Wavelet-Kalman method for image compression
A. David · 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). · 2004
This paper presents a novel wavelet-Kalman based method for compressing digital images. The method is based on the state-space description of the synthesis operation of the discrete wavelet transform (DWT). In particular, the synthesis operation is regarded as the state evolution from a coarse subspace to a finer one. And the analysis operation is considered as a partially observable process. We show that such a description, in the context of an ordinary Kalman filter, provides for an extremely efficient compression method.