Statistical texture image retrieval in DD-DTCWT domain using magnitudes and relative phases

Statistical models of transform coefficients are an efficient way to discriminate between texture classes. Statistical-based approaches provide a natural way to solve texture retrieval problem. In this paper, we proposed a new framework for textured image retrieval in DD-DTCWT (Double-density dual-tree complex wavelet transform) domain, which is based on the mixture of Cauchy and Vonn statistical models. Firstly, the image is decomposed into frequency subbands using DD-DTCWT, and the amplitude and relative phase of DD-DTCWT coefficients are computed. Secondly, Cauchy and Vonn distributions are employed respectively to capture the statistical characteristics of the magnitude and relative phase of DD-DTCWT coefficients, and the Cauchy and Vonn model parameters are utilized to construct a compact texture image feature space. Finally, image similarity measurement is accomplished by using closed-form solutions for the Kullback–Leibler divergences between the Cauchy and Vonn statistical models. Experimental results demonstrate the high efficiency of our textured image retrieval scheme, which can provide better retrieval rates and lower computational cost, in comparison with the state-of-the-art approaches recently proposed in the literature.