CN102334422A - Machine vision based real-time diagnosis method and system of vegetable leaf diseases - Google Patents
Machine vision based real-time diagnosis method and system of vegetable leaf diseases Download PDFInfo
- Publication number
- CN102334422A CN102334422A CN2010102376571A CN201010237657A CN102334422A CN 102334422 A CN102334422 A CN 102334422A CN 2010102376571 A CN2010102376571 A CN 2010102376571A CN 201010237657 A CN201010237657 A CN 201010237657A CN 102334422 A CN102334422 A CN 102334422A
- Authority
- CN
- China
- Prior art keywords
- spot
- disease
- leaf
- real
- scab
- 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.)
- Granted
Links
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a machine vision based real-time diagnosis method and system of vegetable leaf diseases. The system comprises a disease image acquiring hardware part and a real-time diagnosis software part, wherein the image acquiring hardware part consists of a lighting box, a light source bracket, a light source, a round hole at the top of a box body, a digital camera, a camera fixing rod, an optical lens, a polarizer, a box body side door, an objective table and a computer. The method comprises the following steps: acquiring the symptom image of the leaf disease of vegetable to be detected; carrying out image treatment and scab division by utilizing real-time diagnosis software; acquiring the characteristic indexes of scab, such as color, texture and shape; and carrying out real-time diagnosis on the vegetable leaf disease by utilizing a disease identification model. The real-time diagnosis method and system can be directly used for detecting diseases in filed, plastic houses or greenhouses so as to achieve the rapid, stable and real-time diagnosis of various vegetable leaf diseases; no chemical reagent is used, therefore detection cost is reduced and no environment pollution is caused. The real-time diagnosis method and system can be well applied to disease monitoring.
Description
Technical field
The present invention relates to a kind of real-time diagnosis method and system, particularly a kind of vegetables leaf diseases real-time diagnosis method and system based on machine vision based on machine vision.
Background technology
Vegetable disease is to restrict the main factor that vegetables produce always.The vegetable disease number is numerous; The symptom that causes presents diversity, complexity, and the generation of disease not only causes the decline of yield of vegetables and quality, and can cause a large amount of inputs of agricultural chemicals and the rising of expenses for prevention and control; Increase production cost; Influence the nuisanceless green production of vegetables, the export trade is also caused certain obstacle, have potential environment and health risk simultaneously.
The existing diagnostic method of vegetable disease can reduce following several kinds: a kind of is the main traditional pathology method that adopts in producing for a long time; It is observation of symptoms; Discern in conjunction with microscopic examination and cultivation germ; This method takes a lot of work, time-consuming, be difficult to apace disease carried out early diagnosis, bigger to the dependence of planting the disease expert; Second method is the Enzyme-multiplied immune technique (ELISA) that rises the seventies in 20th century, and this method is the content of virus protein in the detection by quantitative plant extraction liquid delicately, but in that to detect aspect vegetative bacteria and the fungal disease successful examples less; The third method is based on the diagnostic method of molecular level; Like molecular marking technique, nucleic acid sequence analysis technology, round pcr etc.; This method has advantage fast and accurately; But the instrument and equipment that preparation diagnostic kit and application need thereof are expensive and the technical support of specialty, thereby also be difficult in a short time break away from laboratory applications in the field.Therefore, setting up a kind of disease screening method quick, accurate, harmless, that can apply is problem demanding prompt solution in China's vegetable disease integrated control.
Machine vision technique is realized the collection of image information through various imaging systems; Utilize image processing techniques to extract and explain the characteristic of acquisition target by calculator; In conjunction with various algorithm for pattern recognitions; Can carry out quantitatively, describe qualitatively and analyze object, obtain application widely aspect the plant disease diagnosis.After plant is susceptible; Certain change takes place in its metabolism, can cause the gap of pigment content, moisture and cell that plant cell is inner, and then causes that the plant external form changes; Produce scab, be reflected in the difference that then can form color, texture, shape facility on the image.These differences have directly been shown the kind and the order of severity of the suffered disease of plant again, for utilizing machine vision technique and image processing techniques diagnosis of plant disease foundation are provided.
