scispace - formally typeset
Proceedings ArticleDOI: 10.1109/ESCI50559.2021.9396972

N-CNN Based Transfer Learning Method for Classification of Powdery Mildew Wheat Disease

05 Mar 2021-pp 707-710
Abstract: Powdery wheat (PW) is one of the most common wheat diseases in northern India. It is the most damaging wheat disease and it is prevalent in April to May season. Several methods of machine learning (ML) and Deep Learning (DL) methods are used to do wheat disease classification. The previous DL techniques have not achieved higher accuracy during PW wheat disease classification. In the current study, 450 wheat images are collected from primary and secondary sources. The normalization technique is used for preprocessing. These normalized preprocessed images are input to CNN. The normalized images increase the training and testing accuracy of CNN. Then, this pre-trained model is applied to the CIAGR images dataset via transfer learning method. During testing with images, CNN achieves 89.9% classification accuracy for PW wheat disease. After these pre-trained model is applied to CIAGR dataset images and achieves 86.5% classification accuracy. Moreover, the result shows that pre-trained NCNN model achieves higher accuracy during transfer learning.

... read more

Topics: Common wheat (54%)

5 results found

Open accessProceedings ArticleDOI: 10.1109/ICRITO51393.2021.9596073
03 Sep 2021-
Abstract: There is a rainy season occurs during the period from June to august in almost all geographical parts of India. Moreover, some of the states like Uttarakhand, Cherapunji, Mumbai, Tamil Nadu etc. may suffer from some natural disaster. If we early predict such misfortunes through the variety of big data collected for such distinct positions at a particular amount of time then certainly can save the life and goods from such big natural calamities. Such normalized data can be updated at a regular interval of time. In view of this, the time series data analysis provides a method to early aware and protects the life of people from such natural disasters. The proposed method exploited the use the Radial Basis Function Neural Network Model with back propagation algorithm to make compatible with time series data analysis to forecast the predication of rainfall for the state of Punjab, India. In this technique, two types of predictions are used which are based on fifteen and twenty days. The comparison results reveal those fifteen days prediction provides more effective classification accuracy than twenty days prediction.

... read more

Proceedings ArticleDOI: 10.1109/SPIN52536.2021.9566079
26 Aug 2021-
Abstract: Detection of plant crop diseases has become an active field of research day by day due to increasing the demand for such systems and techniques as crop diseases are now become a common part of agriculture. Focusing on this demand and need, we have developed a Convolutional neural network (CNN)-based Deep learning (DL) multi-classification model which classifies the total of 900 real-time collected images of potato crop plants having healthy and potato blight (PB) disease images based on their PB disease severity level, along with this binary classification has also been done to simply classify the healthy and disease crop leaf. A total of four disease severity levels have been taken into account which resulted in a binary classification accuracy of 90.77% and 94.77% of best multi-classification accuracy. This work will be a great contribution in the field of potato disease recognition and detection using DL approaches.

... read more

Proceedings ArticleDOI: 10.1109/SPIN52536.2021.9566053
26 Aug 2021-
Abstract: The wide variety of diseases in the tomato plant affects the quality and quantity of the production. To counteract the problem of disease in tomato plants deep learning (DL) based convolutional neural networks (CNN) model has been presented in this paper that classify the real-time and self-captured 3000 images of healthy and tomato spotted wilt (TSW) disease plants. TSW is a type of infected virus that turns the upper sides of young tomato leaves as bronze and eventually acquires prominent, necrotic spots. Binary and multi-classification of the collected dataset have been made based on three different types of severity levels of TSW disease. In the case of binary classification, the accuracy is recorded at 91.56% and on the other hand, the best accuracy of multi-classification is recorded at 95.23% in the case of middle severity level. The model shows the least accuracy 94.5% and middle accuracy 95.2% in the case of early-stage severity and late severity level respectively. The proposed work will make a significant addition to the field of employing DL techniques to detect and classify tomato diseases.

