Parametric Gaussianization procedure of wavelet coefficients for texture retrieval

In this paper, we deal with the problem of feature extraction in content-based image retrieval (CBIR) using statistical approach. A Gaussianization procedure based on parametric density assumptions of steerable pyramid coefficients is proposed. The extraction method of features including the Gaussianization step allows us to limit the order of the statistical model used to characterize the image textures. The performances of the proposed method are analyzed on a database of texture images and compared with the performances of other texture features proposed in previous works.