20th century the mid-80, begin to occur machine vision technique is applied to the report in the plant disease diagnosis.Early-stage Study is many to be main body with information worker, and the disease information gathering is not mature enough; Have from colorimetry, with color characteristic as distinguishing rule, with the difference disease species; Or single with disease sample symptom dichroism, shape or texture as differentiating the factor because what extract all is the single argument characteristic parameter, the accuracy rate of carrying out pattern-recognition at last is not high, does not reach the requirement of applying.Along with going deep into of research, people recognize the complexity of plant disease symptom, begin to combine shape, texture, the colouring information of disease, have set up the multi-level fuzzy artificial neural network that can accomplish the disease species differentiation and have carried out the extraction of multivariable characteristic parameter.Though do not consider the complexity of factors such as field complex environment, kind and morbidity period, but still be to plant disease numerical diagnostic aspect good try.The applied for machines vision technique replaces the people to carry out the diagnosis of plant disease; Can get rid of the interference of artificial subjective factor, avoid the testing result that varies with each individual, not only the people freed from heavy work; And can improve precision, for the networked remote diagnostics management of disease lays the foundation.
Summary of the invention
The object of the present invention is to provide a kind of vegetables leaf diseases real-time diagnosis method and system based on machine vision.The applied for machines vision technique is gathered the image information of vegetables leaf diseases symptom; Utilize image processing techniques to carry out that scab is cut apart and feature extraction; Set up the disease property data base; And fully utilize multi-variate statistical analysis, SVMs and artificial neural network technology on this basis, and set up model based on the vegetables leaf diseases automatic diagnosis of scab image information, realize real-time, quick, harmless vegetable leaf portion disease screening.
The technical scheme that the present invention solves its technical problem employing is:
One, a kind of vegetable leaf portion disease screening method based on machine vision
Gather vegetables leaf diseases image, utilize real-time diagnosis software to carry out image processing, scab feature extraction and disease real-time diagnosis, concrete steps are following:
1) sets up the real-time diagnosis software systems
Gather the vegetables leaf diseases sample of different onset period, different habitat, different cultivars, the disease that each sample infects is identified by planting the disease expert; Gather its disease symptom image then; Utilize image processing techniques, realize cutting apart automatically of scab, extract the various features index of scab, set up the property data base of corresponding disease; On this basis, select suitable scab characteristic parameter and effective patterns recognizer, make up vegetables leaf diseases real-time diagnosis model based on machine vision;
2) carry out real-time diagnosis
During real-time diagnosis, after vegetables leaf diseases sample is gathered in real time, carry out image by the real-time diagnosis software of setting up and handle and feature extraction, according to the disease screening model that makes up the vegetables leaf diseases is carried out real-time diagnosis then.
The described image processing techniques of utilizing comprises image digitazation, image gray processing, figure image intensifying, image is cut apart and the mathematical morphology treatment technology.
The described various features index that extracts scab comprises the color characteristic of scab, like the R average under RGB and the HIS color system, G average, B average, r average, g average, b average, H average, I average and S average; The textural characteristics of scab is like contrast, correlation, energy, the moment of inertia and the entropy of gray level co-occurrence matrixes; The shape facility of scab is like complex-shaped property degree, eccentricity, circularity and form parameter.
Scab characteristic parameter and effective patterns recognizer that described selection is fit to; Refer to utilize principal component analysis, discriminant analysis from the disease property data base of setting up, to select to be suitable for the characteristic parameter of disease identification, with its input parameter as the disease model of cognition; Then, from multi-variate statistical analysis, SVMs and artificial neural network technology various modes recognizer, select effective algorithm to set up vegetables leaf diseases automatic diagnosis model based on the scab image information.
Two, a kind of vegetable leaf portion disease diagnosing system based on machine vision
Comprise disease image acquisition hardware part and real-time diagnosis software section.Wherein image acquisition hardware partly comprises lighting box, four light source brackets, four light sources, camera fixing bar, digital camera, casing top circular hole, optical lens, polariscope, casing side door, objective table, calculator; Four light source brackets are installed in lighting box top four sides, and four light source brackets can be adjusted to sustained height and fixing at the lighting box top, and four light sources are separately fixed on the light source bracket separately; The camera fixing bar is installed in the middle of the lighting box exterior top surface; Digital camera is fixed on the camera fixing bar, and digital camera can move on the camera fixing bar and make view finder of camera place circular hole place, casing top, and polariscope is spun on the optical lens; Objective table places the tank floor center position; But casing side door free switch is to pick and place sample, and the casing side door is closed the back whole box body and formed closed chamber, and digital camera is connected through the USB line with calculator.
