Fuzzy semantic labeling for image retrieval
M.C.S. Paterno, Fun Siong Lim, Wee Kheng Leow · 2005
The paper proposes a fuzzy image labeling method that assigns multiple semantic labels together with confidence measures to each region in an image. The confidence measures are derived from the distance of the region to hyperplanes constructed by support vector machines. Test results show that this method yields higher classification accuracy and retrieval precision than crisp labeling methods that are based on crisp classification.