摘要: We propose a new framework termed Keyblock for content-based image retrieval, which is generalization of the text-based information retrieval technology in domain. In this framework, methods extracting comprehensive features are provided, based on frequency representative blocks, keyblocks, database. Keyblocks, analogous to index terms text document can be constructed by exploiting vector quantization (VQ) method has been used compression. By comparing performance our approach with existing techniques using color feature and wavelet texture feature, experimental results demonstrate effectiveness retrieval.
acm.org
sci-hub.se 参考文章(176)
T. Kato, K. Hirata, Rough sketch-based image information retrieval Nec Research & Development. ,vol. 34, pp. 263- 273 ,(1993)
Paul B. Kantor, Decision Level Data Fusion for Routing of Documents in the TREC3 Context: A Base Case Analysis of Worst Case Results. text retrieval conference. pp. 319- 332 ,(1994)
D. R. Peddle, S. E. Franklin, Image texture processing and data integration for surface pattern discrimination Photogrammetric Engineering and Remote Sensing. ,vol. 57, pp. 413- 420 ,(1991)
Aidong Zhang, Gholamhosein Sheikholeslami, Multiresolution content-based image retrieval and clustering in large visual databases State University of New York at Buffalo. ,(1999)
Arun N. Netravali, B. G. Haskell, Digital Pictures: Representation and Compression ,(2014)
Bangalore S Manjunath, Wei-Ying Ma, Browsing large satellite and aerial photographs international conference on image processing. ,vol. 2, pp. 765- 768 ,(1996) , 10.1109/ICIP.1996.561013
Frederick Jelinek, Statistical methods for speech recognition ,(1997)
Christopher C Vogt, Garrison W Cottrell, Richard K Belew, Brian T Bartell, None, Using relevance to train a linear mixture of experts text retrieval conference. pp. 503- 515 ,(1996)
Ramin Zabih, Jing Huang, Color-spatial image indexing and applications Cornell University. ,(1998)
Theodosios Pavlidis, Structural Pattern Recognition ,(1977)