AN EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING HIERARCHICAL PART-TEMPLATE AND TREE MODELING

Abstract

Image based content recognition and retrieval is critical in many applications. Existing mechanisms for content based image retrieval lack in terms of performance. In this paper a hierarchical template tree based CBIR system is described. Content in image is represented using a combination of shape features and low level features. Comprehensive feature set definitions proposed enables in achieving better performance. Shape and low level features are considered as templates. Templates of similar categories are further decomposed to form a hierarchical template tree. Query image is converted into a query template and is decomposed. A part template based matching scheme and SVM classifier is used to retrieve visually similar images. Results presented in the paper prove superior performance of proposed technique when compared to recent existing mechanisms in place. An improvement of 10.45% and 9.69% in mean average precision and mean retrieval accuracy is reported using proposed approach.