CN113324921A - Construction method and application of astragalus seed chlorophyll content determination model - Google Patents

Construction method and application of astragalus seed chlorophyll content determination model Download PDF

Info

Publication number
CN113324921A
CN113324921A CN202110590590.8A CN202110590590A CN113324921A CN 113324921 A CN113324921 A CN 113324921A CN 202110590590 A CN202110590590 A CN 202110590590A CN 113324921 A CN113324921 A CN 113324921A
Authority
CN
China
Prior art keywords
chlorophyll content
seeds
astragalus
color
astragalus seeds
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110590590.8A
Other languages
Chinese (zh)
Inventor
孙群
许亚男
程莹
涂柯玲
董学会
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN202110590590.8A priority Critical patent/CN113324921A/en
Publication of CN113324921A publication Critical patent/CN113324921A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention provides a construction method and application of a chlorophyll content determination model of astragalus membranaceus seeds, and belongs to the technical field of agriculture. The color indexes of astragalus seeds with different known chlorophyll contents are extracted; and establishing a multiple linear regression equation of the training set by taking the color index as an independent variable and the chlorophyll content as a dependent variable, and constructing to obtain a measuring model of the chlorophyll content of the astragalus seeds. The determination model obtained by the construction method can be used for detecting the chlorophyll content of the astragalus seeds and detecting R2About 0.98, high detection accuracy, no chemical reagent limitation, convenient and quick detection, no damage and low cost.

