middle stage of fixation is 48 degrees, the later stage of fixation is 51 degrees, the earlier stage of drying tendons is 54 degrees, the middle stage of drying tendons is 60 degrees, and the later stage of drying tendons is 68 degrees. Randomly extracting pictures from each category in each batch of data after classification according to the proportion of 10%, obtaining 70 pictures from each batch, taking a total of 210 pictures obtained from three batches as a test set of an algorithm, and taking the rest 630 pictures obtained by the same method as a training set of the algorithm. All references hereinafter to training sets and test sets refer to the training sets and test sets described herein.
1. Testing for tobacco color characteristics
Processing all pictures in the training set and the testing set by using an image preprocessing algorithm to obtain the training set and the testing set after preprocessing operation; all pictures in the training set and the test set use RGB color space, the RGB total average value of all tobacco pictures in the class is calculated according to the class of the pictures in the training set, the total average value of HSV of the training set pictures in the HSV color space is calculated on the basis of the obtained RGB total average value by using a conversion formula from the RGB color space to the HSV color space, and the calculated total average value of R1, G1, B1, H1, S1 and V1 is used as the overall color feature vector of each class of the tobacco pictures. The overall color characteristics of the obtained tobacco are shown in the following table.
Table 1 overall color characterization of tobacco
| Global color characterization | R1 | G1 | B1 | H1 | S1 | V1 |
| Yellowing (33 degree) | 28.98559 | 137.6638 | 124.4221 | 33.68539 | 211.0334 | 140.683 |
| Yellowing (38 degree) | 38.57855 | 140.9432 | 141.5237 | 29.62675 | 212.5255 | 146.98 |
| Yellowing (40 degree) | 78.55272 | 155.6312 | 167.4217 | 26.26303 | 148.1976 | 168.1518 |
| Yellowing (42 degree) | 107.3094 | 154.2366 | 154.3205 | 32.4003 | 96.32923 | 157.6146 |
| Fixed color (45 degree) | 106.5534 | 148.5321 | 151.1236 | 31.14159 | 93.39858 | 153.5185 |
| Fixed color (48 degree) | 104.6428 | 145.0961 | 149.0159 | 30.37808 | 95.19472 | 150.9826 |
| Fixed color (51 degree) | 103.4023 | 146.3611 | 151.2007 | 29.61248 | 99.35446 | 152.8581 |
| Dry rib (54 degree) | 102.2867 | 146.7036 | 151.5612 | 29.418 | 101.4612 | 153.1209 |
| Dry rib (60 degree) | 102.0156 | 146.9476 | 151.9219 | 29.22505 | 102.0616 | 153.2709 |
| Dry rib (68 degree) | 95.815 | 141.6778 | 148.2334 | 28.22364 | 109.2188 | 149.2211 |
As can be seen from Table 1, there is a relatively significant change in both RGB and HSV color space values from the yellow (33 degrees) to yellow (40 degrees) stage. And the RGB and HSV color space values tend to stabilize in the yellow (42 degrees) to dry (68 degrees) stage. Thus, the overall color can be an important feature to distinguish the yellowing (33 degrees) to yellowing (40 degrees) stages.
2. Testing for dominant vein color characteristics
And dividing each picture in the training set after the preprocessing operation by using an image semantic segmentation technology to obtain stem images, forming a stem image training set by all the obtained stem images, and calculating R, G, B, H, S, V total average values corresponding to different temperature stages on the stem image training set by using the same method for calculating the integral color characteristics as local color characteristic vectors of each category. The resulting dominant vein color profile is shown in the table below.
