CN116862456B - Traditional Chinese medicine production monitoring control system and method based on image processing - Google Patents
Traditional Chinese medicine production monitoring control system and method based on image processing Download PDFInfo
- Publication number
- CN116862456B CN116862456B CN202311129303.9A CN202311129303A CN116862456B CN 116862456 B CN116862456 B CN 116862456B CN 202311129303 A CN202311129303 A CN 202311129303A CN 116862456 B CN116862456 B CN 116862456B
- Authority
- CN
- China
- Prior art keywords
- value
- color
- chinese medicine
- leaf
- pixel
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 126
- 238000012544 monitoring process Methods 0.000 title claims abstract description 119
- 238000012545 processing Methods 0.000 title claims abstract description 61
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003384 imaging method Methods 0.000 claims abstract description 150
- 239000002994 raw material Substances 0.000 claims abstract description 105
- 230000000875 corresponding effect Effects 0.000 claims abstract description 79
- 230000007246 mechanism Effects 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 230000002596 correlated effect Effects 0.000 claims abstract description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 43
- 230000000007 visual effect Effects 0.000 claims description 29
- 238000012806 monitoring device Methods 0.000 claims description 19
- 241001604129 Polydactylus Species 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 16
- 230000001360 synchronised effect Effects 0.000 claims description 16
- 239000000463 material Substances 0.000 claims description 11
- 239000000470 constituent Substances 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000007480 spreading Effects 0.000 claims description 2
- 238000003892 spreading Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 8
- 230000000857 drug effect Effects 0.000 abstract description 8
- 241000238588 Balanus Species 0.000 description 14
- 230000001276 controlling effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 235000009008 Eriobotrya japonica Nutrition 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 241001092070 Eriobotrya Species 0.000 description 4
- 244000111489 Gardenia augusta Species 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 206010011224 Cough Diseases 0.000 description 3
- XEKOWRVHYACXOJ-UHFFFAOYSA-N Ethyl acetate Chemical compound CCOC(C)=O XEKOWRVHYACXOJ-UHFFFAOYSA-N 0.000 description 3
- 241000334154 Isatis tinctoria Species 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 229940126680 traditional chinese medicines Drugs 0.000 description 3
- KDCGOANMDULRCW-UHFFFAOYSA-N 7H-purine Chemical compound N1=CNC2=NC=NC2=C1 KDCGOANMDULRCW-UHFFFAOYSA-N 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 235000014435 Mentha Nutrition 0.000 description 2
- 241001072983 Mentha Species 0.000 description 2
- 244000246386 Mentha pulegium Species 0.000 description 2
- 235000016257 Mentha pulegium Nutrition 0.000 description 2
- 235000004357 Mentha x piperita Nutrition 0.000 description 2
- 238000004128 high performance liquid chromatography Methods 0.000 description 2
- 235000001050 hortel pimenta Nutrition 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 244000061508 Eriobotrya japonica Species 0.000 description 1
- 206010017553 Furuncle Diseases 0.000 description 1
- 235000018958 Gardenia augusta Nutrition 0.000 description 1
- 208000000616 Hemoptysis Diseases 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 241000207923 Lamiaceae Species 0.000 description 1
- 235000006679 Mentha X verticillata Nutrition 0.000 description 1
- 235000002899 Mentha suaveolens Nutrition 0.000 description 1
- 235000001636 Mentha x rotundifolia Nutrition 0.000 description 1
- LRHPLDYGYMQRHN-UHFFFAOYSA-N N-Butanol Chemical class CCCCO LRHPLDYGYMQRHN-UHFFFAOYSA-N 0.000 description 1
- 241000508269 Psidium Species 0.000 description 1
- 235000004789 Rosa xanthina Nutrition 0.000 description 1
- 241000220222 Rosaceae Species 0.000 description 1
- 241001107098 Rubiaceae Species 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000005251 capillar electrophoresis Methods 0.000 description 1
- 208000003796 chancre Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000002330 electrospray ionisation mass spectrometry Methods 0.000 description 1
- 208000001780 epistaxis Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 229930003935 flavonoid Natural products 0.000 description 1
- 150000002215 flavonoids Chemical class 0.000 description 1
- 235000017173 flavonoids Nutrition 0.000 description 1
- 208000014617 hemorrhoid Diseases 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000027939 micturition Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000002777 nucleoside Substances 0.000 description 1
- 150000003833 nucleoside derivatives Chemical class 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 239000013558 reference substance Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000012488 sample solution Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 230000004206 stomach function Effects 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 208000006379 syphilis Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000035922 thirst Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 230000008736 traumatic injury Effects 0.000 description 1
- 238000000870 ultraviolet spectroscopy Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to a traditional Chinese medicine production monitoring control system and method based on image processing, which belong to the field of image signal processing, wherein the system comprises: the intelligent analysis device is used for intelligently analyzing the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray based on the pixel values, the horizontal coordinate values and the vertical coordinate values of all pixel points of the barly-leaf imaging area and the pixel information corresponding to the standard barly-leaf pattern by adopting an artificial intelligent model; and the quality judging device is used for determining the quality grade of the barblade positively correlated with the average blade unfolding area. The invention also relates to a traditional Chinese medicine production monitoring control method based on image processing. According to the invention, aiming at the technical problems that the whole quality of the multi-blade raw materials is difficult to analyze and the drug effect of the related traditional Chinese medicine is difficult to judge, an image signal processing mechanism and an intelligent data processing mechanism are organically combined, so that the detection precision and efficiency of the quality of the part-by-part blade raw materials are ensured, and the technical problems are solved.
Description
Technical Field
The invention relates to the field of image signal processing, in particular to a traditional Chinese medicine production monitoring control system and method based on image processing.
Background
The image processing has a plurality of application fields, for example, the method can be used for judging the quality of various materials, particularly, the method can be used for capturing the visual data of the materials at the same time, and carrying out image recognition and image analysis on the visual data so as to obtain the quality information of the materials, and the method can be particularly applied to quality detection and production control of various traditional Chinese medicine materials.
In terms of traditional Chinese medicines, peppermint, gardenia leaves and balanus are all important leaf varieties required by human beings. Peppermint, also known as guava, or verdant, is a perennial herb of the genus Mentha of the family Labiatae, and is a perennial herb of the genus Mentha, which has a pair of leaves, a small light purple flower, a lip shape, and a variety of mountainous wetlands. The whole plant is fragrant, and is a fragrant crop with special economic value. Cape jasmine leaf and Chinese medicine. Is leaf of fructus Gardeniae of Gardenia of Rubiaceae, has effects of promoting blood circulation, relieving swelling, and clearing heat and toxic materials. Is used for treating traumatic injury, furuncle, hemorrhoid, and chancre. The folium Eriobotryae is leaf of Eriobotrya japonica belonging to Rosaceae, and is also called folium Eriobotryae and folium Citri Tangerinae. Has effects of clearing lung-heat, relieving cough, regulating stomach function, promoting urination, and quenching thirst, and can be used for treating lung heat phlegm cough, hemoptysis, epistaxis, stomach heat emesis.
Different types of leaf traditional Chinese medicines have different standards for determining the drug effect or quality, for example, the thicker the mint leaf is, the better the quality of the lobular variety is in the gardenia leaf, and for people who use the leaf for clearing lung and relieving cough and using the leaf more frequently, when producing traditional Chinese medicine medicines related to the leaf, under the premise of ensuring freshness, the older the selected balanus raw material is, the better the balanus raw material is, namely, the bigger the balanus raw material is, the better the drug effect can reach the expected value, so that the quality of the balanus raw material used for producing the traditional Chinese medicine before producing the traditional Chinese medicine related to the balanus raw material is needed to be judged, and the balanus raw material is used as one of determining factors of the drug effect of the produced traditional Chinese medicine.
