Title :
Joint spatial-spectral indexing for image retrieval
Author :
Vellaikal, A. ; Kuo, C. -C Jay
Author_Institution :
Inf. Sci. Lab., Hughes Res. Labs., Malibu, CA, USA
Abstract :
Processing images directly in the compressed domain is very beneficial from the standpoint of lowering the computational complexity. In this paper we present a method of extracting features directly from the DCT coefficients of JPEG compressed imagery for the purpose of aiding image retrieval from a database. Our approach is characterized by a quadtree-based spatial structuring of the image followed by calculation of DCT coefficient features at the various nodes. Features based on DC and energy of AC coefficients are shown to be effective for queries concerning color, edge and texture properties
Keywords :
computational complexity; data compression; discrete cosine transforms; edge detection; feature extraction; image coding; image colour analysis; image texture; indexing; information retrieval; quadtrees; query formulation; transform coding; visual databases; AC coefficients; DC coefficients; DCT coefficients; JPEG compressed imagery; color; compressed domain; computational complexity; edge; image retrieval; joint spatial-spectral indexing; quadtree-based spatial structuring; queries; texture; Computational complexity; Discrete cosine transforms; Feature extraction; Image coding; Image databases; Image retrieval; Indexing; Information retrieval; Spatial databases; Transform coding;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.560895