TABLE 2 Main pulse color characterization
| Local color characterization | R2 | G2 | B2 | H2 | S2 | V2 |
| Yellowing (33 degree) | 105.93025 | 154.492 | 136.6434 | 35.12191 | 97.3493 | 154.7116 |
| Yellowing (38 degree) | 104.33102 | 150.4674 | 142.0018 | 32.68671 | 93.7153 | 151.8783 |
| Yellowing (40 degree) | 108.145 | 156.4141 | 153.3125 | 32.9744 | 91.05542 | 160.7706 |
| Yellowing (42 degree) | 116.8869 | 154.2861 | 138.2176 | 38.59089 | 87.30432 | 155.7851 |
| Fixed color (45 degree) | 140.2987 | 167.4704 | 152.1403 | 53.1951 | 52.93957 | 168.6926 |
| Fixed color (48 degree) | 142.2516 | 168.5237 | 156.8918 | 49.38877 | 49.23513 | 169.7507 |
| Fixed color (51 degree) | 139.4277 | 169.2676 | 160.1516 | 45.20694 | 53.06079 | 170.7832 |
| Dry rib (54 degree) | 128.7576 | 159.7216 | 153.4286 | 41.24326 | 58.02462 | 161.6962 |
| Dry rib (60 degree) | 108.4789 | 132.7844 | 134.1655 | 34.86294 | 60.69841 | 137.4458 |
| Dry rib (68 degree) | 97.17059 | 122.5966 | 127.7227 | 30.35075 | 70.78837 | 129.7092 |
As can be seen from table 2, the change in RGB and HSV color space values is small in the yellow (33 degrees) to yellow (42 degrees) phase; the color value change of RGB and HSV color spaces is obvious in the stage of fixing color (45 degrees) to dry rib (68 degrees), which corresponds to the color of the rib part from bluish white to brown in the stage of fixing color and dry rib in actual flue-cured tobacco, so that the main pulse color can be used as an important feature for distinguishing the stage of fixing color (45 degrees) to dry rib (68 degrees).
3. Testing for tobacco leaf texture characteristics
And extracting the texture characteristics of the tobacco leaves by adopting a classical gray level co-occurrence matrix algorithm. And extracting four characteristic values (contrast, entropy, autocorrelation and energy) describing textures by using a gray level co-occurrence matrix algorithm for pictures in all training data, and calculating the average value of the four texture characteristic values in each category according to the category to which the tobacco leaves belong, wherein the average value is used as the texture characteristic value of each category. The texture feature values for each category are obtained as shown in the following table.
Table 3 tobacco leaf texture characteristics
As can be seen from Table 3, the values of each characteristic of the textures vary significantly from yellowing (33 degrees) to drying (68 degrees), and the texture characteristics can be used as characteristics for distinguishing all stages of flue-cured tobacco.
4. Testing for area ratio features
Because the calculation of the area ratio is related to the initial image of each flue-cured tobacco batch, the data in the training set are divided according to batches, the foreground area ratio of each batch of data is calculated respectively to obtain the shape characteristics of tobacco leaves in different batches, and then the value range of the area ratio of the data in the same stage in the training data is counted according to the state stage of the tobacco leaves. The final calculated shape characteristic data are shown in the following table.
TABLE 4 area bits characterization
| Sign of area bit | Area ratio |
| Yellowing (33 degree) | 1.0-0.95 |
| Yellowing (38 degree) | 0.94-0.85 |
| Yellowing (40 degree) | 0.87-0.81 |
| Yellowing (42 degree) | 0.80-0.75 |
| Fixed color (45 degree) | 0.76-0.74 |
| Fixed color (48 degree) | 0.76-0.75 |
| Fixed color (51 degree) | 0.76-0.74 |
| Dry rib (54 degree) | 0.75-0.74 |
| Dry rib (60 degree) | 0.76-0.74 |
| Dry rib (68 degree) | 0.76-0.73 |
From table 4, it can be obtained that the area ratio of the tobacco leaves tends to be stable (0.76-0.74) at the time of yellowing (42 degrees) to the time of fixing (45 degrees), and the various stages before the yellowing (42 degrees) are changed all the time, so the area ratio can be used as the characteristic for identifying the yellowing (33 degrees) to the yellowing (42 degrees) stages.
Through the test, the different baking stages of the tobacco can be identified by the color characteristics, the main vein color characteristics, the tobacco texture characteristics and the area ratio characteristics of the tobacco. And because the duty ratio of each characteristic in each baking stage is different, the weight of each characteristic in different stages can be set to be different, so as to more accurately identify and distinguish each baking stage. Meanwhile, the judging thresholds of the stages are different, and the specific formula is as described above.