... read more

Open accessProceedings ArticleDOI: 10.1109/ICRITO51393.2021.9596540
03 Sep 2021-
Abstract: A simple Convolutional neural network (CNN) based deep learning (DL) model has been proposed for multi-classification of corn gray leaf spot (CGLS) disease based on five different severity levels of CGLS disease on the corn plant. Certain corn leaf diseases like CGLS, common rust, and leaf blight are quite common and dangerous in corn harvest. Hence, the current work presents a solution for CGLS disease detection on corn plants using a multi-classification DL model which gives the best detection accuracy of 95.33% in high-risk severity level image. Along with this comparison of five different severity levels has also been conducted based on resulted performance measures (PM).

... read more


19 results found

Journal ArticleDOI: 10.1016/J.COMPAG.2004.04.003
Dimitrios Moshou1, C. Bravo1, Jonathan West2, Stijn Wahlen1  +2 moreInstitutions (2)
Abstract: Excessive use of pesticides for plant disease treatment increases costs and raises the danger of toxic residue levels on agricultural products. As pesticides are among the highest components in the production costs of field crops and have been identified as a major contributor to ground water contamination, their use must be minimised. This can be achieved by more precise targeting of pesticides to those places in the field where they are needed. Therefore, a simple and cost-effective optical device is needed for remote disease detection, based on canopy reflectance in several wavebands. In this study, the difference in spectral reflectance between healthy and diseased wheat plants was investigated at an early stage in the development of the “yellow rust” disease. In-field spectral images were taken with a spectrograph mounted at spray boom level. A normalisation method based on reflectance and light intensity adjustments was developed. An innovative technique for visualisation of data properties and interrelations between variables is presented, based on Self-Organizing Maps. Disease detection algorithms were developed, based on neural networks. Through the use of neural networks and more specifically multilayer perceptrons, classification performance increased from 95% to more than 99% using a total of 5137 leaf spectra for evaluation. These results encourage prospects for the development of a cost-effective optical device for recognising diseases at an early stage.

... read more

Topics: Plant disease (56%), Light intensity (53%)

225 Citations

Journal ArticleDOI: 10.1016/J.COMPAG.2012.03.006
Jingcheng Zhang1, Ruiliang Pu1, Jihua Wang2, Wenjiang Huang2  +2 moreInstitutions (2)
Abstract: Powdery mildew (Blumeria graminis) is one of the most destructive diseases, which has a significant impact on the production of winter wheat. Detecting powdery mildew via spectral measurement and analysis is a possible alternative to traditional methods in obtaining the spatial distribution information of the disease. In this study, hyperspectral reflectances of normal and powdery mildew infected leaves were measured with a spectroradiometer in a laboratory. A total of 32 spectral features (SFs) were extracted from the lab spectra and examined through a correlation analysis and an independent t-test associated with the disease severity. Two regression models: multivariate linear regression (MLR) and partial least square regression (PLSR) were developed for estimating the disease severity of powdery mildew. In addition, the fisher linear discriminant analysis (FLDA) was also adopted for discriminating the three healthy levels (normal, slightly-damaged and heavily-damaged) of powdery mildew with the extracted SFs. The experimental results indicated that (1) most SFs showed a clear response to powdery mildew; (2) for estimating the disease severity with SFs, the PLSR model outperformed the MLR model, with a relative root mean square error (RMSE) of 0.23 and a coefficient of determination (R^2) of 0.80 when using seven components; (3) for discrimination analysis, a higher accuracy was produced for the heavily-damaged leaves by FLDA with both producer's and user's accuracies over 90%; (4) the selected broad-band SFs revealed a great potential in estimating the disease severity and discriminating severity levels. The results imply that multispectral remote sensing is a cost effective method in the detection and mapping of powdery mildew.

