Abstract
In this paper, we propose a new algorithm for color texture retrieval by combining the feature extraction and similarity measurement tasks into a joint modeling and classification scheme based on the statistical representation of hypercomplex wavelets. The proposed statistical model leads to a new hypercomplex wavelet-based color texture retrieval method that is based on the accurate modeling of the marginal distribution of the hypecomplex wavelet coefficients using generalized Gaussian density (GGD) and on the existence a closed form for the Kullbak-Leibler distance (KLD) between GGDs. The efficiency of the proposed retrieval method is characterized by greater accuracy and flexibility in capturing the color texture information. Using a database of 640 color textures, the experimental results indicate that the proposed method significantly improves retrieval rates compared with traditional color approaches, while it enjoys a similar computational complexity.