Fast MPEG-7 visual descriptor extraction using DCT coefficient

TMPEG-7 descriptors are known as standard descriptors for the content-based indexing and retrieval. To extract visual features from a compressed image, the spatial domain information should be extracted from the compression domain information. In this paper, we propose the fast feature extraction method that can be applied to MPEG-7 visual descriptor from DCT compressed image. In the proposed method, fast extraction of descriptor is achieved by combination of down sampling and direct calculation of spatial information in DCT domain. Experiment is performed with MPEG-7 reference database. The results show that the proposed method can be applied to fast feature extraction with large size of database in Internet.