Double-Density Dual-Tree Wavelet Transform Based Texture Classification

Texture classification plays an important role in image analysis. The wavelet transform is a very efficient multiscale analysis method that has been successfully applied to describe the texture. The double-density dual-tree wavelet transform can simultaneously possess the properties of the double-density discrete wavelet transform (DWT) and the dual-tree DWT. In this paper, the texture feature based on the double-density dual-tree wavelet transform are derived from the subbands and tested in two benchmark texture databases. The experimental results suggest the potential capacity of the double-density dual-tree wavelet transform in texture analysis.