Object Recognition Based on Parallel Classifiers using Oriented Features

Service robots need object recognition strategy that can work on various objects and backgrounds. We need to combine several methods so that robot can use the appropriate one. In this paper we propose a scheme to classify the situations depending on the characteristics of object of interest, background and user demand. We classify the situations into two categories and employ different techniques for different groups. We use SIFT in a particular situation and propose a kernel principal component based technique for the remaining category which uses Gabor filters for feature extraction and multiple support vector classifiers. Through experiments, we show that our method performs better than a state-of-the-art technique for the remaining category.