Comparing the beneficial effect that the present invention has with background technology is:
(1) utilizes machine vision technique to carry out disease identification, can realize quick, stable, the real-time diagnosis of various vegetables leaf diseases.Whole disease screening process (comprising processes such as IMAQ, image processing, feature extraction and pattern-recognition) generally can be accomplished in 2 minutes;
(2) do not use any chemical reagent, reduce and detect cost, reduce labor intensity, can be good at being applied to environmental monitoring;
(3) whole detection system only is made up of a portable lighting box, a calculator;
(4) when each assembly of diagnostic system all connect finish after, a series of activities such as last IMAQ, image cut apart, feature extraction, disease screening are all accomplished through the image processing software that has the automatic model of cognition of disease;
(5) carry out chemical agent through diagnostic result and handle the vegetables leaf diseases, can reduce since comprehensively the agricultural chemicals that causes of spray medicine abuse, reduce production costs and reduce pollution.
Description of drawings
Fig. 1 is an apparatus structure sketch map of the present invention.
Among the figure: 1. lighting box; 2. four light source brackets; 3. four light sources; 4. casing top circular hole; 5. digital camera; 6. camera fixing bar; 7. optical lens; 8. polariscope; 9. casing side door; 10. objective table; 11. calculator.
Fig. 2 is a software general construction framework of the present invention.
Fig. 3 is a vegetable leaf of the present invention portion Image Processing for Plant Disease procedure chart.
Among the figure: the original disease symptom of A. image; B. scab area image; C.R passage gray level image; D.G passage gray level image; E.B passage gray level image; F. the scab profile extracts; G. scab bianry image; H. scab segmentation result.
Fig. 4 is that software systems of the present invention (early blight of tomato diagnostic system) make up flow chart.
Embodiment
Below in conjunction with accompanying drawing and embodiment the present invention is described further.
System of the present invention is made up of image acquisition hardware part and disease automatic diagnosis software section.
As shown in Figure 1, hardware components of the present invention comprises lighting box 1, four light source brackets 2, four light sources 3, casing top circular hole 4, digital camera 5, camera fixing bar 6, optical lens 7, polariscope 8, casing side door 9, objective table 10, calculator 11; Four light source brackets 2 are installed in lighting box 1 top four sides; Four light source brackets 2 can be adjusted to sustained height and fixing at lighting box 1 top; Four light sources 3 are separately fixed on the light source bracket 2 separately, and camera fixing bar 6 is installed in lighting box 1 exterior top surface central authorities, and digital camera 5 is fixed on the camera fixing bar 6; Digital camera 5 can move and make view finder of camera to place circular hole 4 places, casing top on camera fixing bar 6; Polariscope 8 is spun on the optical lens 7, and objective table 10 places the tank floor center position, but casing side door 9 free switch are to pick and place sample; Casing side door 9 is closed the back whole box body and is formed closed chamber, and digital camera 5 is connected through the USB line with calculator 10.
As shown in Figure 2, disease automatic diagnosis software section of the present invention comprises 5 modules such as image capture module, image input control module, image processing module, image characteristics extraction module and disease automatic diagnosis output module.Wherein the function of image capture module is the classical symptom digital picture of gathering the vegetables leaf diseases in real time; The function of image input control module is the image information digitlization of gathering in the camera and imports computer processor into; The function of image processing module is for carrying out image preliminary treatment, figure image intensifying and scab Region Segmentation to the disease symptom original image of gathering; The function of image characteristics extraction module is for extracting color characteristic, textural characteristics and the shape facility of scab area image; The function of disease screening output module is for providing the diagnostic result of test vegetables leaf diseases according to the disease model of cognition of setting up.
Described image processing module, as shown in Figure 3 may further comprise the steps:
(1) montage goes out the regional coloured image of scab from the original disease symptom image of gathering, like the processing of the original disease symptom of Fig. 3 (A) image to Fig. 3 (B) scab area image;
(2) convert scab zone coloured image to RGB three-channel gray level image, like the processing of Fig. 3 (B) scab zone coloured image to Fig. 3 (C, D, E) gray level image, Fig. 3 (C) is a R passage gray-scale map image pattern, and 3 (D) are G passage gray level image; Fig. 3 (E) is a B passage gray level image;
(3) select scab edge and detail section information to preserve more complete R channel image, adopt medium filtering to handle and carry out the image denoising enhancing, carry out the scab profile then and extract, like of the processing of Fig. 3 (C) R passage gray level image to Fig. 3 (F) scab contour images;
(4) the scab contour images is corroded and a series of mathematical morphologies such as expansion are handled, obtain the scab bianry image, like of the processing of Fig. 3 (F) scab contour images to Fig. 3 (G) scab bianry image;
(5) last, carry out the coloured image of the scab that compose operation obtains from original symptom image, splitting, the processing that will arrive Fig. 3 (H) scab colour split image like Fig. 3 (G) scab bianry image with bianry image as template.