For example, a quality evaluation method of loquat leaf medicinal material proposed by Chinese patent publication CN101354381a comprises the following steps: firstly, collecting more than 10 batches of loquat leaf medicinal materials, preparing a sample solution, preparing a reference substance solution, measuring by using a high performance liquid chromatography and a high performance capillary electrophoresis method, and finally analyzing by using traditional Chinese medicine fingerprint similarity calculation software. The invention has the advantages of simple and convenient method, stability, good precision, good repeatability and easy grasp, can grasp the variety and quality condition of the loquat leaves from the overall characteristic surface of the chromatograph on the same appearance, and can be used as one of the methods for evaluating the quality and identifying the authenticity of the loquat leaves.
For example, a quality detection method for dyers woad leaf as a traditional Chinese medicine is proposed in chinese patent publication CN101732392a, and the method comprises: extracting folium Isatidis with water, treating with ethanol, sequentially extracting with ethyl acetate and water saturated n-butanol, concentrating, and fixing volume to obtain fingerprint of folium Isatidis by electrospray mass spectrometry; determining the content of nucleoside and purine components in folium Isatidis by high performance liquid chromatography; the content of total flavonoids in the dyers woad leaf is measured by ultraviolet-visible spectrophotometry, and the quality of the dyers woad leaf can be evaluated by integrating the fingerprint spectrum and content measurement data. The quality detection method is accurate, quick, convenient and effective.
However, the above prior art does not relate to the identification of the leaf size of a specific balanus raw material, and does not provide a rapid and intelligent identification mechanism for the whole leaf size and the whole quality of a plurality of balanus raw materials, and meanwhile, the adoption of a manual leaf-by-leaf measurement mechanism and a simplified sampling measurement mechanism can have the defects of low efficiency and insufficient precision, so that the prior art still has the technical problems that the whole quality of each raw material consisting of a plurality of balanus raw materials is difficult to analyze and the drug effect of related traditional Chinese medicines is difficult to judge.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a traditional Chinese medicine production monitoring control system and method based on image processing, which can perform visual data acquisition and monitoring on each horizontally placed tray which is uniformly shaken and is fully paved with the barely leaf raw materials, obtain a barely leaf imaging area for subsequent intelligent analysis of the whole leaf size of each barly leaf raw material, and particularly, perform the intelligent analysis by adopting an artificial intelligent model which completes multiple learning, thereby organically combining an image signal processing mechanism and an intelligent data processing mechanism, ensuring the detection efficiency and precision of the quality of each barly leaf raw material, and providing valuable reference information for drug effect evaluation of related traditional Chinese medicine.
According to a first aspect of the present invention, there is provided a system for monitoring and controlling production of a Chinese medicine based on image processing, the system comprising:
the raw material pushing device is used for pushing a horizontally placed tray full of the barely leaf raw materials to the position right below the data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
the vision monitoring device is positioned right above the data acquisition station and is used for executing one vision data acquisition action of the data acquisition station after the raw material pushing device completes one pushing operation every time so as to acquire a traditional Chinese medicine monitoring picture;
the content stripping device is connected with the visual monitoring device and is used for detecting a barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
the information capturing device is used for acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the intelligent analysis device is respectively connected with the content stripping device and the information capturing device and is used for intelligently analyzing the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray by adopting an artificial intelligent model based on pixel information corresponding to each pixel point of the barely-leaf imaging area, each horizontal coordinate value and each vertical coordinate value and each standard barely-leaf pattern;
The quality judging device is connected with the intelligent analyzing device and is used for determining the quality grade of the Barbary leaves positively correlated with the received average leaf expansion area;
the artificial intelligence model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is proportional to the radius of the circle.
According to a second aspect of the present invention, there is provided a method of monitoring and controlling production of a Chinese medicine based on image processing, the method comprising the steps of:
pushing a horizontally placed tray full of barely leaf raw materials to the position right below a data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
a vision monitoring device positioned right above the data acquisition station is adopted to execute one-time vision data acquisition action of the data acquisition station so as to acquire a traditional Chinese medicine monitoring picture;
detecting a barely imaging region in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the artificial intelligent model intelligently analyzes the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray based on pixel information corresponding to each pixel value, each horizontal coordinate value and each vertical coordinate value of each pixel point of the barly-leaf imaging area;
Determining a barblade quality level positively associated with the received average blade deployment area;
the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is in direct proportion to the radius of the circle;
the tray that will be paved with the level of leaf raw materials and place is pushed to the data acquisition station under, the tray is circular tray just circular radius is fixed numerical value and includes: the fixed value is larger than or equal to a set radius threshold value;
wherein the color imaging characteristics of the barbus are a red-green component numerical range, a black-white component numerical range and a yellow-blue component numerical range in an LAB color space;
wherein, detecting the barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly comprises: taking the pixel points with color component values matched with the color imaging characteristics of the barely as the constituent pixel points of the barly imaging region, and taking the pixel points with color component values not matched with the color imaging characteristics of the barly imaging region as other pixel points outside the barly imaging region;
the identification of the pixel points, of which the color component values of the traditional Chinese medicine monitoring picture are matched with the color imaging characteristics of the barbus leaves, comprises the following steps: calculating a first color distance between a color component value of the traditional Chinese medicine monitoring picture and color imaging characteristics of the folium mori by using the following formula:
；
Wherein,representing the first color distance, +.>Representing the mean value of the range of values of the red and green components in the color imaging characteristics of said folium Bambusae,/for>Representing the red-green component value of the color component values of the traditional Chinese medicine monitoring picture, and the +.>Representing the mean value of the range of values of the black and white components in the color imaging characteristics of the folium Bambusae,/for>Representing black and white component values in the color component values of the traditional Chinese medicine monitoring picture>Representing the mean value of the numerical range of the yellow-blue component in the color imaging characteristics of the folium mori>Representing the yellow-blue component value in the color component values of the traditional Chinese medicine monitoring picture;
calculating a second color distance between the color imaging characteristics of the folium Bambusae and a mean value of the color imaging characteristics of the folium Bambusae;
based on the first color distance, performing distance adjustment on the second color distance by using the following formula to obtain a second adjustment distance:
；
wherein,representing said second adjustment distance, +.>Representing the second color distance, +.>Representing the first color distance;
respectively constructing a first curve between the first color distance and pixel points in the traditional Chinese medicine monitoring picture and a second curve between the second adjustment distance and pixel points corresponding to the color imaging characteristics of the folium mori;
Selecting a peak value from the first curve and the second curve; when the first color distance is smaller than the peak value, taking a pixel point corresponding to the first color distance in the traditional Chinese medicine monitoring picture as a pixel point, wherein the color component value of the traditional Chinese medicine monitoring picture is matched with the color imaging characteristic of the folium mori;
the peak value is a value of a first peak occurring in the same pixel number range in the first curve within the pixel number range of the first peak occurring in the second curve.
Thus, compared with the prior art, the invention has at least the following four substantial technical advances:
(1) Pushing a horizontally placed tray fully paved with the barely raw materials after the horizontal shaking is completed to the right below a data acquisition station so as to acquire visual data of a horizontal paving scene of the barly raw materials, and detecting a barly imaging area in an acquired monitoring picture based on the color imaging characteristics of the barly, so that key data is provided for the follow-up intelligent analysis of the overall blade size of the barly;
(2) Acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern as pixel information corresponding to the standard Ballow pattern, and intelligently analyzing the average blade unfolding area of the Ballow raw material currently placed by the tray based on each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the Ballow imaging area and the pixel information corresponding to the standard Ballow pattern by adopting an artificial intelligent model, so as to complete intelligent analysis of the whole blade size of the Ballow;
(3) After intelligently analyzing the average leaf unfolding area of the current-placed balanus raw material of the tray, determining the balanus quality grade positively correlated with the current-placed balanus raw material based on the average leaf unfolding area, and further realizing intelligent identification of the whole quality of the raw material in the traditional Chinese medicine production process;
(4) In order to ensure the reliability and stability of intelligent analysis of the artificial intelligent model, the following three measures are adopted: the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed; the number of learning operations is proportional to the radius of the circle of the tray; and in each learning operation executed on the convolutional neural network, taking the average leaf expansion area of the known barely-leaf raw materials placed by the tray for a certain time as output data of the convolutional neural network, and taking pixel information corresponding to a standard barely-leaf pattern and pixel values, horizontal coordinate values and vertical coordinate values respectively corresponding to pixel points of a corresponding barely-leaf imaging area when the barly-leaf raw materials are placed by the tray for a certain time as item-by-item input data of the convolutional neural network.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings, in which:
FIG. 1 is a technical flow chart of a system and method for monitoring and controlling the production of Chinese medicine based on image processing according to the present invention.
