An Efficient Leaf Disease Detection And Classification For Agricultural Plant

Traditional scheme used for disease scoring scale to grade the plant diseases is primarily based on bare eye observation by agriculture professional or plant pathologist. In this scheme proportion scale was totally used to define different disease severities in an illustrated series of disease evaluation keys for field crops. In the past few years, researchers have studied a number of cultures exploiting different parts of a plant. The evaluation of plant leaf diseases using this approach which may be subjective, time consuming and cost effective. Also precise grading of leaf diseases is necessary to the determination of pest control measures. In order to develop this practice, here we propose a technique for automatically grading the damaged leaf area using k means clustering, which uses square Euclidian distances technique for segmentation of leaf image. For grading of leaf diseases which emerge on leaves based on segmented contaminated region are done automatically by estimating the proportion of the unit pixel expressed under diseased region area and unit pixel expressed under Leaf section area. In count, a contaminated leaf is classified into any one of the disease categories. Experiments are performed by individually utilizing color features, texture features, and their combinations to train three models based on ANN classifier.