Colour and Shape Based Image Retrieval for CVPIC Coded Images

Abstract Compressed domain image retrieval is going to play an increasingly important role in the future. It allows the calculation of image features and hence content-based image retrieval (CBIR) to be performed directly on the compressed data without the need of decoding it beforehand. The Colour Visual Pattern Image Coding (CVPIC) technique represents a compression algorithm where the compressed form is directly meaningful. Data that is readily available in CVPIC compressed images includes information on colour and edge (shape) descriptors of image sub-blocks. In this paper we introduce an image retrieval algorithm based on CVPIC that makes efficient use of this information by calculating colour and shape histograms in the compressed domain. Retrieval results on the UCID dataset show good retrieval performance, outperforming pixel-domain based methods such as colour histograms, colour coherence vectors and colour correlograms.

• Type: Conference
• Year: 2004
• Where: CISST
• Authors: Gerald Schaefer, Simon Lieutaud
• Keywords: CISST 2004, Content-based Image Retrieval, Hardware, Image Retrieval, Image Retrieval Algorithm