Fig. 2 is a schematic structural diagram of a monitoring and controlling system for producing Chinese medicine based on image processing according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a traditional Chinese medicine production monitoring control system based on image processing according to a second embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a monitoring control system for producing chinese medicine based on image processing according to a third embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a traditional Chinese medicine production monitoring control system based on image processing according to a fourth embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a monitoring control system for producing chinese medicine based on image processing according to a fifth embodiment of the present invention.
Fig. 7 is a flowchart showing steps of a method for controlling monitoring of production of a chinese medicine based on image processing according to a sixth embodiment of the present invention.
Detailed Description
As shown in fig. 1, a technical flowchart of a system and a method for monitoring and controlling the production of traditional Chinese medicine based on image processing according to the present invention is provided.
As shown in fig. 1, the specific technical process of the present invention is as follows:
The technical process is as follows: carrying out visual data acquisition and visual data processing on each part of the barely-raw materials with the overall quality to be identified so as to obtain a barely-imaging area of the barly-raw materials, and providing basic data for subsequent analysis of the overall quality;
specifically, each part of the barbus leaf raw material with the overall quality to be identified is a plurality of barbus leaves which are placed on a horizontally placed tray with a fixed size and are in a flat and full state after horizontal shaking is completed, and the tray is also a round tray and has a size large enough to reduce the number of times of overall quality judgment of the raw material of the blades as much as possible while the plurality of barbus leaves can be flat;
and specifically, a barely imaging area in a monitoring picture acquired based on the color imaging characteristics detection of barly can be selected, so that the obtained barly imaging area does not include the edge of the tray, but only includes a plurality of barly leaves which are in a tiled and full state after horizontal shaking is completed uniformly;
the technical flow is as follows: an artificial intelligent model for performing intelligent analysis of the unfolding area of the whole blades of the plurality of blades is constructed, and in order to ensure the reliability and the stability of the analysis result of the artificial intelligent model, the following measures are adopted:
Measure A: the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed;
measure B: the number of learning operations is proportional to the circular radius of the tray, so that different customization of artificial intelligent models for different trays is realized;
measure C: in each learning operation executed on the convolutional neural network, taking the average leaf expansion area of the known barely-leaf raw materials placed by the tray for a certain time as output data of the convolutional neural network, taking pixel information corresponding to a standard barely-leaf pattern and each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of a barely-leaf imaging area corresponding to the situation that the barly-leaf raw materials are placed by the tray for a certain time as input data of the convolutional neural network, and completing the learning operation, thereby ensuring the learning effect of each learning operation;
and the technical flow is as follows: an artificial intelligent model constructed by a second technical process is adopted, and the average blade unfolding area of a plurality of blades currently placed on the tray is intelligently analyzed based on each item of associated visual data of a blade imaging area and pixel information corresponding to a standard blade pattern, which are acquired by the first technical process;
Illustratively, each item of associated visual data of the barely imaged region is each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the barly imaged region, for example, the pixel value may be a gray value;
the technical process is as follows: determining the overall quality grade of the plurality of the currently placed barks of the tray based on the average blade unfolding area of the plurality of the currently placed barks of the tray obtained in the technical process three, so as to provide valuable reference information for the drug effect of the traditional Chinese medicine prepared by the subsequent barks;
specifically, the larger the average leaf expansion area of the plurality of the leaves currently placed in the tray is, the higher the overall quality grade of the plurality of the leaves currently placed in the tray is determined, so that the older the selected raw materials of the leaves are, the larger the raw materials of the leaves are, and the better the raw materials of the leaves are, so that the drug effect can reach the expected preparation characteristics of the Chinese medicine of the leaves.
The key points of the invention are as follows: the method comprises the steps of a targeted visual data acquisition mechanism and an image signal processing mechanism of the barely leaf raw material, customization of different artificial intelligence models of different trays, and organic combination of visual data acquisition processing and intelligent data processing.
Next, the system and method for monitoring and controlling the production of a Chinese medicine based on image processing of the present invention will be specifically described by way of example.
Example 1
Fig. 2 is a schematic structural diagram of a monitoring and controlling system for producing Chinese medicine based on image processing according to an embodiment of the present invention.
As shown in fig. 2, the image processing-based traditional Chinese medicine production monitoring control system comprises the following components:
the raw material pushing device is used for pushing a horizontally placed tray full of the barely leaf raw materials to the position right below the data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
for example, the radius of the circular tray needs to reach a larger value, so that on one hand, the blades of each blade can be guaranteed to be tiled, and on the other hand, the number of times of judging the overall quality of the blade raw material can be reduced;
the vision monitoring device is connected with the raw material pushing device and is positioned right above the data acquisition station, and is used for executing one vision data acquisition action of the data acquisition station after the raw material pushing device completes one pushing operation every time so as to acquire traditional Chinese medicine monitoring picture information;
for example, the vision monitoring device may be selectively built with an image sensor, the image sensor may be selected as a CCD sensor or a CMOS sensor, and the vision monitoring device may be further selectively built with a lens, an optical filter, and a flexible circuit board;
In particular, the optical filter may be disposed between the lens and the image sensor, the flexible circuit board for providing power supply to the image sensor;
the content stripping device is connected with the visual monitoring device and is used for detecting a barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
alternatively, the gray level imaging characteristic of the barely leaf can be used for detecting the barly leaf imaging area in the traditional Chinese medicine monitoring picture, and compared with the gray level imaging characteristic of the barly leaf, the detection effect accuracy of the color imaging characteristic of the barly leaf is higher;
the information capturing device is used for acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the intelligent analysis device is respectively connected with the content stripping device and the information capturing device and is used for intelligently analyzing the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray by adopting an artificial intelligent model based on pixel information corresponding to each pixel point of the barely-leaf imaging area, each horizontal coordinate value and each vertical coordinate value and each standard barely-leaf pattern;
For example, the intelligent analysis device, the content stripping device and the information capturing device may be implemented by using SOC chips of different models;
specifically, a numerical simulation mode can be selected to be used for realizing a data processing process of intelligently analyzing the average blade unfolding area of the current blade raw material placed by the tray based on pixel information corresponding to each pixel value, each horizontal coordinate value and each vertical coordinate value of the blade imaging area and the standard blade pattern of the artificial intelligent model;
the quality judging device is connected with the intelligent analyzing device and is used for determining the quality grade of the Barbary leaves positively correlated with the received average leaf expansion area;
the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is in direct proportion to the radius of the circle;
illustratively, the artificial intelligence model is a convolutional neural network after completion of a plurality of learning operations and the number of learning operations is proportional to the radius of the circle comprises: the radius of the circle is 50 cm, the number of learning operations is 100, the radius of the circle is 60 cm, the number of learning operations is 120, and the radius of the circle is 80 cm, and the number of learning operations is 160;
The tray that will be paved with the level of leaf raw materials and place is pushed to the data acquisition station under, the tray is circular tray just circular radius is fixed numerical value and includes: the fixed value is larger than or equal to a set radius threshold value;
wherein the color imaging characteristics of the barbus are a red-green component numerical range, a black-white component numerical range and a yellow-blue component numerical range in an LAB color space;
