Author(s):

Dr. P Prema, Dr. A Veeramani, Dr. M Theradimani and Dr. T Sivakumar

Abstract: Early detection of Leaf disease is the most significant process in the agricultural applications to reduce the usage of fungicides in the agricultural field and to increase the quality and quantity of the product. To identify the plant diseases at an early stage is not yet explored. Existing disease detection techniques does not yield better performance due to the complex background and illumination variation. Hence, there arises a need for the development of effective disease identification technique. This paper proposes a novel wrapping based Curvelet transformation with texture feature extraction method for automatic detection and classification of plant leaf disease. In this paper, Adaptive Median Filter (AMF) is used for filtering the impulse noise from the image. Leaf image identification is performed using green pixel extraction and K-means clustering. Wrapping based Curvelet transform is applied to the leaf image. GLCM based feature extraction is performed to extract the texture pattern of the plant image. Then, the selected features are learned and passed through an RVM-based classifier to find out the disease. Edge detection and contouring is performed to identify the disease affected area in the leaf image. The proposed approach achieves higher accuracy for disease detection.

Pages: 2314-2317  |  695 Views  245 Downloads

Download (660KB)