scholarly journals Rice Leaf Blast Classification Method Based on Fused Features and One-Dimensional Deep Convolutional Neural Network

2021 ◽  
Vol 13 (16) ◽  
pp. 3207
Author(s):  
Shuai Feng ◽  
Yingli Cao ◽  
Tongyu Xu ◽  
Fenghua Yu ◽  
Dongxue Zhao ◽  
...  

Rice leaf blast, which is seriously affecting the yield and quality of rice around the world, is a fungal disease that easily develops under high temperature and humidity conditions. Therefore, the use of accurate and non-destructive diagnostic methods is important for rice production management. Hyperspectral imaging technology is a type of crop disease identification method with great potential. However, a large amount of redundant information mixed in hyperspectral data makes it more difficult to establish an efficient disease classification model. At the same time, the difficulty and small scale of agricultural hyperspectral imaging data acquisition has resulted in unrepresentative features being acquired. Therefore, the focus of this study was to determine the best classification features and classification models for the five disease classes of leaf blast in order to improve the accuracy of grading the disease. First, the hyperspectral imaging data were pre-processed in order to extract rice leaf samples of five disease classes, and the number of samples was increased by data augmentation methods. Secondly, spectral feature wavelengths, vegetation indices and texture features were obtained based on the amplified sample data. Thirdly, seven one-dimensional deep convolutional neural networks (DCNN) models were constructed based on spectral feature wavelengths, vegetation indices, texture features and their fusion features. Finally, the model in this paper was compared and analyzed with the Inception V3, ZF-Net, TextCNN and bidirectional gated recurrent unit (BiGRU); support vector machine (SVM); and extreme learning machine (ELM) models in order to determine the best classification features and classification models for different disease classes of leaf blast. The results showed that the classification model constructed using fused features was significantly better than the model constructed with a single feature in terms of accuracy in grading the degree of leaf blast disease. The best performance was achieved with the combination of the successive projections algorithm (SPA) selected feature wavelengths and texture features (TFs). The modeling results also show that the DCNN model provides better classification capability for disease classification than the Inception V3, ZF-Net, TextCNN, BiGRU, SVM and ELM classification models. The SPA + TFs-DCNN achieved the best classification accuracy with an overall accuracy (OA) and Kappa of 98.58% and 98.22%, respectively. In terms of the classification of the specific different disease classes, the F1-scores for diseases of classes 0, 1 and 2 were all 100%, while the F1-scores for diseases of classes 4 and 5 were 96.48% and 96.68%, respectively. This study provides a new method for the identification and classification of rice leaf blast and a research basis for assessing the extent of the disease in the field.

2021 ◽  
Author(s):  
Guosheng Zhang ◽  
Tongyu Xu ◽  
Youwen Tian ◽  
Shuai Feng ◽  
Dongxue Zhao ◽  
...  

Abstract Background: Hyperspectral imaging is an emerging technology applied in plant disease research, including disease detection, multiple disease identification, disease severity assessment, and disease resistance evaluation. Rice leaf blast is prevalent all over the world and is a serious threat to rice yield and quality. In this paper, the standard deviation (STD) of the spectral reflectance of whole leaves was calculated and a support vector machine (SVM) model was built to classify the degree of rice leaf blast at different growth stages.Results: The classification accuracy of the full-spectrum-based SVM model at jointing stage, booting stage and heading stage was 94.44%, 81.58% and 80.48%, respectively. The corresponding macro recall values were 0.9714, 0.715 and 0.79. The average STD of the spectral reflectance of the whole leaf differed not only within samples with different disease grades, but also those with the same disease level. Conclusion: The STD of the spectral reflectance of whole leaf could be utilized to classify the rice leaf blast degree at different growth stages. The classification method was derived from physiological phenomena that were visible to the naked eye, making it more intuitive and convincing.


2020 ◽  
Vol 49 (5) ◽  
pp. 571-578 ◽  
Author(s):  
GuoSheng Zhang ◽  
TongYu Xu ◽  
YouWen Tian ◽  
Han Xu ◽  
JiaYu Song ◽  
...  