wherein, detecting the barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly comprises: taking the pixel points with color component values matched with the color imaging characteristics of the barely as the constituent pixel points of the barly imaging region, and taking the pixel points with color component values not matched with the color imaging characteristics of the barly imaging region as other pixel points outside the barly imaging region;
the identification of the pixel points, of which the color component values of the traditional Chinese medicine monitoring picture are matched with the color imaging characteristics of the barbus leaves, comprises the following steps: calculating a first color distance between a color component value of the traditional Chinese medicine monitoring picture and color imaging characteristics of the folium mori by using the following formula:
；
Wherein,representing the first color distance, +.>Representing the mean value of the range of values of the red and green components in the color imaging characteristics of said folium Bambusae,/for>Representing the red-green component value of the color component values of the traditional Chinese medicine monitoring picture, and the +.>Representing the mean value of the range of values of the black and white components in the color imaging characteristics of the folium Bambusae,/for>Representing black and white component values in the color component values of the traditional Chinese medicine monitoring picture>Representing the mean value of the numerical range of the yellow-blue component in the color imaging characteristics of the folium mori>Representing the yellow-blue component value in the color component values of the traditional Chinese medicine monitoring picture;
calculating a second color distance between the color imaging characteristics of the folium Bambusae and a mean value of the color imaging characteristics of the folium Bambusae;
based on the first color distance, performing distance adjustment on the second color distance by using the following formula to obtain a second adjustment distance:
；
wherein,representing said second adjustment distance, +.>Representing the second color distance, +.>Representing the first color distance;
respectively constructing a first curve between the first color distance and pixel points in the traditional Chinese medicine monitoring picture and a second curve between the second adjustment distance and pixel points corresponding to the color imaging characteristics of the folium mori;
Selecting a peak value from the first curve and the second curve; when the first color distance is smaller than the peak value, taking a pixel point corresponding to the first color distance in the traditional Chinese medicine monitoring picture as a pixel point, wherein the color component value of the traditional Chinese medicine monitoring picture is matched with the color imaging characteristic of the folium mori;
the peak value is a value of a first peak occurring in the same pixel number range in the first curve within the pixel number range of the first peak occurring in the second curve.
Example two
Fig. 3 is a schematic structural diagram of a traditional Chinese medicine production monitoring control system based on image processing according to a second embodiment of the present invention.
As shown in fig. 3, unlike the embodiment in fig. 2, the image processing-based traditional Chinese medicine production monitoring control system further includes the following components:
the repeated learning device is connected with the intelligent analysis device and is used for performing repeated learning operation on the convolutional neural network so as to obtain the convolutional neural network after the repeated learning operation is finished and output the convolutional neural network as the artificial intelligent model;
for example, a MATLAB tool box can be selected to complete multiple learning operations on the convolutional neural network, so as to obtain a convolutional neural network after the multiple learning operations are completed and serve as simulation and test processing of the artificial intelligent model output;
Wherein, carry out many times of learning operations to convolutional neural network to obtain convolutional neural network after accomplishing many times of learning operations and export as artificial intelligence model includes: in each learning operation executed on the convolutional neural network, taking the average leaf expansion area of the known balanophyll raw material which is placed by the tray for a certain time as output data of the convolutional neural network, taking pixel information corresponding to a standard balanophyll pattern and each pixel value, each horizontal coordinate value and each vertical coordinate value which are respectively corresponding to each pixel point of a balanophyll imaging area corresponding to the condition that the tray is placed by the balanophyll raw material for a certain time as item-by-item input data of the convolutional neural network, and executing the learning operation;
wherein the output data of the convolutional neural network, which is obtained by taking the average leaf spread area of the known balanobal leaf raw material in which the tray is placed a certain time, comprises: manually measuring the expansion area of each blade of the raw material of the known blade placed in the past of the tray to obtain measured area data, and performing average processing on the measured area data to obtain the average expansion area of each blade of the raw material of the known blade placed in the past of the tray;
Wherein, the process of each learning operation performed on the convolutional neural network comprises: carrying out gray scale identification on the input data to obtain gray scale pixel points; performing binarization processing on the gray pixel points to obtain binarized pixel points; performing edge detection on the binarized pixel points to obtain edge pixel points; based on the edge pixel points, the average blade deployment area is calculated using the following formula:
；
wherein,representing the average leaf spreading area, i representing the i-th leaf area of the leaf imaging areas corresponding to the standard leaf pattern and the tray when the leaf raw material is placed for a certain time, and @ being the leaf area of the leaf imaging area corresponding to the tray when the leaf raw material is placed for a certain time>Representing the total number of imaging areas of the leaves corresponding to the standard leaf pattern and the tray when the leaf material is placed for a certain time before, and ∈>Represents the total number of pixels in the ith lobe region, +.>Representing the number of pixels in the standard size grid in the ith barely leaf region, +.>Representing the area of a standard size grid within the ith barely region.
Example III
Fig. 4 is a schematic structural diagram of a monitoring control system for producing chinese medicine based on image processing according to a third embodiment of the present invention.
As shown in fig. 4, unlike the embodiment in fig. 3, the image processing-based traditional Chinese medicine production monitoring control system further includes the following components:
The uniform shaking device is arranged at the front end of the raw material pushing device and is used for carrying out uniform shaking operation in the horizontal direction on a horizontally placed tray full of the barely leaf raw material and conveying the tray subjected to the uniform shaking operation to a station where the raw material pushing device is located;
the uniform shaking device comprises a shaking executing unit, a shaking control unit and a control unit, wherein the shaking executing unit is used for carrying out uniform shaking operation in the horizontal direction on a horizontally placed tray fully paved with the barely leaf raw materials at a set frequency;
illustratively, uniformly shaking horizontally placed trays filled with the balanus raw material at a set frequency includes: uniformly shaking the horizontally placed tray fully paved with the barely leaf raw materials in the horizontal direction within a fixed time period at a set frequency;
the uniform shaking device further comprises a pushing execution unit, and the pushing execution unit is used for conveying the tray subjected to uniform shaking operation to a station where the raw material pushing device is located.
Example IV
Fig. 5 is a schematic structural diagram of a traditional Chinese medicine production monitoring control system based on image processing according to a fourth embodiment of the present invention.
As shown in fig. 5, unlike the embodiment in fig. 3, the image processing-based traditional Chinese medicine production monitoring control system further includes the following components:
The synchronous driving mechanism is respectively connected with the raw material pushing device and the visual monitoring device and is used for realizing synchronous driving control of pushing operation of the raw material pushing device and visual data acquisition action of the data acquisition station;
for example, a CPLD device or an FPGA device may be selected to implement the synchronous drive;
specifically, when the CPLD device is adopted to realize the synchronous driving mechanism, the programming design of the CPLD device is executed by using VHDL language;
the synchronous driving control for realizing the pushing operation of the raw material pushing device and the visual data acquisition action of the data acquisition station comprises the following steps: the synchronous driving mechanism is used for sending a monitoring trigger signal to the visual monitoring device after detecting that the raw material pushing device completes one pushing operation, so as to complete the triggering of one visual data acquisition action of the data acquisition station;
the synchronous driving mechanism is used for sending a monitoring trigger signal to the visual monitoring device after each time the raw material pushing device completes one pushing operation, so as to complete the triggering of one visual data acquisition action of the data acquisition station, and the synchronous driving mechanism comprises the following steps: and the synchronous driving mechanism adopts the falling edge of the rectangular wave to complete the triggering of one-time visual data acquisition action of the data acquisition station.
