Detection and classification of pests from crop images using Support Vector Machine

Abstract

Agriculture is the mother of all culture. Economy and prosperity of a country depends on agriculture production. Agriculture provides food as well as raw material for industry. Agriculture production is inversely affected by pest infestation and plant diseases. Early pest identification and disease detection will help to minimize the loss of production. Naked eye observation is a common using method to identify the pest. But it is time consuming process. In this paper we proposed an automatic pest identification system using image processing techniques. Color feature is used to train the SVM to classify the pest pixels and leaf pixels. Morphological operations are used to remove the unwanted elements in the classified image.