... read more

Topics: Powdery mildew (65%), Blumeria graminis (50%)

117 Citations

Open accessJournal ArticleDOI: 10.1016/J.COMPAG.2017.09.012
Jiang Lu1, Jie Hu1, Guannan Zhao1, Fenghua Mei  +1 moreInstitutions (1)
Abstract: Crop diseases are responsible for the major production reduction and economic losses in agricultural industry worldwide Monitoring for health status of crops is critical to control the spread of diseases and implement effective management This paper presents an in-field automatic wheat disease diagnosis system based on a weakly supervised deep learning framework, ie deep multiple instance learning, which achieves an integration of identification for wheat diseases and localization for disease areas with only image-level annotation for training images in wild conditions Furthermore, a new in-field image dataset for wheat disease, Wheat Disease Database 2017 (WDD2017), is collected to verify the effectiveness of our system Under two different architectures, ie VGG-FCN-VD16 and VGG-FCN-S, our system achieves the mean recognition accuracies of 9795% and 9512% respectively over 5-fold cross-validation on WDD2017, exceeding the results of 9327% and 7300% by two conventional CNN frameworks, ie VGG-CNN-VD16 and VGG-CNN-S Experimental results demonstrate that the proposed system outperforms conventional CNN architectures on recognition accuracy under the same amount of parameters, meanwhile maintaining accurate localization for corresponding disease areas Moreover, the proposed system has been packed into a real-time mobile app to provide support for agricultural disease diagnosis

... read more

Topics: Wheat diseases (54%)

111 Citations

Journal ArticleDOI: 10.1016/J.COMPAG.2011.09.011
Christoph Römer1, Kathrin Bürling1, Mauricio Hunsche1, Till Rumpf1  +2 moreInstitutions (1)
Abstract: Early recognition of pathogen infection is of great relevance in precision plant protection. Pre-symptomatic disease detection is of particular interest. By use of a laserfluoroscope, UV-light induced fluorescence data were collected from healthy and with leaf rust inoculated wheat leaves of the susceptible cultivar Ritmo 2-4days after inoculation under controlled conditions. In order to evaluate pathogen impact on fluorescence spectra 215 wavelengths in the range of 370-800nm were recorded. The medians of fluorescence signatures suggest that inoculated leaves may be separated from healthy ones, but high-frequency oscillations and individual reactions of leaves indicate that separability is difficult to achieve. The misbalance between the high number of measured wavelengths and the low number of training examples induces a high overfitting risk. For a pre-symptomatic pathogen identification a small number of robust features was desired which comprise most of the information relevant for the given classification task. Instead of choosing only the most relevant wavelengths, the coefficients of polynomials fitting the spectra were used for classification. They specify the global curve characteristics. Piecewise fitting by polynomials of fourth order led to high classification accuracy. Support Vector Machines were used for classification. Cross validation demonstrated that the achieved classification accuracy reached 93%. This result could be attained on the second day after inoculation, before any visible symptoms appeared. The described method is of general interest for pre-symptomatic pathogen detection based on fluorescence spectra.

... read more

64 Citations

Proceedings ArticleDOI: 10.1109/ICNC.2012.6234701
29 May 2012-
Abstract: Plant disease identification based on image processing could quickly and accurately provide useful information for the prediction and control of plant diseases. In this study, 21 color features, 4 shape features and 25 texture features were extracted from the images of two kinds wheat diseases (wheat stripe rust and wheat leaf rust) and two kinds of grape diseases (grape downy mildew and grape powdery mildew), principal component analysis (PCA) was performed for reducing dimensions in feature data processing, and then neural networks including backpropagation (BP) networks, radial basis function (RBF) neural networks, generalized regression networks (GRNNs) and probabilistic neural networks (PNNs) were used as the classifiers to identify wheat diseases and grape diseases, respectively. The results showed that these neural networks could be used for image recognition of these diseases based on reducing dimensions using PCA and acceptable fitting accuracies and prediction accuracies could be obtained. For the two kinds of wheat diseases, the optimal recognition result was obtained when image recognition was conducted based on PCA and BP networks, and the fitting accuracy and the prediction accuracy were both 100%. For the two kinds of grape diseases, the optimal recognition results were obtained when GRNNs and PNNs were used as the classifiers after reducing the dimensions of feature data with PCA, and the prediction accuracies were 94.29% with the fitting accuracies equal to 100%.

... read more

Topics: Plant disease (55%), Wheat diseases (52%), Artificial neural network (51%) ... show more

46 Citations