An Investigation Into Machine Learning Regression Techniques for the Leaf Rust Disease Detection Using Hyperspectral Measurement

Ashourloo, Davoud; Aghighi, Hossein; Matkan, A A; Mobasheri, Mohammad Reza; Rad, Amir Moeini

doi:10.1109/jstars.2016.2575360

Cited by 148 publications

(51 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Use of average spectra of hyperspectral imaging was the same as Vis/NIR spectroscopy. The differences was that the spectra of Vis/NIR spectroscopy were collected from a small part of the leaves [ 41 , 42 ] and each sample has one spectra averaged by several times of scans, while average spectra of hyperspectral imaging was acquired from a predefined region of interest (ROI) in the sample. The use of average spectra of infected samples had two situations, average spectra of the entire sample including the infected region and the healthy region within the sample, and average spectra of only the infected region [ 40 , 41 ].…”

Section: Discussionmentioning

confidence: 99%

“…After selecting representative spectra, chemometrics was another essential important issue to be addressed. To bring hyperspectral imaging to real-world application, qualitative analysis of spectral features was not enough, discriminant models should be built [ 42 , 43 ]. Without robust and accurate models, real-world application of hyperspectral imaging was impossible to achieve.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Kong

Zhang

Huang

et al. 2018

Sensors

View full text Add to dashboard Cite

Hyperspectral imaging covering the spectral range of 384–1034 nm combined with chemometric methods was used to detect Sclerotinia sclerotiorum (SS) on oilseed rape stems by two sample sets (60 healthy and 60 infected stems for each set). Second derivative spectra and PCA loadings were used to select the optimal wavelengths. Discriminant models were built and compared to detect SS on oilseed rape stems, including partial least squares-discriminant analysis, radial basis function neural network, support vector machine and extreme learning machine. The discriminant models using full spectra and optimal wavelengths showed good performance with classification accuracies of over 80% for the calibration and prediction set. Comparing all developed models, the optimal classification accuracies of the calibration and prediction set were over 90%. The similarity of selected optimal wavelengths also indicated the feasibility of using hyperspectral imaging to detect SS on oilseed rape stems. The results indicated that hyperspectral imaging could be used as a fast, non-destructive and reliable technique to detect plant diseases on stems.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Kong

Zhang

Huang

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Fuzzy logic, neural network and machine learning have been applied to learn about the patterns of diseases [11,12]. The authors of paper [14] described regression based methods for leaf rust disease detection on wheat plant leaves. Experiments were conducted using Partial Least Square Regression (PSLR), support Vector Regression(SVR), ν-Support Vector regression(ν-SVR), and Gaussian process regression (GPR).…”

Section: Leaf Disease Detection Methodsmentioning

confidence: 99%

Nature Inspired Algorithms as a Tool for Diseased Millets Leaf Segmentation

2020

IJEAT

View full text Add to dashboard Cite

Agriculture is the main occupation undertaken by majority of population in India. The Indian farmers produce food grains for entire population. Growing population needs constant increase in quantity and quality of agriculture produce. This is possible only by adopting improved technology in production and plant protection. Hence, technology intervention is at every stage of production and food processing is needed. Timely and suitable plant protection measures directly improve quantity and quality of agriculture produce. Effective result oriented plant protection mainly involves early detection of pest and diseases and suitable control measures. The entire human population consume products of food grains like cereals and millets as their staple food. This paper aims at summarizing common image processing methods to identify plant diseases and how it could be improved using nature inspired algorithm.

show abstract

“…For classification tasks like image classification, face recognition, as well as plant disease identification, it is commonly believed that machine learning techniques require sufficient training data per subject that can span the variations of testing samples. However, acquiring appropriate and useful agricultural data is usually laborious and time-consuming [ 22 ]; only a few training samples per subject can be offered in many practical cases, thus, the trained models derived from insufficient training samples lack good ability of generalization and hence, may be unsuitable for testing samples with unsatisfactory performances. For this problem, an ECR-based classification model is presented and then, cucumber disease recognition is used as a proof-of-concept.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Leaf Image-Based Cucumber Disease Recognition Using the Extended Collaborative Representation Model

Luo

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Collaborative representation (CR)-based classification has been successfully applied to plant disease recognition in cases with sufficient training samples of each disease. However, collecting enough training samples is usually time consuming and labor-intensive. Moreover, influenced by the non-ideal measurement environment, samples may be corrupted by variables introduced by bad illumination and occlusions of adjacent leaves. Consequently, an extended collaborative representation (ECR)-based classification model is presented in this paper. Then, it is applied to cucumber leaf disease recognition, which constructs a pure spectral library consisting of several representative samples for each disease and designs a universal variation spectral library that deals with linear variables superimposed on samples. Thus, each query sample is encoded as a linear combination of atoms from these two spectral libraries and disease identity is determined by the disease of minimal reconstruction residuals. Experiments are conducted on spectral curves extracted from normal leaves and the disease lesions of leaves infected with cucumber anthracnose and brown spot. The diagnostic accuracy is higher than 94.7% and the average online diagnosis time is short, about 1 to 1.3 ms. The results indicate that the ECR-based classification model is feasible in the fast and accurate diagnosis of cucumber leaf diseases.

show abstract

An Investigation Into Machine Learning Regression Techniques for the Leaf Rust Disease Detection Using Hyperspectral Measurement

Cited by 148 publications

References 40 publications

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Nature Inspired Algorithms as a Tool for Diseased Millets Leaf Segmentation

Hyperspectral Leaf Image-Based Cucumber Disease Recognition Using the Extended Collaborative Representation Model

Contact Info

Product

Resources

About