Optionally, according to the tobacco leaf baking process curve, the tobacco leaf baking stage is divided into a yellowing initial stage, a yellowing early stage, a yellowing middle stage, a yellowing later stage, a fixation earlier stage, a fixation middle stage, a fixation later stage, a reinforcement drying earlier stage, a reinforcement drying middle stage and a reinforcement drying later stage, and the characteristic weights in the tobacco leaf baking stage identification model in each period are different. In one example, applicants have counted the following based on sets of experiments and experience:
table 5 weight values and threshold values for each feature at each stage
| Temperature (temperature) | Tobacco color weight | Main pulse color weight | Texture weight | Area weight | Threshold value |
| Yellowing (33 degree) | 0.5 | 0 | 0.25 | 0.25 | 0.6 |
| Yellowing (38 degree) | 0.5 | 0 | 0.25 | 0.25 | 0.67 |
| Yellowing (40 degree) | 0.5 | 0 | 0.25 | 0.25 | 0.76 |
| Yellowing (42 degree) | 0.5 | 0 | 0.25 | 0.25 | 0.79 |
| Fixed color (45 degree) | 0.5 | 0 | 0.25 | 0.25 | 0.85 |
| Fixed color (48 degree) | 0.4 | 0.1 | 0.4 | 0.1 | 0.85 |
| Fixed color (51 degree) | 0.4 | 0.1 | 0.4 | 0.1 | 0.86 |
| Dry rib (54 degree) | 0.4 | 0.1 | 0.4 | 0.1 | 0.87 |
| Dry rib (60 degree) | 0.4 | 0.1 | 0.4 | 0.1 | 0.91 |
| Dry rib (68 degree) | 0.4 | 0.1 | 0.4 | 0.1 | 0.92 |
Remarks: the threshold in the table is the set threshold in step S5.
S5, comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, triggering the tobacco leaf baking process to enter the next stage, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
Specifically, after the actual measurement value of the current tobacco leaf baking stage is calculated through the tobacco leaf baking stage identification model, the actual measurement value is compared with the set threshold value of the previous tobacco leaf baking stage. If the set threshold is not reached, the baking is still carried out according to the current stage process. If the set value is exceeded, the baking equipment is controlled to perform baking according to a tobacco baking process curve set in the next stage, such as temperature rise setting, humidity discharge and the like.
For the same batch of tobacco leaves, the applicant adopts the same curing process (the existing flue-cured tobacco intensive curing technology), wherein one adopts a curing engineer to observe and identify different curing stages, and adjusts, and the other adopts the method of the invention to identify different curing stages (the parameters of each stage are shown in table 5). After baking, the quality of the two kang tobacco leaves is compared with the appearance quality, the main chemical components and the sucking quality, and the quality of the two kang tobacco leaves is found to be almost the same.
According to the invention, the main characteristics of tobacco leaves such as the color characteristics, the main vein color characteristics, the texture characteristics and the area ratio characteristics of the tobacco leaves are extracted, and the tobacco leaf baking stage identification model in the baking process is established, so that the baking stage of the tobacco leaves is predicted, and a basis is provided for intelligent baking of the tobacco leaves. The invention can effectively solve the problems of the traditional baking method that the operation and control difficulty is high, time and labor are wasted, more personnel are needed and the baking quality is uneven in baking through the experience of each baking engineer.