Description

Construction method and application of astragalus seed chlorophyll content determination model
Technical Field
The invention relates to the technical field of agriculture, in particular to a construction method and application of a chlorophyll content determination model of astragalus seeds.
Background
The seed maturity plays an important role in each link of astragalus seed production, processing, sale and the like. The maturity of the seeds is directly related to the chlorophyll content, and the maturity is low if the chlorophyll content of the seeds is high; conversely, a low chlorophyll content results in a relatively high degree of maturity.
The traditional method for detecting the chlorophyll content of the seeds is a chemical method, namely, a sample is dissolved in a chemical reagent to extract and detect the chlorophyll content. Although the chemical method can accurately measure the chlorophyll content of the seeds, the adopted chemical reagent has certain toxicity and destructiveness, such as acetone, and the chemical method needs to be extracted and then measured, and is time-consuming and labor-consuming.
The prior art also discloses portable devices for measuring the chlorophyll content of seeds, such as a FluoMini Pro optical Chlorophyll Fluorescence (CF) detector, which uses blue modulated pulsed LED light to measure chlorophyll fluorescence of plant leaves, algae, seeds, etc., and converts to the chlorophyll content of the plant based on the measured fluorescence values. Although the measuring instrument is very portable, the instrument is high in cost and is not suitable for wide-range popularization.
Disclosure of Invention
The invention aims to provide a construction method and application of a chlorophyll content measurement model of astragalus seeds.
In order to achieve the above object, the present invention provides the following technical solutions:
the invention provides a construction method of a chlorophyll content determination model of astragalus membranaceus seeds, which comprises the following steps:
1) extracting color indexes of astragalus seeds with different known chlorophyll contents;
2) establishing a multiple linear regression equation of a training set by taking the color index as an independent variable and the chlorophyll content as a dependent variable to obtain a chlorophyll content measuring model of the astragalus seeds;
the color index comprises red, green, blue and gray; and measuring each color index for 5-7 times and taking an average value.
Preferably, the method for extracting the color index includes:
and (3) tiling, scanning or photographing the astragalus seeds to obtain color scanning images or color photos of the astragalus seeds, extracting color indexes in the color scanning images or color photos of each group of astragalus seeds and calculating an average value.
Preferably, before the astragalus seeds are tiled, the method further comprises the following steps: classifying the astragalus seeds according to colors, and mixing the astragalus seeds with different colors according to different proportions to obtain astragalus seeds of different groups.
Preferably, the chlorophyll content is an average value of chlorophyll content obtained by measuring 5-7 times.
The invention also provides application of the determination model constructed by the construction method in the scheme in determination of the content of chlorophyll in the astragalus seeds.
Preferably, the method for measuring the chlorophyll content of the astragalus seeds comprises the following steps:
measuring the color index of the astragalus seeds to be detected;
and inputting the color index serving as an input factor into the measurement model obtained by the construction method in the scheme, and outputting the chlorophyll content of the astragalus seeds to be measured.
The invention provides a construction method of a chlorophyll content determination model of astragalus seeds, which extracts color indexes of astragalus seeds with different known chlorophyll contents; and establishing a multiple linear regression equation of the training set by taking the color index as an independent variable and the chlorophyll content as a dependent variable, and constructing to obtain a measuring model of the chlorophyll content of the astragalus seeds. The determination model obtained by the construction method can be used for detecting the chlorophyll content of the astragalus seeds and detecting R2About 0.98, high detection accuracy, no chemical reagent limitation, convenient and quick detection, no damage and low cost.
Drawings
FIG. 1 is a schematic flow chart of a method for measuring chlorophyll content in Astragalus membranaceus seeds according to an embodiment of the present invention;
FIG. 2 is a graph of the training effect of a multiple linear regression model established for different characteristic indexes;
FIG. 3 is a graph for comparing predicted values and actual values of a multiple linear regression model established by different characteristic indexes.
Detailed Description
The invention provides a construction method of a chlorophyll content determination model of astragalus membranaceus seeds, which comprises the following steps:
1) extracting color indexes of astragalus seeds with different known chlorophyll contents;
2) establishing a multiple linear regression equation of a training set by taking the color index as an independent variable and the chlorophyll content as a dependent variable to obtain a chlorophyll content measuring model of the astragalus seeds;
the color index comprises red, green, blue and gray; and measuring each color index for 5-7 times and taking an average value.
The method firstly extracts the color indexes of the astragalus seeds with different known chlorophyll contents.
In the invention, the method for measuring the chlorophyll content of the astragalus seeds with different known chlorophyll contents comprises the following steps: the measurement was performed using a FluoMini Pro optical Chlorophyll Fluorescence (CF) detector. In the invention, the chlorophyll content is preferably an average value after 5-7 measurements, and more preferably an average value after 6 measurements. In the specific implementation process of the invention, certain errors exist in the chlorophyll content measurement among seeds with different masses, so that the mass of the astragalus seeds needs to be determined before measurement in order to reduce the errors by unifying the variables.
In the invention, the color indexes for extracting astragalus seeds with different known chlorophyll contents comprise:
and (3) tiling, scanning or photographing the astragalus seeds to obtain color scanning images or color photos of the astragalus seeds, extracting color indexes in the color scanning images or color photos of each group of astragalus seeds and calculating an average value. In the scanning or photographing process, the seed position and the ambient light source are fixed, and the environment is kept constant and consistent. In the invention, the camera used for taking the picture is preferably a camera with a CCD lens. In the invention, the adopted equipment for color scanning is preferably a Qinghua purple light D6810 scanner, the resolution is 600dpi, and the pictures are stored in tif lossless format. In the present invention, the device for extracting the color index in the color scanning picture is preferably a seed phenotype fully automatic extraction system (phenoscan), which is developed by Nanjing Zhi nong cloud core big data technology Co., Ltd and China university of agriculture, seed science and technology research center, wherein the color index includes Red (Red in three primary colors), Green (Green in three primary colors), Blue (Blue in three primary colors), Luminosity (brightness), a (range from Red to Green), B (range from Blue to yellow), Hue, Satution (Saturation), Value (brightness), Gray (Gray scale), average Value and standard deviation under 20 color indexes, namely R _ mean, R _ std, G _ mean, G _ std, B _ mean, B _ std, L _ mean, L _ std, a _ mean, B _ mean, L _ std, a _ mean, a _ std, B _ mean _ med, b _ std, H _ mean, H _ std, S _ mean, S _ std, V _ mean, V _ std, Gray _ mean, and Gray _ std. And taking the average value of the color indexes of each group of seeds. In the invention, the scanner and the phenospeed software are adopted for extracting the color characteristics, so that the cost is lower and the method is quick. Besides the full-automatic seed morphology extraction system, the software for extracting the color features also comprises OpenCV.
In the invention, the color indexes preferably comprise R _ mean, G _ mean, B _ mean and Gray _ mean, and the establishment of the multiple linear regression model by using the four color indexes can enable the acquisition of the color scanning picture of the sample to be more convenient and faster. In the implementation process of the present invention, the color index preferably further includes: hue, saturation, brightness, range from red to green, and range from blue to yellow.
In the invention, the seeds are placed into a single layer when being scanned or photographed, and the seeds are not separated from each other specially.
Before the astragalus seeds are tiled, preferably classifying the astragalus seeds according to colors, and mixing the astragalus seeds with different colors according to different proportions to obtain the astragalus seeds of different groups.
In the present invention, the color preferably includes one or more of black, brown and yellow; the brown color includes dark brown and yellow brown, which can be distinguished by naked eyes.
After obtaining astragalus seeds of different groups, the invention preferably also comprises randomly dividing the astragalus seeds of different groups into a training set and a verification set for establishing a subsequent astragalus seed chlorophyll content multiple linear regression prediction model; the training set is used to train a model; the validation set is used for verifying model prediction accuracy; the ratio of the number of samples in the training set to the number of samples in the validation set is preferably 7: 3.
extracting color indexes in color scanning images or color photographs of each group of astragalus seeds, calculating an average value, screening the characteristic indexes by different screening methods, and respectively establishing a multiple linear regression prediction model for the screened characteristic indexes; and comparing the characteristic variable extraction methods, selecting a method with high prediction rate and few contained variables, and simplifying the model.
In the specific implementation process of the invention, the invention preferably further comprises the steps of carrying out correlation analysis, principal component analysis and screening of different characteristic indexes on the extracted color indexes, and removing repeated influence factors which are weakly related to chlorophyll content prediction, thereby realizing optimization and dimension reduction of the characteristic indexes and effectively improving the training efficiency of the model. In the specific implementation process of the invention, before the multiple linear regression analysis, the distribution of data is considered and the normality of variables is analyzed. In order to better screen and clarify a phenotype index related to the chlorophyll content of the seeds.
The invention also provides application of the determination model constructed by the construction method in the scheme in determination of the content of chlorophyll in the astragalus seeds.
In the present invention, the application comprises the following steps:
measuring the color index of the astragalus seeds to be detected;
inputting the color index serving as an input factor into a measurement model obtained by the construction method in the scheme, and outputting the chlorophyll content of the astragalus seeds to be measured
In the specific implementation process of the invention, the color index is used as an independent variable, the chlorophyll content is used as a dependent variable, and the stepwise regression method is used for establishing the multi-linear regression prediction of the chlorophyll content of the astragalus seedsAnd (4) modeling. All variables are incorporated into the regression equation by using stepwise regression methods, typically by adjusting R2Indicating how well the linear equation can be reflected in the real data, the Durbin-Watson statistic is typically used to determine whether there is an autocorrelation between the data. The VIF value is usually used for judging whether the independent variables have collinearity, and the VIF value smaller than 10 indicates that the collinearity does not exist among the independent variables, so that the model operation is more accurate.
The technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
The flow schematic diagram of the method for measuring the chlorophyll content of astragalus seeds provided by the embodiment of the invention is shown in figure 1.
The method comprises the following steps of manually dividing astragalus seeds into dark seeds and light seeds according to the color of the astragalus seeds, wherein the dark color refers to black brown, and the light color refers to yellow or yellow brown, determining that 5g of the seeds are determined in the embodiment, and measuring 50 groups, wherein 5g of the dark seeds and 0g of the light seeds are adopted; 4.9g of dark color, 0.1g of light color; 4.8g dark, 0.2g light.
Determining the mass of each group of seeds to be 5g according to a FluoMini Pro optical Chlorophyll Fluorescence (CF) detector, measuring the chlorophyll content of the astragalus seeds mixed according to a certain proportion by using the FluoMini Pro optical Chlorophyll Fluorescence (CF) detector, measuring each group for 6 times, taking an average value, and measuring 50 groups in total.