With the example that is configured to early blight of tomato real-time diagnosis software systems, as shown in Figure 4 in the present embodiment, the practical implementation process of present embodiment is following:
(1) gathers the early blight of tomato sample in different tomato varieties, different onset period, different habitats, each sample is identified by planting the disease expert; To its symptom image of early blight of tomato sample collection after identifying, set up the standardized digital image library of early blight of tomato classical symptom;
(2) the early blight of tomato symptom image to gathering carries out image preliminary treatment, figure image intensifying and scab and cuts apart, with the scab zone with from whole disease symptom image, split;
(3) the various features index of extraction early blight of tomato scab comprises color characteristic, like average and mathematics conversion type and the mathematical combination parameter of R, G, B, r, g, b, H, I, S under RGB and the HIS color system; Textural characteristics is like contrast, correlation, energy, the moment of inertia and the entropy of gradation of image co-occurrence matrix; Shape facility is like complex-shaped property degree, eccentricity, circularity and form parameter; Set up the property data base of early blight of tomato image recognition;
(4) utilize principal component analytical method, stepwise discriminant analysis method from property data base, to choose and put principal component, the characteristic parameter of answering early blight of tomato scab characteristic, its input parameter as structure early blight of tomato diagnostic model;
(5) comprehensive utilization multi-variate statistical analysis, SVMs and artificial neural network technology set up the pattern recognition model that is suitable for the early blight of tomato diagnosis, accomplishes the structure based on the early blight of tomato real-time diagnosis system of machine vision.
The method of introducing above utilizing is accomplished the establishment of vegetable leaf portion disease diagnosing system software on MATLAB 7.0 development platforms, can fast and effeciently carry out the collection of vegetables leaf diseases symptom image real-time, image processing, feature extraction and pattern-recognition.When native system is used for greenhouse, booth or field detection, can the disease sample directly be placed on the objective table of lighting box bottom surface, utilize IMAQ and disease screening software can obtain the qualification result of vegetables blade institute introduced disease then.
Claims (5)
1. vegetable leaf portion disease screening method based on machine vision is characterized in that: gather vegetables leaf diseases image, utilize that real-time diagnosis software carries out that image is handled, scab feature extraction and disease real-time diagnosis, concrete steps are following:
(1) sets up the real-time diagnosis software systems
Gather the vegetables leaf diseases sample of different onset period, different habitat, different cultivars, the disease that each sample infects is identified by planting the disease expert; Gather its disease symptom image then; Utilize image processing techniques, realize cutting apart automatically of scab; Extract the various features index of scab, set up the property data base of corresponding disease; On this basis, select suitable scab characteristic parameter and effective patterns recognizer, make up vegetables leaf diseases real-time diagnosis model based on machine vision;
(2) carry out real-time diagnosis
During real-time diagnosis, after vegetables leaf diseases sample is gathered in real time, carry out image by the real-time diagnosis software of setting up and handle and feature extraction, the vegetables leaf diseases is carried out real-time diagnosis according to the disease screening model.
2. the vegetable leaf portion disease diagnosing system based on machine vision is characterized in that: comprise disease image acquisition hardware part and real-time diagnosis software section.Wherein image acquisition hardware partly comprises lighting box (1), four light source brackets (2), four light sources (3), casing top circular hole (4), digital camera (5), camera fixing bar (6), optical lens (7), polariscope (8), casing side door (9), objective table (10), calculator (11); Four light source brackets (2) are installed in lighting box (1) top four sides; Four light source brackets (2) can be adjusted to sustained height and fixing at lighting box (1) top; Four light sources (3) are separately fixed on the light source bracket (2) separately, and camera fixing bar (6) is installed in lighting box (1) exterior top surface central authorities, and digital camera (5) is fixed on the camera fixing bar (6); Digital camera (5) can move on camera fixing bar (6) and make view finder of camera place casing top circular hole (4) to locate; Polariscope (8) is spun on the optical lens (7), and objective table (10) places the tank floor center position, casing side door (9) but free switch to pick and place sample; Casing side door (9) is closed the back whole box body and is formed closed chamber, and digital camera (5) is connected through the USB line with calculator (10).
3. a kind of vegetable leaf portion disease screening method according to claim 1 based on machine vision; It is characterized in that: the described various features index that extracts scab; The color characteristic that comprises scab is like the R average under RGB and the HIS color system, G average, B average, r average, g average, b average, H average, I average and S average; The textural characteristics of scab is like contrast, correlation, energy, the moment of inertia and the entropy of gray level co-occurrence matrixes; The shape facility of scab is like complex-shaped property degree, eccentricity, circularity and form parameter.