Example two
Referring to fig. 2, a second embodiment of the present invention provides a tobacco leaf baking control system based on image recognition, where the system includes: an image acquisition module for: acquiring a cured tobacco leaf image; an image processing module for: preprocessing the tobacco leaf image to obtain a preprocessed image; the feature extraction module is used for: extracting tobacco leaf characteristics from the pretreatment image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values; a stage calculation module for: inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage; the control processing module is used for: comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
Since the device described in the second embodiment of the present invention is a device for implementing the method described in the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the device, and thus the detailed description thereof is omitted herein. All devices used in the method according to the first embodiment of the present invention are within the scope of the present invention.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (3)
1. The tobacco leaf baking control method based on image recognition, wherein the method comprises the following steps:
acquiring a cured tobacco leaf image;
preprocessing the tobacco leaf image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: image denoising is carried out on the tobacco leaf image, so that a denoised image is obtained; performing color correction on the denoising image to obtain a corrected image; performing foreground refinement on the corrected image to obtain a refined image; performing foreground segmentation on the refined image to obtain a foreground image;
extracting tobacco leaf characteristics from the preprocessed image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values, and the extraction method of the tobacco leaf color characteristic values comprises the following steps: converting the preprocessed image from RGB space into HSV space; calculating the average value of each channel in the RGB space and the HSV space to obtain six values of R1, G1, B1, H1, S1 and V1 as the integral tobacco color characteristic value; the extraction method of the main vein color characteristic value comprises the following steps: dividing the preprocessing image to obtain a stem image; converting the stem image from RGB space to HSV space; calculating the average value of each channel of the main vein of tobacco in the RGB space and the HSV space to obtain six values of R2, G2, B2, H2, S2 and V2, wherein the six values are used as main vein color characteristic values; the extraction method of the tobacco leaf texture features comprises the following steps: extracting texture characteristic values of tobacco leaves by adopting a gray level co-occurrence matrix algorithm, wherein the texture characteristic values comprise contrast, entropy, autocorrelation and energy; the extraction method of the tobacco leaf area ratio characteristic value comprises the following steps: calculating the tobacco leaf area value at the current baking time of the tobacco leaves, and taking the tobacco leaf area value as the current tobacco leaf area value; calculating the tobacco leaf area value at the initial tobacco leaf baking time, wherein the tobacco leaf area value is the initial tobacco leaf area value; calculating the ratio of the current tobacco leaf area value to the initial tobacco leaf area value, namely the characteristic value of the tobacco leaf area ratio;
inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage; the tobacco leaf baking stage identification model is as follows:
b=a1*x1+a2*x2+a3*x3+a4*x4
wherein b is an actual measurement value in a current tobacco baking stage, a1 is a tobacco color characteristic value, x1 is a current stage tobacco color weight, a2 is a main vein color characteristic value, x2 is a current stage main vein color weight, a3 is a tobacco texture characteristic value, x3 is a current stage tobacco texture characteristic weight, a4 is an area ratio characteristic value, and x4 is a current stage area ratio characteristic weight;
comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
2. The control method according to claim 1, wherein the tobacco baking stage is divided into an early stage of yellowing, an intermediate stage of yellowing, an late stage of yellowing, an early stage of fixation, an intermediate stage of fixation, an late stage of fixation, a pre-drying period, a mid-drying period, a post-drying period, and the respective feature weights in the tobacco baking stage identification model within each period are different according to a tobacco baking process curve.
3. A tobacco curing control system based on image recognition, wherein the system comprises:
an image acquisition module for: acquiring a cured tobacco leaf image;
an image processing module for: preprocessing the tobacco leaf image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: image denoising is carried out on the tobacco leaf image, so that a denoised image is obtained; performing color correction on the denoising image to obtain a corrected image; performing foreground refinement on the corrected image to obtain a refined image; performing foreground segmentation on the refined image to obtain a foreground image;
