LEAF DISEASES DETECTION

Abstract

the aim of this project is to style, implement and judge a picture process code primarily based resolution for
automatic detection and classification of plant disease. But studies show that hoping on pure naked-eye observation of
consultants to observe and classify diseases may be time intense and dearly-won, particularly in rural areas and
developing countries. Thus we tend to gift quick, automatic, low-cost and correct image process primarily based
resolution. Resolution consists of 4 main sections; within the 1st phase we tend to produce a color transformation
structure for the RGB leaf image then, we tend to apply color area transformation for the color transformation structure.
Next, within the second section, the photographs are segmental mistreatment the K-means clump technique. Within the
third section, we tend to calculate the feel options for the segmental infected objects. Finally, within the fourth section the
extracted options are knowledgeable a pre-trained neural network.