Computer Aided Classification and Detection of Leaf Disease using ANN

Abstract

The contribution of a plant is highly important for both human life and environment. Diseases will affect plant, like all humans and animals. Various diseases may affect plant which disturbs the plants normal growth. Leaf, stem, fruit, root, and flower of the plant may get affected by these diseases. Without proper care the plant may die or its leaves, flowers, and fruits drop. Finding of such infections is required for exact distinguishing proof and treatment of plant sicknesses. The current technique for plant malady discovery utilizes human contribution for distinguishing proof and characterization of illnesses and these strategies endure with time-unpredictability. PC supported programmed division of illnesses from plant leaf utilizing delicate registering can be fundamentally valuable than the current techniques. In this paper, we proposed a method using Artificial neural network (ANN) for identification, classification and segmentation of diseases in plant leaf automatically. In the proposed system capturing the leaf images is done first and then contrast of the image is improved by using Contrast Limited Adaptive Histogram Equalization(CLAHE) method. Then, color and texture features are extracted from the segmented outputs and the ANN classifier is then trained by using that features and it could able to separate the healthy and diseased leaf samples properly. Exploratory outcomes demonstrate that the arrangement execution by ANN taking list of capabilities is better with an exactness of 98%.