Example five
Fig. 6 is a schematic structural diagram of a monitoring control system for producing chinese medicine based on image processing according to a fifth embodiment of the present invention.
As shown in fig. 6, unlike the embodiment in fig. 5, the image processing-based traditional Chinese medicine production monitoring control system further includes the following components:
the instant display device is connected with the quality judging device and is used for receiving and instant displaying the character string information corresponding to the quality grade of the barbus leaves;
for example, an LED display array, an LCD display array, or a liquid crystal display screen may be selected to implement the instant display device;
the parameter storage device is connected with the intelligent analysis device and used for storing various model parameters of the artificial intelligent model;
for example, a FLASH memory device, a dynamic memory device, or an MMC memory device may be selected to implement the parameter memory device.
Next, detailed descriptions of various embodiments of the present invention will be continued.
In the image processing-based traditional Chinese medicine production monitoring control system according to various embodiments of the present invention:
the method for forming the pixel points of the imaging area of the folium Bambusae by using the pixel points with the color component values matched with the color imaging characteristics of the folium Bambusae in the traditional Chinese medicine monitoring picture comprises the following steps: when a red-green component value, a black-white component value and a yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture in an LAB color space are respectively in a red-green component value range, a black-white component value range and a yellow-blue component value range, judging that the pixel point is a single component pixel point of a Ballow imaging area;
Alternatively, a CMYK color space may be selected to replace the LAB color space to complete a single constituent pixel of the pixel as a barely imaged region;
for example, the method for forming the pixel point of the imaging area of the folium Bambusae by using the pixel point with the color component value matched with the color imaging characteristic of the folium Bambusae in the traditional Chinese medicine monitoring picture comprises the following steps: when a cyan component value, a magenta component value, a yellow component value and a black component value of a pixel point in the traditional Chinese medicine monitoring picture are respectively in a cyan component value range, a magenta component value range, a yellow component value range and a black component value range in a CMYK color space, judging that the pixel point is a single constituent pixel point of a barely imaging region;
wherein when the red-green component value, the black-white component value and the yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture under the LAB color space are respectively in the red-green component value range, the black-white component value range and the yellow-blue component value range, the judgment that the pixel point is a single constituent pixel point of the Baye imaging region comprises: the value of any one of the red-green component value, the black-white component value and the yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture in the LAB color space is between 0 and 255.
And in the image processing-based traditional Chinese medicine production monitoring control system according to various embodiments of the present invention:
each pixel value corresponding to each pixel point of the standard Ballow pattern respectively, and each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern are obtained, and the pixel information output corresponding to the standard Ballow pattern comprises: each pixel value corresponding to each pixel point of the standard Ballow pattern is each gray value corresponding to each pixel point of the standard Ballow pattern;
wherein, each pixel value that each pixel point of the standard Ballow pattern corresponds to respectively and obtain each horizontal coordinate value and each vertical coordinate value that each pixel point of the standard Ballow pattern corresponds to respectively, and regard as the pixel information output that the standard Ballow pattern corresponds to still include: the standard barely pattern is an imaged image comprising only a single standard shape of barly;
wherein, each pixel value that each pixel point of the standard Ballow pattern corresponds to respectively and obtain each horizontal coordinate value and each vertical coordinate value that each pixel point of the standard Ballow pattern corresponds to respectively, and regard as the pixel information output that the standard Ballow pattern corresponds to still include: in the standard Barballon pattern, the pixel point at the lower right corner is taken as the origin of a two-dimensional coordinate system, the pixel at the bottommost acts as the forward direction of the horizontal coordinate axis of the two-dimensional coordinate system, and the pixel example at the rightmost side is taken as the forward direction of the vertical coordinate axis of the two-dimensional coordinate system, so that the two-dimensional coordinate system is established.
Example six
Fig. 7 is a flowchart showing steps of a method for controlling monitoring of production of a chinese medicine based on image processing according to a sixth embodiment of the present invention.
As shown in fig. 7, the method for monitoring and controlling the production of traditional Chinese medicine based on image processing according to the sixth embodiment of the present invention specifically includes the following steps:
pushing a horizontally placed tray full of barely leaf raw materials to the position right below a data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
for example, the radius of the circular tray needs to reach a larger value, so that on one hand, the blades of each blade can be guaranteed to be tiled, and on the other hand, the number of times of judging the overall quality of the blade raw material can be reduced;
a vision monitoring device positioned right above the data acquisition station is adopted to execute one-time vision data acquisition action of the data acquisition station so as to acquire a traditional Chinese medicine monitoring picture;
for example, the vision monitoring device may be selectively built with an image sensor, the image sensor may be selected as a CCD sensor or a CMOS sensor, and the vision monitoring device may be further selectively built with a lens, an optical filter, and a flexible circuit board;
in particular, the optical filter may be disposed between the lens and the image sensor, the flexible circuit board for providing power supply to the image sensor;
Detecting a barely imaging region in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
alternatively, the gray level imaging characteristic of the barely leaf can be used for detecting the barly leaf imaging area in the traditional Chinese medicine monitoring picture, and compared with the gray level imaging characteristic of the barly leaf, the detection effect accuracy of the color imaging characteristic of the barly leaf is higher;
acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the artificial intelligent model intelligently analyzes the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray based on pixel information corresponding to each pixel value, each horizontal coordinate value and each vertical coordinate value of each pixel point of the barly-leaf imaging area;
specifically, a numerical simulation mode can be selected to realize a data processing process of intelligently analyzing the average blade unfolding area of the current-placed barely raw material of the tray by adopting an artificial intelligent model based on each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the barely imaging area and pixel information corresponding to a standard barely pattern;
Determining a barblade quality level positively associated with the received average blade deployment area;
the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is in direct proportion to the radius of the circle;
illustratively, the artificial intelligence model is a convolutional neural network after completion of a plurality of learning operations and the number of learning operations is proportional to the radius of the circle comprises: the radius of the circle is 50 cm, the number of learning operations is 100, the radius of the circle is 60 cm, the number of learning operations is 120, and the radius of the circle is 80 cm, and the number of learning operations is 160;
the tray that will be paved with the level of leaf raw materials and place is pushed to the data acquisition station under, the tray is circular tray just circular radius is fixed numerical value and includes: the fixed value is larger than or equal to a set radius threshold value;
wherein the color imaging characteristics of the barbus are a red-green component numerical range, a black-white component numerical range and a yellow-blue component numerical range in an LAB color space;
wherein, detecting the barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly comprises: taking the pixel points with color component values matched with the color imaging characteristics of the barely as the constituent pixel points of the barly imaging region, and taking the pixel points with color component values not matched with the color imaging characteristics of the barly imaging region as other pixel points outside the barly imaging region;
The identification of the pixel points, of which the color component values of the traditional Chinese medicine monitoring picture are matched with the color imaging characteristics of the barbus leaves, comprises the following steps: calculating a first color distance between a color component value of the traditional Chinese medicine monitoring picture and color imaging characteristics of the folium mori by using the following formula:
；
wherein,representing the first color distance, +.>Representing the mean value of the range of values of the red and green components in the color imaging characteristics of said folium Bambusae,/for>Representing the red-green component value of the color component values of the traditional Chinese medicine monitoring picture, and the +.>Representing the mean value of the range of values of the black and white components in the color imaging characteristics of the folium Bambusae,/for>Representing black and white component values in the color component values of the traditional Chinese medicine monitoring picture>Representing the mean value of the numerical range of the yellow-blue component in the color imaging characteristics of the folium mori>Representing the yellow-blue component value in the color component values of the traditional Chinese medicine monitoring picture;
calculating a second color distance between the color imaging characteristics of the folium Bambusae and a mean value of the color imaging characteristics of the folium Bambusae;
based on the first color distance, performing distance adjustment on the second color distance by using the following formula to obtain a second adjustment distance:
；
Wherein,representing said second adjustment distance, +.>Representing the second color distance, +.>Representing the first color distance;
respectively constructing a first curve between the first color distance and pixel points in the traditional Chinese medicine monitoring picture and a second curve between the second adjustment distance and pixel points corresponding to the color imaging characteristics of the folium mori;
selecting a peak value from the first curve and the second curve; when the first color distance is smaller than the peak value, taking a pixel point corresponding to the first color distance in the traditional Chinese medicine monitoring picture as a pixel point, wherein the color component value of the traditional Chinese medicine monitoring picture is matched with the color imaging characteristic of the folium mori;
the peak value is a value of a first peak occurring in the same pixel number range in the first curve within the pixel number range of the first peak occurring in the second curve.