the feature extraction module is used for: extracting tobacco leaf characteristics from the preprocessed image to obtain tobacco leaf characteristic values, wherein the tobacco leaf characteristic values at least comprise tobacco leaf color characteristic values, main vein color characteristic values, tobacco leaf texture characteristic values and area ratio characteristic values, and the extraction method of the tobacco leaf color characteristic values comprises the following steps: converting the preprocessed image from RGB space into HSV space; calculating the average value of each channel in the RGB space and the HSV space to obtain six values of R1, G1, B1, H1, S1 and V1 as the integral tobacco color characteristic value; the extraction method of the main vein color characteristic value comprises the following steps: dividing the preprocessing image to obtain a stem image; converting the stem image from RGB space to HSV space; calculating the average value of each channel of the main vein of tobacco in the RGB space and the HSV space to obtain six values of R2, G2, B2, H2, S2 and V2, wherein the six values are used as main vein color characteristic values; the extraction method of the tobacco leaf texture features comprises the following steps: extracting texture characteristic values of tobacco leaves by adopting a gray level co-occurrence matrix algorithm, wherein the texture characteristic values comprise contrast, entropy, autocorrelation and energy; the extraction method of the tobacco leaf area ratio characteristic value comprises the following steps: calculating the tobacco leaf area value at the current baking time of the tobacco leaves, and taking the tobacco leaf area value as the current tobacco leaf area value; calculating the tobacco leaf area value at the initial tobacco leaf baking time, wherein the tobacco leaf area value is the initial tobacco leaf area value; calculating the ratio of the current tobacco leaf area value to the initial tobacco leaf area value, namely the characteristic value of the tobacco leaf area ratio;
a stage calculation module for: inputting the tobacco leaf characteristic values into a tobacco leaf baking stage identification model, and calculating actual measurement values of the current tobacco leaf baking stage; the tobacco leaf baking stage identification model is as follows:
b=a1*x1+a2*x2+a3*x3+a4*x4
wherein b is an actual measurement value in a current tobacco baking stage, a1 is a tobacco color characteristic value, x1 is a current stage tobacco color weight, a2 is a main vein color characteristic value, x2 is a current stage main vein color weight, a3 is a tobacco texture characteristic value, x3 is a current stage tobacco texture characteristic weight, a4 is an area ratio characteristic value, and x4 is a current stage area ratio characteristic weight;
the control processing module is used for: comparing the actual measurement value of the current tobacco leaf baking stage with a current tobacco leaf baking stage set threshold value, and triggering a tobacco leaf baking process to enter the next stage if the actual measurement value of the current tobacco leaf baking stage is larger than the current tobacco leaf baking stage set threshold value, and controlling baking equipment to bake according to a tobacco leaf baking process curve set in the next stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110120000.5A CN112949663B (en) | 2021-01-28 | 2021-01-28 | Tobacco leaf baking control system and method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110120000.5A CN112949663B (en) | 2021-01-28 | 2021-01-28 | Tobacco leaf baking control system and method based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949663A CN112949663A (en) | 2021-06-11 |
| CN112949663B true CN112949663B (en) | 2024-01-23 |
Family
ID=76238876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110120000.5A Active CN112949663B (en) | 2021-01-28 | 2021-01-28 | Tobacco leaf baking control system and method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949663B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114002977B (en) * | 2021-10-22 | 2023-12-08 | 珠海格力电器股份有限公司 | Control method and device of tobacco dryer unit, electronic equipment and storage medium |
| CN114304699A (en) * | 2021-12-27 | 2022-04-12 | 上海创和亿电子科技发展有限公司 | Method for extracting green and yellow ratio of primary flue-cured tobacco leaves |
| CN114931230B (en) * | 2022-05-13 | 2023-10-27 | 中国烟草总公司郑州烟草研究院 | Process execution index analysis characterization method for tobacco leaf baking process |
| CN115067529A (en) * | 2022-07-28 | 2022-09-20 | 青岛海尔空调器有限总公司 | Tobacco curing equipment and tobacco curing method |
| CN115316699B (en) * | 2022-07-29 | 2024-05-28 | 湖北文理学院 | Method and device for predicting and modulating dry and wet bulb temperature of tobacco leaf baking system |
| CN115281361A (en) * | 2022-08-23 | 2022-11-04 | 中国烟草总公司郑州烟草研究院 | Control method for tobacco leaf baking process |
| CN115969073A (en) * | 2023-01-16 | 2023-04-18 | 河南讯飞人工智能科技有限公司 | Baking stage determination method and device, electronic equipment, baking oven and storage medium |