4. a kind of vegetable leaf portion disease screening method according to claim 1 based on machine vision; It is characterized in that: scab characteristic parameter and effective patterns recognizer that described selection is fit to; Refer to utilize principal component analysis, discriminant analysis from the disease property data base of setting up, to select to be suitable for the characteristic parameter of vegetable leaf portion disease screening, with its input parameter as the disease screening model; Then, from multi-variate statistical analysis, SVMs and artificial neural network technology various modes recognizer, select effective algorithm to set up vegetables leaf diseases automatic diagnosis model based on the scab image information.
5. a kind of vegetable leaf portion disease screening method based on machine vision according to claim 1 is characterized in that: described vegetables leaf diseases comprises 15 kinds of main leaf diseases such as climing rot (Ascochyta citrullina), downy mildew (Pseudoperonospora cubensis), scab (Cladosporium cucumerinum), gray mold (Botrytis cinerea), anthracnose (Colletortichum orbiculare), stalk break (Sclerotinia sclerotiorum), powdery mildew (Sphaerotheca fuliginea), black spot (Alternariacucumerina), brown spot (Corynespora cassiicola), rouge and powder sick (Trichothecium roseum), spot disease (Phyllosticta cucurbitacearum), leaf spot (Cercospora citrullina), bacillary leaf blight (Xanthomonascampestris pv.Cucurbitae), bacterial angular leaf spot (Pseudomopnas syringae pv.Lachrymans), the bacillary marginal leaf blight (Pseudomopnas marginalis pv.Marginalis) of cucumber, sponge gourd, pumpkin, custard squash, wax gourd, balsam pear, bottle gourd, snake melon, serpent melon; The early blight of tomato (Alternaria solani); Leaf mold (Fulvia fulva); Gray mold (Botrytis cinerea); Spot blight (Septoria lycopersici); Brown spot (Corynesporacassiicola); Late blight (Phytophthora infestans); Powdery mildew (Sphaerotheca fulifinea); Stalk break (Sclerotinia sclerotiporum); Sooty mould (Pseudocercospora fuligena); Gray leaf spot (Stemphyliumsolani); Tomato myrothecium rot (Myrothecium roridum); Anthracnose (colletotrichum coccodes); Tomato spot disease (Stemphylium lycopersici); Bacterial speck (Pseudomonas syringae pv.tomato); The brown line sick (Phomopsis vexans) of eggplant; Early blight (Alternaria solani); Black spot (Alternaria melongenae); Brown spot (Corynespora cassiicola); Suede bacterial plaque sick (Mycovellosiella nattrassii); Anthracnose (Colletotrichumcapsici); Tomato myrothecium rot (Myrothecium roridum); Powdery mildew (Sphaerotheca fulifinea); Gray mold (Botrytiscinerea); Rust (Septoria melongenae); The brown spot of capsicum (Corynespora cassiicola), gray mold (Botrytis cinerea), anthracnose (Gloeosporium Piperatum), powdery mildew (Podosphaera xanthii), gray leaf spot (Stemphylium solani), leaf spot (Cercospora capsici), anthracnose (Colletotrichum capsici), early blight (Alternaria solani), bacterial speck (Pseudomonas syringae pv.aptata); Kidney bean; Cowpea; Sword bean; The rust of green soy bean (Uromyces appendiculatus); Red spot disease (Cercospora canescens); Anthracnose (Colletotrichum truncata); Spot disease (Phyllosticta phaseolina); Powdery mildew (Sphaerotheca astragali); Brown spot (Corynespora mazei); Ring spot (Ascochyta phaseolorum); Gray mold (Botrytis cinerea); Angular leaf spot (Phaeoisariopsis griseola); Sooty mould (Pseudocercospora cruenta); Spot blight (Septoriaphaseoli); The downy mildew of Chinese cabbage, wild cabbage, tender flower stalk, cauliflower, broccoli (Peronospora parasitica), black spot (Alternaria brassicicola), powdery mildew (Erysiphe cruciferarum), white blister (Albugo candida), anthracnose (Colletotrichum higginsianum), brown spot (Cercospora brassicicola), gray mold (Botrytis cinerea); The leaf spot of spinach, New Zealand spinach (Cercospora beticola), black spot (Alternaria spinaciae), gray mold (Botrytiscinerea), white blister (Albugo occidentalis), downy mildew (Peronospora effusa), anthracnose (Colletotrichumspinaciae); The spot blight of celery (Septoria apiicola), leaf spot (Cercospora apii), rust (Pucciniaangelicicola), leaf