In addition, the present invention may further incorporate the following technical matters to further demonstrate the prominent essential features of the present invention:
the intelligent analysis of the average blade unfolding area of the current-placed barely raw material of the tray based on the pixel information corresponding to each pixel value, each horizontal coordinate value and each vertical coordinate value of each pixel point of the barely imaging area by adopting an artificial intelligent model comprises the following steps: taking pixel values, horizontal coordinate values and vertical coordinate values corresponding to pixel points of a Barbary imaging area and pixel information corresponding to a standard Barbary pattern as item-by-item input data of the artificial intelligent model, and executing the artificial intelligent model to obtain an average blade unfolding area of the Barbary raw material currently placed by the tray and output by the artificial intelligent model;
Wherein, regarding the pixels of the traditional Chinese medicine monitoring picture, which have color component values not matched with the color imaging characteristics of the folium Bambusae, as other pixels outside the folium Bambusae imaging area comprises: and judging that one pixel point in the traditional Chinese medicine monitoring picture is a single other pixel point outside a barely imaging area when the red-green component value of the pixel point in the LAB color space is outside a red-green component value range, the black-white component value is outside a black-white component value range or the yellow-blue component value is outside a yellow-blue component value range.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (10)
1. A traditional Chinese medicine production monitoring control system based on image processing, characterized in that the system comprises:
the raw material pushing device is used for pushing a horizontally placed tray full of the barely leaf raw materials to the position right below the data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
the vision monitoring device is positioned right above the data acquisition station and is used for executing one vision data acquisition action of the data acquisition station after the raw material pushing device completes one pushing operation every time so as to acquire a traditional Chinese medicine monitoring picture;
The content stripping device is connected with the visual monitoring device and is used for detecting a barely imaging area in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
the information capturing device is used for acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the intelligent analysis device is respectively connected with the content stripping device and the information capturing device and is used for intelligently analyzing the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray by adopting an artificial intelligent model based on pixel information corresponding to each pixel point of the barely-leaf imaging area, each horizontal coordinate value and each vertical coordinate value and each standard barely-leaf pattern;
the quality judging device is connected with the intelligent analyzing device and is used for determining the quality grade of the Barbary leaves positively correlated with the received average leaf expansion area;
the artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is directly related to the radius of the circle;
the color imaging characteristics of the barbus are a red-green component numerical range, a black-white component numerical range and a yellow-blue component numerical range in an LAB color space;
Detecting the barely imaged region in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly comprises: taking the pixel points with color component values matched with the color imaging characteristics of the barely as the constituent pixel points of the barly imaging region, and taking the pixel points with color component values not matched with the color imaging characteristics of the barly imaging region as other pixel points outside the barly imaging region;
the identification of the pixel points, of which the color component values of the traditional Chinese medicine monitoring picture are matched with the color imaging characteristics of the barbus leaves, comprises the following steps: calculating a first color distance between a color component value of the traditional Chinese medicine monitoring picture and color imaging characteristics of the folium mori by using the following formula:
；
in the above-mentioned formula(s),representing the first color distance, +.>Representing the mean value of the range of values of the red and green components in the color imaging characteristics of said folium Bambusae,/for>Representing the red-green component value of the color component values of the traditional Chinese medicine monitoring picture, and the +.>Representing the mean value of the range of values of the black and white components in the color imaging characteristics of the folium Bambusae,/for>Representing the saidThe Chinese medicine monitoring picture has black and white component value and +. >Representing the mean value of the numerical range of the yellow-blue component in the color imaging characteristics of the barbus,representing the yellow-blue component value in the color component values of the traditional Chinese medicine monitoring picture;
calculating a second color distance between the color imaging characteristics of the folium Bambusae and a mean value of the color imaging characteristics of the folium Bambusae;
based on the first color distance, performing distance adjustment on the second color distance by using the following formula to obtain a second adjustment distance:
；
in the above-mentioned formula(s),representing said second adjustment distance, +.>Representing the second color distance, +.>Representing the first color distance;
respectively constructing a first curve between the first color distance and pixel points in the traditional Chinese medicine monitoring picture and a second curve between the second adjustment distance and pixel points corresponding to the color imaging characteristics of the folium mori;
selecting a peak value from the first curve and the second curve; when the first color distance is smaller than the peak value, taking a pixel point corresponding to the first color distance in the traditional Chinese medicine monitoring picture as a pixel point, wherein the color component value of the traditional Chinese medicine monitoring picture is matched with the color imaging characteristic of the folium mori;
The peak value is the value of the first peak in the range of the same number of pixels in the first curve within the range of the number of pixels in which the first peak in the second curve is located;
in each learning operation executed on the convolutional neural network, taking the average leaf expansion area of the known balanophyll raw material which is placed by the tray for a certain time as output data of the convolutional neural network, taking pixel information corresponding to a standard balanophyll pattern and each pixel value, each horizontal coordinate value and each vertical coordinate value which are respectively corresponding to each pixel point of a balanophyll imaging area corresponding to the condition that the tray is placed by the balanophyll raw material for a certain time as item-by-item input data of the convolutional neural network, and executing the learning operation;
the output data of the convolutional neural network, which is obtained by taking the average leaf expansion area of the known barely-leaf raw material placed by the tray for a certain time, comprises: manually measuring the expansion area of each blade of the raw material of the known blade placed in the past of the tray to obtain measured area data, and performing average processing on the measured area data to obtain the average expansion area of each blade of the raw material of the known blade placed in the past of the tray;
Wherein each learning operation performed on the convolutional neural network includes: carrying out gray scale identification on the input data to obtain gray scale pixel points; performing binarization processing on the gray pixel points to obtain binarized pixel points; performing edge detection on the binarized pixel points to obtain edge pixel points; based on the edge pixel points, the average blade deployment area is calculated using the following formula:
；
wherein,representing the flatLeaf mean area, i represents the standard leaf pattern and i leaf area of leaf imaging area corresponding to the tray when leaf material is placed a certain time before,/leaf area of leaf>Representing the total number of imaging areas of the leaves corresponding to the standard leaf pattern and the tray when the leaf material is placed for a certain time before, and ∈>Represents the total number of pixels in the ith lobe region, +.>Representing the number of pixels in the standard size grid in the ith barely leaf region, +.>Representing the area of a standard size grid within the ith barely region.
2. The image processing-based traditional Chinese medicine production monitoring control system according to claim 1, wherein:
pushing a horizontally placed tray full of barely leaf raw materials to the position right below a data acquisition station, wherein the tray is a circular tray and the radius of the circular shape is a fixed value and comprises: the fixed value is larger than or equal to a set radius threshold.
3. The image processing-based traditional Chinese medicine production monitoring control system according to claim 2, wherein the system further comprises:
and the repeated learning device is connected with the intelligent analysis device and is used for executing repeated learning operation on the convolutional neural network so as to obtain the convolutional neural network after the repeated learning operation is completed and output the convolutional neural network as the artificial intelligent model.
