TY  - JOUR
T1  - Perception-based Feature Weight Refinement for Boosting Image Retrieval Performance
AU - , Hun-Woo Yoo AU - , Sang-Sung Park AU - , Dong-Sik Jang 
JO  - Asian Journal of Information Technology
VL  - 3
IS  - 12
SP  - 1276
EP  - 1283
PY  - 2004
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2004.1276.1283
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2004.1276.1283
KW  - 
AB  - Image similarity is often measured by computing the distance between two feature vectors. Unfortunately, the feature space cannot always capture the notion of similarity in human perception. Therefore, most current image retrieval systems use weights measuring the importance of each feature. In this paper new weight update rules are proposed for image retrieval purpose. In order to obtain optimal feature weights, database images are first divided into groups based on human perception, and then optimal feature weights for each database images are computed by using internal and outer query results. Experimental results show the proposed algorithm obtains more similar images to the query as the query process continues.
ER  -