Title :
MIRROR: an interactive content based image retrieval system
Author :
Wong, Ka-Man ; Cheung, Kwok-Wai ; Po, Lai-Man
Author_Institution :
City Univ. of Hong Kong, China
Abstract :
A content based image retrieval system, called MPEG-7 image retrieval refinement based on relevance feedback (MIRROR), is developed for evaluating MPEG-7 visual descriptors and developing new retrieval algorithms. The system core is based on MPEG-7 experimentation mode (XM) with Web-based user interface for query by image example retrieval. A new merged color palette approach for MPEG-7 dominant color descriptor similarity measure and relevance feedback are also developed in this system. Several MPEG-7 visual descriptors are adopted in MIRROR for performance comparison purposes.
Keywords :
content-based retrieval; graphical user interfaces; image colour analysis; image representation; image retrieval; interactive systems; query formulation; relevance feedback; MIRROR; MPEG-7 experimentation mode; Web-based user interface; dominant color descriptor similarity measure; image databases; image retrieval refinement; image retrieval system; interactive content based retrieval; merged color palette; merged palette histogram; query by image example; relevance feedback; visual descriptors; Content based retrieval; Data mining; Feature extraction; Histograms; Image databases; Image retrieval; Information retrieval; MPEG 7 Standard; Mirrors; Output feedback; Content Based Image Retrieval; Image Databases; MIRROR; Merged Palette Histogram; Relevance Feedback;
Conference_Titel :
Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on
Print_ISBN :
0-7803-8834-8
DOI :
10.1109/ISCAS.2005.1464894