Wavelet Feature Based Neural Classifier System for Object Classification with Complex Background

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 amidst background clutter and mild occlusion. This paper addresses the issues to classify objects of real-world images containing side views of cars with complex background with that of non-car images with natural scenes. The threshold technique with background subtraction is used to segment the background region to extract the object of interest. Features of the objects are extracted using single-level discrete daubechies wavelet coefficients. The features of the objects are fed to the back- propagation neural classifier. Quantitative evaluation shows improved results by comparison of classification done with feature extraction after background removal with that of classification done with feature extraction alone. A critical evaluation of our approach under the proposed standards is presented.