A statistical approch for image feature extraction in the wavelet domain

In this paper a new image feature extraction method based on the statistical analysis in the wavelet domain is developed for content-based image retrieval (CBIR). A two component Gaussian mixture model is developed to describe the statitistical characteristics of images in the wavelet domain. The model parameters are obtained by an EM (Expectation-Maximization) algorithm and then employed to construct the indexing feature space for CBIR. The new method is applied on the Brodatz image database to demonstrate its performance. The preliminary experimental results indicate that the composed indexing feature space through the statistical approach is very effective in representing image features and provides a high retrieval rate in CBIR. Compared with other CBIR feature extraction methods, the new method achieves comparable retrieval performance with less number of features in the feature space, which means the new method is more computationally efficient.