Shape similarity measure for k nearest-neighbor queries [articol]

Abstract

One of the content based image retrieval techniques is the shape based technique which allows users to ask for objects similar in shape to a query object. In this paper, a region-based approach to shape representation and similarity measure is presented. The proposed algorithm is based on the grid descriptor method. Its performance is compared with the grid descriptor method in case of the k nearest-neighbor queries. The performance is tested using a database of synthetic shapes. Experimental results show that the proposed method performs favorably compared with the grid based method in case of the k-nearest neighbor queries.