| CN116434045B (en) * | 2023-03-07 | 2024-06-14 | 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) | Intelligent identification method for tobacco leaf baking stage |
| CN117894012B (en) * | 2024-03-12 | 2024-05-31 | 西安大业食品有限公司 | Machine vision-based mass cake baking stage identification method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0003775A1 (en) * | 1978-02-18 | 1979-09-05 | Hoechst Aktiengesellschaft | Car polish drying agent |
| CN104256882A (en) * | 2014-09-04 | 2015-01-07 | 国家烟草质量监督检验中心 | Method for measuring proportion of reconstituted tobacco in cut tobacco on basis of computer vision |
| CN106250896A (en) * | 2016-03-03 | 2016-12-21 | 上海创和亿电子科技发展有限公司 | The recognition methods of the positive and negative of online Nicotiana tabacum L. based on image collecting device |
| CN107358586A (en) * | 2017-07-06 | 2017-11-17 | 中山大学 | A kind of image enchancing method, device and equipment |
| CN110111263A (en) * | 2019-03-29 | 2019-08-09 | 中国地质大学（武汉） | A kind of tobacco planting based on image procossing instructs system |
| CN111274860A (en) * | 2019-11-08 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Machine vision-based online automatic tobacco leaf grade sorting identification method |
| CN111466605A (en) * | 2020-04-23 | 2020-07-31 | 贵州省烟草科学研究院 | Method, system and device for measuring yellowing and browning degree of tobacco leaf baking based on RGB value |
-
2021
- 2021-01-28 CN CN202110120000.5A patent/CN112949663B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0003775A1 (en) * | 1978-02-18 | 1979-09-05 | Hoechst Aktiengesellschaft | Car polish drying agent |
| CN104256882A (en) * | 2014-09-04 | 2015-01-07 | 国家烟草质量监督检验中心 | Method for measuring proportion of reconstituted tobacco in cut tobacco on basis of computer vision |
| CN106250896A (en) * | 2016-03-03 | 2016-12-21 | 上海创和亿电子科技发展有限公司 | The recognition methods of the positive and negative of online Nicotiana tabacum L. based on image collecting device |
| CN107358586A (en) * | 2017-07-06 | 2017-11-17 | 中山大学 | A kind of image enchancing method, device and equipment |
| CN110111263A (en) * | 2019-03-29 | 2019-08-09 | 中国地质大学（武汉） | A kind of tobacco planting based on image procossing instructs system |
| CN111274860A (en) * | 2019-11-08 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Machine vision-based online automatic tobacco leaf grade sorting identification method |
| CN111466605A (en) * | 2020-04-23 | 2020-07-31 | 贵州省烟草科学研究院 | Method, system and device for measuring yellowing and browning degree of tobacco leaf baking based on RGB value |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949663A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949663B (en) | Tobacco leaf baking control system and method based on image recognition | |
| CN112818827B (en) | Method for judging stage temperature control point in tobacco leaf baking process based on image recognition | |
| Yang et al. | Efficient illuminant estimation for color constancy using grey pixels | |
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| CN107341463B (en) | Face feature recognition method combining image quality analysis and metric learning | |
| CN107194317B (en) | Violent behavior detection method based on grid clustering analysis | |
| Vetal et al. | Tomato plant disease detection using image processing | |
| CN104732200B (en) | A kind of recognition methods of skin type and skin problem | |
| CN106023151B (en) | Tongue object detection method under a kind of open environment | |
| CN110717896A (en) | Plate strip steel surface defect detection method based on saliency label information propagation model | |
| CN110659586B (en) | Gait recognition method based on identity-preserving cyclic generation type confrontation network | |
| CN110458792B (en) | Method and device for evaluating quality of face image | |
| CN112633221B (en) | Face direction detection method and related device | |
| CN109242792B (en) | White balance correction method based on white object | |
| CN105184771A (en) | Adaptive moving target detection system and detection method | |
| CN109344758B (en) | Face recognition method based on improved local binary pattern | |
| CN107358635B (en) | Color morphological image processing method based on fuzzy similarity | |
| Díaz-Huerta et al. | Analysis and comparison of image processing and artificial intelligence algorithms to detect afb in pulmonary tuberculosis images | |
| Patki et al. | A review: Cotton leaf disease detection | |
| CN112270220B (en) | Sewing gesture recognition method based on deep learning | |
| Liang et al. | Applying Image Processing Technology to Face Recognition. | |
| Guang-Sheng et al. | Wood cell recognition using geodesic active contour and principal component analysis | |
| CN116824586B (en) | Image processing method and black garlic production quality online detection system applying same | |
| KR20210154593A (en) | Image based body composition analyzing apparatus and body composition analyzing method, and smart device using the same | |
| Balkys et al. | Segmenting the eye fundus images for identification of blood vessels |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |