Neural Classifier System for Object Classification with Cluttered Background Using Invariant Moment Features

Object recognition and classification in a multi-environment is an important part of machine vision. The goal of this study, is to build a system that classifies the objects amidst background clutter and mild occlusion. This study addresses the issues to classify objects of real-world images containing side views of cars with cluttered 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. The background segmented image with region of interest is divided into rectangular sub-images of equal size. The moment features which are invariant to Rotation, Scaling and Translation (RST) are extracted from each rectangular block. The features of the objects are fed to the back-propagation neural classifier. Thus, the performance of the neural classifier is compared with various categories of rectangular block size. Quantitative evaluation shows improved results of 84.9%. A critical evaluation of our approach under the proposed standards is presented.