DISEASES DETECTION AND CLASSIFICATION OF AFFECTED PART OF PLANT LEAVES
S. SINGARAVELAN *
Department of Computer Science and Engineering, PSR Engineering College, Sivakasi, India.
R. ARUN
Department of Computer Science and Engineering, PSR Engineering College, Sivakasi, India.
D. MURUGAN
Department of Computer Science and Engineering, Manonmaniam Sundaranar University,Tirunelveli, India.
*Author to whom correspondence should be addressed.
Abstract
Plant pathology is the scientific study of plant diseases caused by pathogens and environmental conditions. It includes pathogen identification, diseases cycles, economic impact, management of plant diseases, etc. In existing, to detect the diseases they used the spectroscopic techniques. These techniques are very expensive and can only be utilized by trained persons only. To overcome these problem, the detection of diseases which are detected using ELM (Extreme Learning Machine) technique. First the sample leaf image is given as input. Then, color channels are separated from the leaf image from these the green pixels are masked from the original image. The masking is done to avoid the processing of the green area of the leaves, since, it is healthy. By removing the green area from the original area the remaining infected area is calculated. Then the features are extracted from the affected area. Finally these features are given to the ELM to classify the disease. After finding the disease the solution for that disease is send to the corresponding user mobile using GSM device.
Keywords: Leaf disease, fuzzy c-means clustering, GLCM, extreme learning machine