Framework for Detection and Classification of Soybean Diseases using Leaf Image Processing

Author Name : Varsha Alhat, Sunita Mane

ABSTRACT

Agriculture being the primary occupation in India, it is expected that the contribution of agriculture to Indian economy must be significant. However statistics show that the contribution made by agricultural sector to Gross Domestic Product (GDP) is comparatively less. More than half of the Indian people depend on agriculture for employment and for their living. The main reason for decrease in agricultural productivity is adverse climatic conditions, unseasonal rains and attack of infections and pests on the plants. Farmers encounter great difficulties in detecting and controlling plant diseases. Thus, appropriate and timely action should be taken by the farmers to detect and identify the plant disease at early stages. The proposed work will help farmers to increase their productivity by implementing automated disease detection.

The proposed work focuses on the approach based on image processing for detection of diseases of soybean plants. The acquisition of soybean images is done using mobile camera having resolution more than 2 mega pixels. The intention of this research work is to provide help to the farmers regarding the health of the plant using decision support system (DSS). Our proposed work classifies the images of soybean leaves into five classes as normal and abnormal leaves. The abnormal leaves are further classified into four disease classes as sunburn, yellow mosaic virus, grass-hopper attack and leaf blight. The support vector machine (SVM) multi-class classifier is used for classification. The performance of SVM is compared with other classifiers such as K-nearest neighbour (KNN) and artificial neural network (ANN). Finally, it can be concluded from the experimental results that this approach can classify the leaves with an average accuracy of 95.33%. 

Keywords: (K-nearest neighbour (KNN); Decision Support System (DSS); HSV (Hue Saturation Value); Support Vector Machine (SVM))