Object Based Image Retrieval from Database Using Combined Features

Abstract

Content based image retrieval (CBIR) is a promising way to address image retrieval based on the visual features of an image like color, texture and shape. Every visual feature will address a specific property of the image, so the state of the art focuses on combination of multiple visual features for content based image retrieval. In this paper we have devised a content based image retrieval system based on the combination of local and global features. The local features used are Bidirectional Empirical Mode Decomposition (BEMD) technique for edge detection and Harris corner detector to detect the corner points of an image. The global feature used is HSV colorfeature. For the experimental purpose the COIL-100 database has been used. The result show significant improvement in the retrieval accuracy when compared to the existing systems.