Texture Image Retrieval Algorithm Based on Complex Features in Brushlet Domain
Xiaohui Yang · 2011
A key step of texture image retrieval is how to extract texture features effectively.However,the directions of wavelet transform are limited.This paper proposed an image retrieval algorithm based on complex,since Brushlets is a complex function and is multi-directional.The energy and phase characteristics are extracted to describe the texture information.The impact of Brushlet transform decomposition levels in the retrieval results was analyzed.Moreover,the retrieval results and reasons for different kinds of texture images were discussed.The test results show that the new method describes texture information detailedly and comprehensively.So that similarity's metric criterions were significant higher,especially for texture images with stronger directivity.