4. The image processing-based traditional Chinese medicine production monitoring control system according to claim 2, wherein the system further comprises:
the uniform shaking device is arranged at the front end of the raw material pushing device and is used for carrying out uniform shaking operation in the horizontal direction on a horizontally placed tray full of the barely leaf raw material and conveying the tray subjected to the uniform shaking operation to a station where the raw material pushing device is located;
the uniform shaking device comprises a shaking executing unit, a shaking control unit and a control unit, wherein the shaking executing unit is used for carrying out uniform shaking operation in the horizontal direction on a horizontally placed tray fully paved with the barely leaf raw materials at a set frequency;
the uniform shaking device further comprises a pushing execution unit used for conveying the tray after the uniform shaking operation to a station where the raw material pushing device is located.
5. The image processing-based traditional Chinese medicine production monitoring control system according to claim 2, wherein the system further comprises:
The synchronous driving mechanism is respectively connected with the raw material pushing device and the visual monitoring device and is used for realizing synchronous driving control of pushing operation of the raw material pushing device and visual data acquisition action of the data acquisition station;
the synchronous driving control for realizing the pushing operation of the raw material pushing device and the visual data acquisition action of the data acquisition station comprises the following steps: the synchronous driving mechanism is used for sending a monitoring trigger signal to the visual monitoring device after detecting that the raw material pushing device completes one pushing operation, so as to complete the triggering of one visual data acquisition action of the data acquisition station;
the synchronous driving mechanism is used for sending a monitoring trigger signal to the visual monitoring device after detecting that the raw material pushing device completes one pushing operation, so as to complete the triggering of one visual data acquisition action of the data acquisition station, and the synchronous driving mechanism comprises the following steps: and the synchronous driving mechanism adopts the falling edge of the rectangular wave to complete the triggering of one-time visual data acquisition action of the data acquisition station.
6. The image processing-based traditional Chinese medicine production monitoring control system according to claim 2, wherein the system further comprises:
The instant display device is connected with the quality judging device and is used for receiving and instant displaying the character string information corresponding to the quality grade of the barbus leaves;
and the parameter storage device is connected with the intelligent analysis device and used for storing various model parameters of the artificial intelligent model.
7. The image processing-based traditional Chinese medicine production monitoring control system according to any one of claims 2 to 6, wherein:
the method for forming the pixel points of the imaging area of the folium Bambusae by using the pixel points with the color component values matched with the color imaging characteristics of the folium Bambusae in the traditional Chinese medicine monitoring picture comprises the following steps: when a red-green component value, a black-white component value and a yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture in an LAB color space are respectively in a red-green component value range, a black-white component value range and a yellow-blue component value range, judging that the pixel point is a single component pixel point of a Ballow imaging area;
when the red-green component value, the black-white component value and the yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture under the LAB color space are respectively in the red-green component value range, the black-white component value range and the yellow-blue component value range, the judgment that the pixel point is a single component pixel point of the Ballow imaging region comprises the following steps: the value of any one of the red-green component value, the black-white component value and the yellow-blue component value of a pixel point in the traditional Chinese medicine monitoring picture in the LAB color space is between 0 and 255.
8. The image processing-based traditional Chinese medicine production monitoring control system according to any one of claims 2 to 6, wherein:
each pixel value corresponding to each pixel point of the standard Ballow pattern respectively, and each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern are obtained, and the pixel information output corresponding to the standard Ballow pattern comprises: the pixel values corresponding to the pixels of the standard Ballow pattern are gray values corresponding to the pixels of the standard Ballow pattern.
9. The image processing-based traditional Chinese medicine production monitoring control system according to claim 8, wherein:
each pixel value corresponding to each pixel point of the standard Ballow pattern respectively, and obtaining each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern respectively, and outputting the pixel values as pixel information corresponding to the standard Ballow pattern further comprises: the standard barely pattern is an imaged image comprising only a single standard shape of barly;
wherein, each pixel value that each pixel point of the standard Ballow pattern corresponds to respectively and obtain each horizontal coordinate value and each vertical coordinate value that each pixel point of the standard Ballow pattern corresponds to respectively, and regard as the pixel information output that the standard Ballow pattern corresponds to still include: in the standard Barballon pattern, the pixel point at the lower right corner is taken as the origin of a two-dimensional coordinate system, the pixel at the bottommost acts as the forward direction of the horizontal coordinate axis of the two-dimensional coordinate system, and the pixel example at the rightmost side is taken as the forward direction of the vertical coordinate axis of the two-dimensional coordinate system, so that the two-dimensional coordinate system is established.
10. A traditional Chinese medicine production monitoring control method based on image processing is characterized by comprising the following steps:
pushing a horizontally placed tray full of barely leaf raw materials to the position right below a data acquisition station, wherein the tray is a circular tray, and the radius of the circle is a fixed value;
a vision monitoring device positioned right above the data acquisition station is adopted to execute one-time vision data acquisition action of the data acquisition station so as to acquire a traditional Chinese medicine monitoring picture;
detecting a barely imaging region in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly;
acquiring each pixel value, each horizontal coordinate value and each vertical coordinate value corresponding to each pixel point of the standard Ballow pattern, and outputting the pixel values, each horizontal coordinate value and each vertical coordinate value as pixel information corresponding to the standard Ballow pattern;
the artificial intelligent model intelligently analyzes the average blade unfolding area of the current barely-placed barely-leaf raw material of the tray based on pixel information corresponding to each pixel value, each horizontal coordinate value and each vertical coordinate value of each pixel point of the barly-leaf imaging area;
determining a barblade quality level positively associated with the received average blade deployment area;
The artificial intelligent model is a convolutional neural network after a plurality of learning operations are completed, and the number of the learning operations is in direct proportion to the radius of the circle;
the tray that will be paved with the level of leaf raw materials and place is pushed to the data acquisition station under, the tray is circular tray just circular radius is fixed numerical value and includes: the fixed value is larger than or equal to a set radius threshold value;
the color imaging characteristics of the barbus are a red-green component numerical range, a black-white component numerical range and a yellow-blue component numerical range in an LAB color space;
detecting the barely imaged region in the traditional Chinese medicine monitoring picture based on the color imaging characteristics of the barly comprises: taking the pixel points with color component values matched with the color imaging characteristics of the barely as the constituent pixel points of the barly imaging region, and taking the pixel points with color component values not matched with the color imaging characteristics of the barly imaging region as other pixel points outside the barly imaging region;
the identification of the pixel points, of which the color component values of the traditional Chinese medicine monitoring picture are matched with the color imaging characteristics of the barbus leaves, comprises the following steps: calculating a first color distance between a color component value of the traditional Chinese medicine monitoring picture and color imaging characteristics of the folium mori by using the following formula:
；
In the above-mentioned formula(s),representing the first color distance, +.>Representing the mean value of the range of values of the red and green components in the color imaging characteristics of said folium Bambusae,/for>Representing the red-green component value of the color component values of the traditional Chinese medicine monitoring picture, and the +.>Representing the mean value of the range of values of the black and white components in the color imaging characteristics of the folium Bambusae,/for>Representing black and white component values in the color component values of the traditional Chinese medicine monitoring picture>Representing the mean value of the numerical range of the yellow-blue component in the color imaging characteristics of the barbus,representing the yellow-blue component value in the color component values of the traditional Chinese medicine monitoring picture;
