Different Complex Wavelet Transforms for Texture Retrieval and Similarity Measure

Complex wavelet transform overcomes the drawbacks of discrete wavelet transform, such as shift sensitivity, poor directionality and lack of the phase information. In this paper, the performance of the first-order and the second-order (co-occurrence) statistical characters of the different complex wavelet transforms (CWT) is studied with the consideration of the wavelet energy, and applied to texture feature extraction. It is concluded that the performance of the CWT is better than the pyramid discrete wavelet decomposition transforms (PDWT) on the texture feature extraction through theory analysis and the contrast experiments results on the texture retrieval. Best performance is achieved by combining the first-order signatures with the second-order signatures and the performance of retrieval is raised 8%.