EFFICIENT OBJECT RECOGNITION USING DISCRIMINATIVE WEIGHT LEARNING

Object recognition is the process of identifying and detecting an object or a feature in a digital image or video. But it is also challenging vision problems because objects often suffer from significant scale, illumination variations, material recognition, pose changes, background clutter and partial occlusion. The scale invariant feature transform (SIFT) is a leading feature extraction approach which generates high dimensional features from regions selected based on pixel values. We proposed novel approach based Discriminative Weight Learning to discriminate the image features efficiently which enjoy the important applications of computer vision. This approach extracts image features using SIFT algorithm and weights are assigned to features based Discriminative Weight Learning. Extensive experiments were conducted to evaluate thoroughly this approach and the result showed that this approach is very competitive in object recognition.