The astragalus seeds with known chlorophyll content are scanned by a Qinghua purple light D6810 scanner, the resolution is 600dpi, and the pictures are stored in tif lossless format. Extraction of seed phenotype index was performed using a seed phenotype fully automatic extraction system (PhenoSeed, co-developed by Nanjing Zhi nong cloud core big data technology Co., Ltd. and China university of agriculture for seed science and technology research), wherein the color index includes Red (Red of three primary colors), Green (Green of three primary colors), Blue (Blue of three primary colors), Luminosity, a (range from Red to Green), B (range from Blue to yellow), Hue, Saturation, Value (brightness), mean and standard deviation under Gray (Gray scale), for a total of 20 color indexes (R _ mean, R _ std, G _ mean, G _ std, B _ mean, B _ std, L _ mean, L _ std, a _ mean, a _ d, B _ mean, B _ std, H _ mean, H _ std, S _ mean, S _ std, V _ V _ std, H _ std, S _ V _ std, S _ m, S, Gray mean, Gray std). And taking the average value of the color indexes of each group of seeds.
Dividing 50 parts of astragalus seed material data into a training set (35 parts) and a verification set (15 parts), then establishing a multiple linear regression equation by using all color indexes, main component factors extracted after analyzing main components of all color indexes, all color average indexes, main component factors extracted after analyzing main components of all color average indexes, and four indexes of R _ mean, G _ mean, B _ mean and Gray _ mean as independent variables and using chlorophyll content as a dependent variable.
Before performing multiple linear regression analysis, the distribution of data is considered first, and the normality of variables is analyzed. In order to better screen and clarify a phenotype index related to the chlorophyll content of the seeds. Wherein, all color indexes were subjected to principal component analysis as shown in table 1: finally, 3 principal component factors are extracted, the cumulative variance contribution rate is 95.898%, and the extracted factors can reflect the information content of nearly 95.898% of the original total variables.
TABLE 1 Total color index impact factor principal component eigenvalues, contribution rates and cumulative contribution rates
Figure BDA0003089365720000061
The overall color average index was subjected to principal component analysis, as shown in table 2: finally, 2 principal component factors are extracted, the cumulative variance contribution rate is 96.442%, and the extracted factors can reflect the information content of nearly 96.442% of the original total variables.
TABLE 2 Total color average index impact factor principal component eigenvalue, contribution rate and cumulative contribution rate
Figure BDA0003089365720000071
After the pretreatment is finished, various characteristic indexes and main component factors are respectively adopted as independent variables, chlorophyll content is used as dependent variables, and a stepwise regression method is used for establishing a multi-linear regression prediction model of chlorophyll content of the astragalus seeds. By incorporating all variables into the regression equation using stepwise regression, the extent to which a linear equation can be reflected on real data is generally expressed by adjusting R2, and the Durbin-Watson statistic is commonly used to determine whether there is an autocorrelation between data. The VIF value is usually used for judging whether the independent variables have collinearity, and the VIF value smaller than 10 indicates that the collinearity does not exist among the independent variables, so that the model operation is more accurate.
Five models are respectively established by using the total color index (a), the principal component factor (B) extracted after the analysis of the principal component of the total color index, the total color average index (c), the principal component factor (d) extracted after the analysis of the principal component of the total color average index, and four indexes (e) of R _ mean, G _ mean, B _ mean and Gray _ mean as independent variables, and the prediction results of the models are shown in Table 3. There was no significant difference between the five models, and the resulting adjusted R2The data are all about 0.98, which shows that the linear equation has good reflection degree on real data. In the research, Durbin-Watson statistics are all around 1.8 and close to 2, so that the data can be basically explained to have no autocorrelation. FIG. 2 is a graph of the training effect of five multiple linear regression models established for different characteristic indexes.
TABLE 3 Astragalus membranaceus seed chlorophyll content multiple linear regression prediction model summary
Figure BDA0003089365720000072
Table 4 shows the results of the five model chlorophyll content multiple linear regression, and it can be seen from the significance levels that the significance levels corresponding to the independent variables of the models are less than 0.05, which indicates that the independent variables can significantly affect the chlorophyll content of the dependent variable. In addition, by observing the VIF, the fact that no collinearity exists between independent variables can be judged, and model operation is more accurate.
TABLE 4 Multi-element linear regression prediction model results for chlorophyll content of astragalus seeds
Figure BDA0003089365720000081
Note: the factors 1, 2 and 3 are the main component factors 1, 2 and 3 extracted by the main component analysis.
The five models were then verified using 15 samples (verification set) of astragalus seeds, respectively, with the results shown in fig. 3. The chlorophyll content predicted value is distributed near the true value, and the predicted result is better.
According to the embodiment of the invention, the sample astragalus seeds are used for respectively establishing the chlorophyll content determination models based on various characteristic indexes and main component factors, and the result shows that the established models predict the chlorophyll content R2Around 0.98, there were no significant differences between the five types of models. Therefore, in practical application, the establishment of the multiple linear regression model is only carried out by acquiring four indexes of R _ mean, G _ mean, B _ mean and Gray _ mean, so that the acquisition of a sample image is more convenient and faster. After the identification model is established by using the sample, the model is stored, and after the model is loaded and used, the prediction accuracy of the chlorophyll content is extremely high.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (6)