Author(s):  
Aoife Gowen ◽  
Jun-Li Xu ◽  
Ana Herrero-Langreo

Applications of hyperspectral imaging (HSI) to the quantitative and qualitative measurement of samples have grown widely in recent years, due mainly to the improved performance and lower cost of imaging spectroscopy instrumentation. Data sampling is a crucial yet often overlooked step in hyperspectral image analysis, which impacts the subsequent results and their interpretation. In the selection of pixel spectra for the calibration of classification models, the spatial information in HSI data can be exploited. In this paper, a variety of sampling strategies for selection of pixel spectra are presented, exemplified through five case studies. The strategies are compared in terms of the proportion of global variability captured, practicality and predictive model performance. The use of variographic analysis as a guide to the spatial segmentation prior to sampling leads to the selection of representative subsets while reducing the variation in model performance parameters over repeated random selection.


1992 ◽  
Vol 58 (2) ◽  
pp. 259-266 ◽  
Author(s):  
Kiyoshi ISHIGURO ◽  
Seiichi TAKECHI ◽  
Akira HASHIMOTO

Plant Disease ◽  
2021 ◽  
Author(s):  
Mariam Barro ◽  
Abalo Itolou Kassankogno ◽  
Issa Wonni ◽  
Drissa SEREME ◽  
Irénée SOMDA ◽  
...  

Multiple constraints affect rice yields and global production in West Africa. Among these constraints are viral, bacterial and fungal pathogens. We aimed to describe the spatiotemporal patterns of occurrence and incidence of multiple rice diseases in farmers’ fields in contrasting rice growing systems in western Burkina Faso. For this purpose, we selected a set of three pairs of sites, each comprising an irrigated area and a neighboring rainfed lowland, and studied them over four consecutive years. We first performed interviews with the rice farmers to better characterize the management practices at the different sites. This study revealed that the transplanting of rice and the possibility of growing rice twice a year are restricted to irrigated areas, while other practices, such as the use of registered rice cultivars, fertilization and pesticides, are not specific but differ between the two rice growing systems. Then, we performed symptom observations at these study sites to monitor the following four diseases: yellow mottle disease, Bacterial Leaf Streak (BLS), rice leaf blast and brown spot. The infection rates were found to be higher in irrigated areas than in rainfed lowlands, both when analyzing all observed symptoms together (any of the four diseases) and when specifically considering each of the two diseases: BLS and rice leaf blast. Brown spot was particularly prevalent in all six study sites, while yellow mottle disease was particularly structured geographically. Various diseases were frequently found together in the same field (co-occurrence) or even on the same plant (coinfection), especially in irrigated areas.


2021 ◽  
Vol 11 ◽  
Author(s):  
Yanjie Li ◽  
Mahmoud Al-Sarayreh ◽  
Kenji Irie ◽  
Deborah Hackell ◽  
Graeme Bourdot ◽  
...  

Weeds can be major environmental and economic burdens in New Zealand. Traditional methods of weed control including manual and chemical approaches can be time consuming and costly. Some chemical herbicides may have negative environmental and human health impacts. One of the proposed important steps for providing alternatives to these traditional approaches is the automated identification and mapping of weeds. We used hyperspectral imaging data and machine learning to explore the possibility of fast, accurate and automated discrimination of weeds in pastures where ryegrass and clovers are the sown species. Hyperspectral images from two grasses (Setaria pumila [yellow bristle grass] and Stipa arundinacea [wind grass]) and two broad leaf weed species (Ranunculus acris [giant buttercup] and Cirsium arvense [Californian thistle]) were acquired and pre-processed using the standard normal variate method. We trained three classification models, namely partial least squares-discriminant analysis, support vector machine, and Multilayer Perceptron (MLP) using whole plant averaged (Av) spectra and superpixels (Sp) averaged spectra from each weed sample. All three classification models showed repeatable identification of four weeds using both Av and Sp spectra with a range of overall accuracy of 70–100%. However, MLP based on the Sp method produced the most reliable and robust prediction result (89.1% accuracy). Four significant spectral regions were found as highly informative for characterizing the four weed species and could form the basis for a rapid and efficient methodology for identifying weeds in ryegrass/clover pastures.


2013 ◽  
Vol 38 (5) ◽  
pp. 387-397 ◽  
Author(s):  
Ana P.A. Sena ◽  
Amanda A. Chaibub ◽  
Márcio V.C.B. Côrtes ◽  
Gisele B. Silva ◽  
Valácia L. Silva-Lobo ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document