calculating a second color distance between the color imaging characteristics of the folium Bambusae and a mean value of the color imaging characteristics of the folium Bambusae;
based on the first color distance, performing distance adjustment on the second color distance by using the following formula to obtain a second adjustment distance:
；
in the above-mentioned formula(s),representing said second adjustment distance, +.>Representing the second color distance, +.>Representing the first color distance;
respectively constructing a first curve between the first color distance and pixel points in the traditional Chinese medicine monitoring picture and a second curve between the second adjustment distance and pixel points corresponding to the color imaging characteristics of the folium mori;
Selecting a peak value from the first curve and the second curve; when the first color distance is smaller than the peak value, taking a pixel point corresponding to the first color distance in the traditional Chinese medicine monitoring picture as a pixel point, wherein the color component value of the traditional Chinese medicine monitoring picture is matched with the color imaging characteristic of the folium mori;
the peak value is the value of the first peak in the range of the same number of pixels in the first curve within the range of the number of pixels in which the first peak in the second curve is located;
performing a plurality of learning operations on the convolutional neural network to obtain the convolutional neural network after the plurality of learning operations are completed and outputting as the artificial intelligence model includes: in each learning operation executed on the convolutional neural network, taking the average leaf expansion area of the known balanophyll raw material which is placed by the tray for a certain time as output data of the convolutional neural network, taking pixel information corresponding to a standard balanophyll pattern and each pixel value, each horizontal coordinate value and each vertical coordinate value which are respectively corresponding to each pixel point of a balanophyll imaging area corresponding to the condition that the tray is placed by the balanophyll raw material for a certain time as item-by-item input data of the convolutional neural network, and executing the learning operation;
The output data of the convolutional neural network, which is obtained by taking the average leaf expansion area of the known barely-leaf raw material placed by the tray for a certain time, comprises: manually measuring the expansion area of each blade of the raw material of the known blade placed in the past of the tray to obtain measured area data, and performing average processing on the measured area data to obtain the average expansion area of each blade of the raw material of the known blade placed in the past of the tray;
wherein each learning operation performed on the convolutional neural network includes: carrying out gray scale identification on the input data to obtain gray scale pixel points; performing binarization processing on the gray pixel points to obtain binarized pixel points; performing edge detection on the binarized pixel points to obtain edge pixel points; based on the edge pixel points, the average blade deployment area is calculated using the following formula:
；
wherein,representing the average leaf spreading area, i representing the i-th leaf area of the leaf imaging areas corresponding to the standard leaf pattern and the tray when the leaf raw material is placed for a certain time, and @ being the leaf area of the leaf imaging area corresponding to the tray when the leaf raw material is placed for a certain time>Representing the total number of imaging areas of the leaves corresponding to the standard leaf pattern and the tray when the leaf material is placed for a certain time before, and ∈ >Represents the total number of pixels in the ith lobe region, +.>Representing the number of pixels in the standard size grid in the ith barely leaf region, +.>Representing the area of a standard size grid within the ith barely region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129303.9A CN116862456B (en) | 2023-09-04 | 2023-09-04 | Traditional Chinese medicine production monitoring control system and method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129303.9A CN116862456B (en) | 2023-09-04 | 2023-09-04 | Traditional Chinese medicine production monitoring control system and method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116862456A CN116862456A (en) | 2023-10-10 |
| CN116862456B true CN116862456B (en) | 2023-12-19 |
Family
ID=88221989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311129303.9A Active CN116862456B (en) | 2023-09-04 | 2023-09-04 | Traditional Chinese medicine production monitoring control system and method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116862456B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455860B (en) * | 2023-10-26 | 2024-04-09 | 宁波市宇星水表有限公司 | Water meter delivery data monitoring management system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103175835A (en) * | 2013-02-26 | 2013-06-26 | 上海烟草集团有限责任公司 | Method for determining area quality of tobacco leaves based on intelligent image processing and model estimation |
| WO2014122256A1 (en) * | 2013-02-08 | 2014-08-14 | Universita' Degli Studi Di Milano | Method and electronic equipment for determining a leaf area index |
| CN106067026A (en) * | 2016-05-30 | 2016-11-02 | 天水师范学院 | A kind of Feature extraction and recognition search method of microimage of Chinese medical herb |
| CN106468543A (en) * | 2015-08-21 | 2017-03-01 | 浙江托普云农科技股份有限公司 | A kind of method for measuring leaf area based on image procossing |
| CN109191520A (en) * | 2018-09-30 | 2019-01-11 | 湖北工程学院 | A kind of Measurement Approach of Leaf Area and system based on color calibration |
| 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 |
-
2023
- 2023-09-04 CN CN202311129303.9A patent/CN116862456B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014122256A1 (en) * | 2013-02-08 | 2014-08-14 | Universita' Degli Studi Di Milano | Method and electronic equipment for determining a leaf area index |
| CN103175835A (en) * | 2013-02-26 | 2013-06-26 | 上海烟草集团有限责任公司 | Method for determining area quality of tobacco leaves based on intelligent image processing and model estimation |
| CN106468543A (en) * | 2015-08-21 | 2017-03-01 | 浙江托普云农科技股份有限公司 | A kind of method for measuring leaf area based on image procossing |
| CN106067026A (en) * | 2016-05-30 | 2016-11-02 | 天水师范学院 | A kind of Feature extraction and recognition search method of microimage of Chinese medical herb |
| CN109191520A (en) * | 2018-09-30 | 2019-01-11 | 湖北工程学院 | A kind of Measurement Approach of Leaf Area and system based on color calibration |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 基于图像分析叶类中药材植物叶面积的质量评估研究;侯青;韩玲;侯宝峰;;当代教育实践与教学研究(第08期);第157-158、139页 * |
| 基于图像处理技术的枸杞子商品规格等级评价方法研究;王丹 等;《世界科学技术-中医药现代化》;第22卷(第8期);第2817-2823页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116862456A (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101692037B (en) | Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component | |
| CN106951836B (en) | crop coverage extraction method based on prior threshold optimization convolutional neural network | |
| CN116862456B (en) | Traditional Chinese medicine production monitoring control system and method based on image processing | |
| CN102621077B (en) | Corn seed purity nondestructive detection method based on hyper-spectral reflection image collecting system | |
| CN108593569A (en) | EO-1 hyperion water quality parameter quantitative inversion method based on spectrum morphological feature | |
| CN102072882B (en) | Method for quantitatively analyzing plant nutrient content index based on leaf image characteristics | |
| CN105842173A (en) | Method for identifying hyperspectral material | |
| CN106250896B (en) | The recognition methods of the front and back sides of online tobacco leaf based on image collecting device | |
| CN102081039A (en) | Environment-controllable hyperspectral image detecting device for crop nutrition and moisture | |
| CN105181912A (en) | Method for detection of freshness during rice storage | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN103076288A (en) | Automatic fish flesh grading device and method based on computer vision | |
| CN105021529A (en) | Spectrum information and image information fusing crop plant disease and insect pest identifying and distinguishing method | |
| CN112699756B (en) | Hyperspectral image-based tea origin identification method and system | |
| CN103942555B (en) | Method for detecting nitrogen content of plant through images | |
| CN103630091B (en) | Leaf area measurement method based on laser and image processing techniques | |
| Wang et al. | Landscape-level vegetation classification and fractional woody and herbaceous vegetation cover estimation over the dryland ecosystems by unmanned aerial vehicle platform | |
| CN106483130B (en) | A kind of detection method and its automatic detection device of rice disease | |
| CN109765194A (en) | Fructus lycii Production area recognition method based on high light spectrum image-forming technology | |
| CN102445421B (en) | Preparation method of leaf colour card used for rapidly diagnosing nitrogen of flue-cured tobacco | |
| CN109827957B (en) | Rice leaf SPAD value estimation method and system based on computer vision | |
| CN103048266A (en) | Automatic recognizing method and device for nitrogen phosphorus and potassium stress of protected tomatoes | |
| CN109540831A (en) | Fructus lycii variety ecotype method based on high light spectrum image-forming technology | |
| CN105067532A (en) | Method for identifying early-stage disease spots of sclerotinia sclerotiorum and botrytis of rape | |
| CN103528967A (en) | Hyperspectral image based overripe Lonicera edulis fruit identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |