Performance analysis in content-based retrieval with textures

K. Xu, B. Georgescu, D. Comaniciu, P. Meer
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000  
The features employed i n c ontent-based r etrieval are most often simple low-level representations, while a human observer judges similarity between images based on high-level semantic properties. Using textures as an example, we show that a more a c curate description of the underlying distribution of low-level features does not improve the retrieval performance. We also introduce the simpli ed multiresolution symmetric autoregressive model for textures, and the Bhattacharyya distance based
more » ... ya distance based similarity measure. Experiments are performed with four texture r epresentations and four similarity measures over the Brodatz and VisTex databases.
doi:10.1109/icpr.2000.902912 dblp:conf/icpr/XuGMC00 fatcat:ftiwm5nlfrf2vktbyei7udp4we