Clustering context properties of wavelet coefficients in automatic modelling and image coding

An algorithm for automatic modelling of wavelet coefficients from context properties is presented. The algorithm is used to implement an image coder, in order to demonstrate its image coding efficiency. The modelling of wavelet co-efficients is performed by partitioning the weighted context property space to regions. Each of the regions has a dynamic probability distribution stating the predictions of the modeled co-efficients. The coding performance of the algorithm is compared to other efficient wavelet-based image compression methods.