spot (Phyllosticta apii), gray mold (Botrytis cinerea), bacterial leaf spot (Pseudomonascichorii); The downy mildew of lettuce (Bremia lactucae), brown spot (Cercospora lactucae-sativae), black spot (Alternaria alternata), gray mold (Botrytis cinerea), powdery mildew (Sphaerotheca fulifinea), spot blight (Septoria lactucae); The downy mildew of crowndaisy chrysanthemum (Peronospora chrysanthemi-coronarii), leaf spot (Phyllostictachrysanthemi), anthracnose (Colletotrichum gloeosporioides), brown spot (Cercospora chrysanthemi), black spot (Alternaria zinniae); The downy mildew of romaine lettuce (Bremia lactucae), leaf spot (Cercosporalactucae-sativae); The rust of hare's-lettuce (Puccinia sonchi), downy mildew (Bremia lactucae), ring spot (Stemphyliumchisha), black spot (Alternariasonchi).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010237657 CN102334422B (en) | 2010-07-27 | 2010-07-27 | Machine vision based real-time diagnosis method and system of vegetable leaf diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010237657 CN102334422B (en) | 2010-07-27 | 2010-07-27 | Machine vision based real-time diagnosis method and system of vegetable leaf diseases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102334422A true CN102334422A (en) | 2012-02-01 |
| CN102334422B CN102334422B (en) | 2013-02-27 |
Family
ID=45510566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010237657 Active CN102334422B (en) | 2010-07-27 | 2010-07-27 | Machine vision based real-time diagnosis method and system of vegetable leaf diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102334422B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102706877A (en) * | 2012-06-06 | 2012-10-03 | 石河子大学 | Portable detecting system for diseases and insect pests of cotton and detecting method |
| CN102789579A (en) * | 2012-07-26 | 2012-11-21 | 同济大学 | Identification method for stressed state of water fertilizer of greenhouse crop on basis of computer vision technology |
| CN103336010A (en) * | 2013-07-10 | 2013-10-02 | 江苏大学 | Early tobacco virus disease detection method based on infrared thermal imaging technology |
| CN103424956A (en) * | 2013-09-04 | 2013-12-04 | 常州智能农业装备研究院有限公司 | Light filling device of crab shell image collector |
| CN103559511A (en) * | 2013-11-20 | 2014-02-05 | 天津农学院 | Automatic identification method of foliar disease image of greenhouse vegetable |
| CN103983249A (en) * | 2014-04-18 | 2014-08-13 | 北京农业信息技术研究中心 | Plant growth detailed-process image continuous-acquisition system |
| CN104297166A (en) * | 2014-11-07 | 2015-01-21 | 张勤书 | Intelligent diagnosis system for plant diseases and application method of system |
| CN104636981A (en) * | 2013-11-08 | 2015-05-20 | 财团法人资讯工业策进会 | Treatment mode suggestion system and method for plant symptoms |
| CN104766152A (en) * | 2015-01-30 | 2015-07-08 | 安徽大学 | Crop disease recognition and disease condition assessment device |
| CN105180850A (en) * | 2015-07-15 | 2015-12-23 | 中国农业大学 | Method for calculating corn leaf exserohilum turcicum disease spot area ratio and device |
| CN105466866A (en) * | 2014-09-03 | 2016-04-06 | 上海市闵行第二中学 | Visible light spectrophotometer |
| CN105510332A (en) * | 2015-12-16 | 2016-04-20 | 吉林大学 | Multichannel pesticide residue detecting device and method |
| CN106023159A (en) * | 2016-05-10 | 2016-10-12 | 中国农业大学 | Disease spot image segmentation method and system for greenhouse vegetable leaf |
| CN106134813A (en) * | 2016-07-25 | 2016-11-23 | 北京小米移动软件有限公司 | Plant cultural method, Apparatus and system |
| CN107099592A (en) * | 2017-05-04 | 2017-08-29 | 中国农业科学院蔬菜花卉研究所 | Detect reagent set and the application of eggplant stemphylium botryosum |
| CN107462561A (en) * | 2017-09-09 | 2017-12-12 | 华中农业大学 | Tobacco leaf scab character fluorescence dynamic automatic testing device and method |
| CN108471712A (en) * | 2015-12-16 | 2018-08-31 | 富兰帝欧公司 | Information processing unit, information processing method and program |
| WO2019000563A1 (en) * | 2017-06-30 | 2019-01-03 | 深圳前海弘稼科技有限公司 | Cultivation parameter regulation method and cultivation parameter regulation device |
| CN110567968A (en) * | 2019-09-04 | 2019-12-13 | 中国科学院长春光学精密机械与物理研究所 | part defect detection method and device |