1. A method for constructing a model for measuring the chlorophyll content of astragalus seeds comprises the following steps:
1) extracting color indexes of astragalus seeds with different known chlorophyll contents;
2) establishing a multiple linear regression equation of a training set by taking the color index as an independent variable and the chlorophyll content as a dependent variable to obtain a chlorophyll content measuring model of the astragalus seeds;
the color index comprises red, green, blue and gray; and measuring each color index for 5-7 times and taking an average value.
2. The building method according to claim 1, wherein the method of extracting the color index includes:
and (3) tiling, scanning or photographing the astragalus seeds to obtain color scanning images or color photos of the astragalus seeds, extracting color indexes in the color scanning images or color photos of each group of astragalus seeds and calculating an average value.
3. The method of claim 2, wherein before the step of tiling the astragalus seeds, the method further comprises: classifying the astragalus seeds according to colors, and mixing the astragalus seeds with different colors according to different proportions to obtain astragalus seeds of different groups.
4. The construction method according to claim 1, wherein the chlorophyll content is an average value of chlorophyll content obtained by measuring 5-7 times.
5. The application of the determination model constructed by the construction method of any one of claims 1 to 4 in the determination of the chlorophyll content of astragalus seeds.
6. The use according to claim 5, wherein the determination of the chlorophyll content of the astragalus seeds comprises the following steps:
measuring the color index of the astragalus seeds to be detected;
inputting the color index serving as an input factor into a determination model obtained by the construction method according to any one of claims 1 to 5, and outputting the chlorophyll content of the astragalus membranaceus seed to be detected.
CN202110590590.8A 2021-05-28 2021-05-28 Construction method and application of astragalus seed chlorophyll content determination model Pending CN113324921A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110590590.8A CN113324921A (en) 2021-05-28 2021-05-28 Construction method and application of astragalus seed chlorophyll content determination model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110590590.8A CN113324921A (en) 2021-05-28 2021-05-28 Construction method and application of astragalus seed chlorophyll content determination model

