Hybrid Feature based Object Classification with Cluttered Background Combining Statistical and Central Moment Textures

Object classification in static images is a difficult task since motion information in no longer usable. The challenging task in object classification problem is the removal of cluttered background containing trees, road views, buildings and occlusions. The goal of this paper is to build a system that detects and classifies the car objects amidst background clutter and mild occlusion. This paper addresses the issues to classify objects of realworld images containing side views of cars with cluttered background with that of non-car images with natural scenes taken from University of Illinois at Urbana- Champaign (UIUC) standard database. 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 equal sized blocks of sub-images. The statistical central moment features and statistical texture features are combined to form hybrid features. The hybrid features are extracted from each sub-block. The features of the objects are fed to the backpropagation neural classifier. Thus the performance of the neural classifier is compared with various categories of block size. Quantitative evaluation shows improved results of 94.7%. A critical evaluation of this approach under the proposed standards is presented.