An invariant approach to object classification using background removal

Object recognition and classification in a multi-environment is an important part of machine vision. The goal of this paper is to build a system that classifies the objects of interest plane and helicopter. This paper addresses the issues to classify objects by combining pose and viewpoint invariant to certain extend. The threshold technique with background subtraction is used to segment the background region to extract the object of interest. Feature extraction is done through edge detection. The features of the objects with variety of pose, viewpoint images are fed to the back-propagation neural classifier. Quantitative evaluation shows improved results by comparison of classification done with the proposed method with that of classification done with conventional feature extraction method.