The Research of Image Retrieval based on Multi Feature DS Evidence Theory Fusion
Che Hao Chang, Xiaoyang Yu, Yu Guang · International Journal of Signal Processing Image Processing and Pattern Recognition · 2016
The traditional image retrieval method is based on single feature retrieval method like color, texture, shape or multi feature weighted fusion method.The retrieval rate of existing methods is not high.This paper presents fusion multi feature image retrieval.Two kinds of feature play a complementary effect in retrieval.Most color feature can not reflect the spatial information of image.Texture is a regional characteristics which contains important spatial information of image.Fusing the color and texture feature can play their respective advantages.At the same time, avoiding the one-sidedness of single feature retrieval.Improving the retrieval accuracy and flexibility well.