| CN112668404A (en) * | 2020-12-10 | 2021-04-16 | 哈尔滨师范大学 | Effective identification method for soybean diseases and insect pests |
| CN113575397A (en) * | 2021-08-24 | 2021-11-02 | 中国科学院南京地理与湖泊研究所 | Method for constructing three-dimensional geometric configuration of aquatic plant root system |
| CN117269108A (en) * | 2023-10-16 | 2023-12-22 | 河南省科学院 | Portable eucommia ulmoides leaf screening device and screening method for near infrared spectrum transmission detection |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021939A (en) * | 2007-03-29 | 2007-08-22 | 沈阳理工大学 | Computer image processing-based crops disease diagnosing system |
| CN101482514A (en) * | 2008-01-10 | 2009-07-15 | 北京农业信息技术研究中心 | Disease detecting instrument and method |
-
2010
- 2010-07-27 CN CN 201010237657 patent/CN102334422B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021939A (en) * | 2007-03-29 | 2007-08-22 | 沈阳理工大学 | Computer image processing-based crops disease diagnosing system |
| CN101482514A (en) * | 2008-01-10 | 2009-07-15 | 北京农业信息技术研究中心 | Disease detecting instrument and method |
Non-Patent Citations (4)
| Title |
|---|
| 冯洁: "常见黄瓜病害的多光谱诊断", 《光谱学与光谱分析》, vol. 29, no. 2, 28 February 2009 (2009-02-28) * |
| 岑哲鑫: "基于彩色图像颜色统计特征的黄瓜炭病和褐斑病的识别研究", 《园艺学报》, vol. 34, no. 6, 31 December 2007 (2007-12-31) * |
| 柴阿丽: "基于高光谱成像和判别分析的黄瓜病害识别", 《光谱学与光谱分析》, vol. 30, no. 5, 30 May 2010 (2010-05-30) * |
| 赖军臣: "作物病害机器视觉诊断研究进展", 《中国农业科学》, vol. 42, no. 4, 31 December 2009 (2009-12-31) * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102706877A (en) * | 2012-06-06 | 2012-10-03 | 石河子大学 | Portable detecting system for diseases and insect pests of cotton and detecting method |
| CN102789579A (en) * | 2012-07-26 | 2012-11-21 | 同济大学 | Identification method for stressed state of water fertilizer of greenhouse crop on basis of computer vision technology |
| CN102789579B (en) * | 2012-07-26 | 2015-06-03 | 同济大学 | Identification method for stressed state of water fertilizer of greenhouse crop on basis of computer vision technology |
| CN103336010A (en) * | 2013-07-10 | 2013-10-02 | 江苏大学 | Early tobacco virus disease detection method based on infrared thermal imaging technology |
| CN103336010B (en) * | 2013-07-10 | 2015-11-11 | 江苏大学 | A kind of tobacco virus early detection method based on infrared thermal imaging technique |
| CN103424956A (en) * | 2013-09-04 | 2013-12-04 | 常州智能农业装备研究院有限公司 | Light filling device of crab shell image collector |
| CN104636981A (en) * | 2013-11-08 | 2015-05-20 | 财团法人资讯工业策进会 | Treatment mode suggestion system and method for plant symptoms |
| CN103559511A (en) * | 2013-11-20 | 2014-02-05 | 天津农学院 | Automatic identification method of foliar disease image of greenhouse vegetable |
| CN103983249A (en) * | 2014-04-18 | 2014-08-13 | 北京农业信息技术研究中心 | Plant growth detailed-process image continuous-acquisition system |
| CN105466866A (en) * | 2014-09-03 | 2016-04-06 | 上海市闵行第二中学 | Visible light spectrophotometer |
| CN104297166A (en) * | 2014-11-07 | 2015-01-21 | 张勤书 | Intelligent diagnosis system for plant diseases and application method of system |
| CN104766152A (en) * | 2015-01-30 | 2015-07-08 | 安徽大学 | Crop disease recognition and disease condition assessment device |
| CN105180850A (en) * | 2015-07-15 | 2015-12-23 | 中国农业大学 | Method for calculating corn leaf exserohilum turcicum disease spot area ratio and device |
| CN105180850B (en) * | 2015-07-15 | 2017-09-22 | 中国农业大学 | Calculate the method and device of Maize Leaf leaf blight lesion area ratio |
| CN105510332A (en) * | 2015-12-16 | 2016-04-20 | 吉林大学 | Multichannel pesticide residue detecting device and method |
| CN108471712A (en) * | 2015-12-16 | 2018-08-31 | 富兰帝欧公司 | Information processing unit, information processing method and program |
| CN105510332B (en) * | 2015-12-16 | 2018-04-20 | 吉林大学 | A kind of Detecting Pesticide apparatus and method for of multichannel |
| CN106023159A (en) * | 2016-05-10 | 2016-10-12 | 中国农业大学 | Disease spot image segmentation method and system for greenhouse vegetable leaf |
| CN106023159B (en) * | 2016-05-10 | 2019-02-26 | 中国农业大学 | Facilities vegetable leaf portion scab image partition method and system |
| CN106134813A (en) * | 2016-07-25 | 2016-11-23 | 北京小米移动软件有限公司 | Plant cultural method, Apparatus and system |