Publications (1)

Publication Number Publication Date
CN113324921A true CN113324921A (en) 2021-08-31

Family

ID=77421964

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110590590.8A Pending CN113324921A (en) 2021-05-28 2021-05-28 Construction method and application of astragalus seed chlorophyll content determination model

Country Status (1)

Country Link
CN (1) CN113324921A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105651713A (en) * 2015-12-30 2016-06-08 浙江工业大学 Quantitative determination method for chlorophyll of green vegetable leaves based on computer image analysis
CN106971409A (en) * 2017-02-23 2017-07-21 北京农业信息技术研究中心 Maize canopy leaf color modeling and method
JP2019000088A (en) * 2017-06-19 2019-01-10 満明 児玉 Paddy rice growth evaluation method and device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105651713A (en) * 2015-12-30 2016-06-08 浙江工业大学 Quantitative determination method for chlorophyll of green vegetable leaves based on computer image analysis
CN106971409A (en) * 2017-02-23 2017-07-21 北京农业信息技术研究中心 Maize canopy leaf color modeling and method
JP2019000088A (en) * 2017-06-19 2019-01-10 満明 児玉 Paddy rice growth evaluation method and device

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
关静 等主编: "《实用多元统计分析》", 31 March 2020, 天津大学出版社 *
刘炜: "基于图像处理的乳瓜叶片叶绿素含量预测研究", 《中国优秀博硕士学位论文全文数据库(硕士)农业科技辑》 *
张传雷 等著: "《基于图像分析的植物及其病虫害识别方法研究》", 31 October 2018 *
易时来 等: "锦橙叶片叶绿素含量诊断模型", 《农机化研究》 *

Similar Documents

Publication Publication Date Title
CN100480680C (en) Multiple spectrum meat freshness artificial intelligence measurement method and system
CN107144353B (en) A kind of textile chromatism measurement method based on digital camera
CN106991679A (en) One kind quantifies recognition methods based on cloud platform urine test paper physical signs
CN101426150B (en) Video image quality evaluation method and system
CN103076288B (en) A kind of flesh of fish self-grading device based on computer vision and method
CN109121437A (en) For assessing the method and system of histological stain
CN109323999B (en) Spectrophotometric detection method based on image numerical analysis
JP3581149B2 (en) Method and apparatus for identifying an object using a regular sequence of boundary pixel parameters
CN104198325B (en) Stem ratio measuring method in pipe tobacco based on computer vision
CN105466921A (en) Simultaneous detection method of many samples
CN109827957B (en) Rice leaf SPAD value estimation method and system based on computer vision
CN110044485B (en) Image type fabric color measuring method
CN201041553Y (en) Fruit quality non-damage detection system base on multi-spectrum imaging technology
CN111879709A (en) Method and device for detecting spectral reflectivity of lake water body
CN110009609B (en) Method for rapidly detecting yellow rice
CN109030488B (en) Algae biomass detection method and device
CN113570538B (en) Blade RGB image bias distribution parameter information acquisition and analysis method
CN112884058A (en) Fritillaria variety identification method and system based on image and hyperspectrum combination
KR101901812B1 (en) A method for discriminating new rice and staled rice using electronic eye
CN113324921A (en) Construction method and application of astragalus seed chlorophyll content determination model
Barman et al. Predication of soil pH using K mean segmentation and HSV color image processing
KR102082102B1 (en) Soil classification estimation method and soil moisture percentage estimation method using soil image
RU2638910C1 (en) Method of object express control
CN115880257A (en) Method for rapidly predicting intensity of ocean porous reef limestone
CN114486895A (en) Method for detecting sample substance concentration based on pushing of urine drying test strip to identification

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