Field pest identification by an improved Gabor texture segmentation scheme

Abstract

Segmentation of pests is a critical step in using machine vision for field automation tasks. A new method called GaborBoostSVM is proposed in this paper. The method comprises Gabor wavelets-based feature extraction, AdaBoost-based feature selection and SVM-based pattern recognition algorithm. It performed unsupervised classification in field images into pest and background categories for real-time selective insecticide application. The results showed that the method is capable of performing texture-based pest and background classification consistently high, effectively and with high classification accuracy. © 2007 Taylor & Francis Group, LLC.