| CN107099592A (en) * | 2017-05-04 | 2017-08-29 | 中国农业科学院蔬菜花卉研究所 | Detect reagent set and the application of eggplant stemphylium botryosum |
| WO2019000563A1 (en) * | 2017-06-30 | 2019-01-03 | 深圳前海弘稼科技有限公司 | Cultivation parameter regulation method and cultivation parameter regulation device |
| CN107462561A (en) * | 2017-09-09 | 2017-12-12 | 华中农业大学 | Tobacco leaf scab character fluorescence dynamic automatic testing device and method |
| CN110567968A (en) * | 2019-09-04 | 2019-12-13 | 中国科学院长春光学精密机械与物理研究所 | part defect detection method and device |
| CN112668404A (en) * | 2020-12-10 | 2021-04-16 | 哈尔滨师范大学 | Effective identification method for soybean diseases and insect pests |
| CN113575397A (en) * | 2021-08-24 | 2021-11-02 | 中国科学院南京地理与湖泊研究所 | Method for constructing three-dimensional geometric configuration of aquatic plant root system |
| CN113575397B (en) * | 2021-08-24 | 2022-08-02 | 中国科学院南京地理与湖泊研究所 | Method for constructing three-dimensional geometric configuration of aquatic plant root system |
| CN117269108A (en) * | 2023-10-16 | 2023-12-22 | 河南省科学院 | Portable eucommia ulmoides leaf screening device and screening method for near infrared spectrum transmission detection |
| CN117269108B (en) * | 2023-10-16 | 2024-02-27 | 河南省科学院 | Portable eucommia ulmoides leaf screening device and screening method for near infrared spectrum transmission detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102334422B (en) | 2013-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102334422B (en) | Machine vision based real-time diagnosis method and system of vegetable leaf diseases | |
| CN111709333B (en) | Tracing early warning system based on abnormal excrement of cage-raised chickens and health monitoring method | |
| WO2011055791A1 (en) | Device for harvesting bacterial colony and method therefor | |
| CN101167101A (en) | Automated image analysis | |
| CN110082298B (en) | Hyperspectral image-based wheat variety gibberellic disease comprehensive resistance identification method | |
| CN108858122A (en) | A kind of greenhouse plant disease crusing robot and method for inspecting | |
| US20080102487A1 (en) | Method and apparatus for non-invasive rapid fungal specie (mold) identification having hyperspectral imagery | |
| CN109684906A (en) | The method of detection red turpentine beetle based on deep learning | |
| CN109661473B (en) | Methods, systems, and computer program products for determining the presence of and identifying microorganisms | |
| CN105067532A (en) | Method for identifying early-stage disease spots of sclerotinia sclerotiorum and botrytis of rape | |
| Abdullakasım et al. | An images analysis technique for recognition of brown leaf spot disease in cassava | |
| Vishnoi et al. | Crop disease classification through image processing and machine learning techniques using leaf images | |
| CN1385700A (en) | Sperm fluorescent staining computer detection system | |
| Syed et al. | Machine vision technology in agriculture: A review on the automatic seedling transplanters | |
| KR101907563B1 (en) | Method for the viability of embryo in white fertilized egg using hyperspectral imaging | |
| PP et al. | Automated quality assessment of cocoons using a smart camera based system | |
| He et al. | A binocular stereovision system for transplant growth variables analysis | |
| López Flórez et al. | Automatic Cell Counting With YOLOv5: A Fluorescence Microscopy Approach | |
| CN116524344A (en) | Tomato string picking point detection method based on RGB-D information fusion | |
| CN108007916B (en) | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method | |
| Rangarajan et al. | A vision based crop monitoring system using segmentation techniques | |
| CN109633143B (en) | System and method for detecting bone marrow microcirculation environment of patient after hematopoietic stem cell transplantation | |
| CN112734688A (en) | Potato browning detection method based on machine vision | |
| Liu et al. | 3D Rotation-Invariant description from tensor operation on spherical HOG field | |
| Kaiyan et al. | A real time image segmentation approach for crop leaf |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |