Photobook: content-based manipulation of image databases
International Journal of Computer Vision
Curvature scale space image in shape similarity retrieval
Multimedia Systems
Content-Based Image Retrieval at the End of the Early Years
IEEE Transactions on Pattern Analysis and Machine Intelligence
MPEG-7 visual shape descriptors
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
A content-based image retrieval system using an image sequence as a query is proposed in this study. The proposed system is applied to a fish database in Taiwan, which is collected by the Institute of Zoology, Academia Sinica. Major contribution of this study is threefold: (1) The proposed query-by-an-image-sequence scheme can eliminate the problems caused by non-rigid fish motions, serious deformations, and partial occlusions. (2) In traditional query-by-an-example schemes, queries with different imaging conditions may generate completely different retrieval results, but the proposed query scheme can overcome varying imaging conditions. (3) The proposed fish representation scheme is invariant to translation, scaling, and rotation. Experimental results have proven the effectiveness of the proposed system.