Publication

Abstract : Agriculture plays a significant role in the overall socio-economic fabric of India. One of the several problems it faces in the country is the decline in productivity due to the drastic increase in plant diseases. The observations for detection of such diseases can be prohibitively expensive. Hence, a system which provides a faster and more accurate solution is necessary. Thermal images have a fine potential for early detection of diseases due to the temperature variations that occur as a result of the change in transpiration rate in plant leaves. Thus an attempt is made for the combined analysis of the visible light and thermal image features for early and accurate disease detection. The proposed work aims at developing a computer aided system that uses image processing algorithms to detect and classify plant diseases from Solanum Melongena (brinjal) leaves. The process starts with image acquisition using thermal and RGB cameras to obtain the data set, these images are then pre-processed and the region of interest is segmented out. The colour and temperature features are extracted and are used to detect and classify the healthy and diseased leaves. For classification, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used and their performances are compared. The experimentation reveals that SVM has a better accuracy (90.9%) than that of ANN (89.1%)