Title | A maximum entropy Kalman filter for image compression |
Publication Type | Conference Paper |
Year of Publication | 2000 |
Authors | David, A., and T. Aboulnasr |
Conference Name | Circuits and Systems, 2000. Proceedings of the 43rd IEEE Midwest Symposium on |
Pagination | 884 -887 vol.2 |
Keywords | data compression, digital image compression, edge detection, image coding, image texture, Kalman filters, maximum entropy Kalman filter, maximum entropy methods, optimisation, optimization |
Abstract | In this paper, we propose a novel compression method applicable to digital images. We employ Maximum Entropy (ME) as the optimization criterion and Kalman Filter (KF) as means of implementing the compressor. We will show for compression ratios comparable to those of traditional methods, such as JPEG, the high frequency components of the signal, i.e. texture and edges, are preserved. The motivation for using ME as the optimization criterion is to avoid over-smoothing of the signal associated with traditional methods based on Mean Square Error (MSE). The ME criterion is motivated by the fact that it does not make any assumptions, regarding the unobserved data |
URL | http://dx.doi.org/10.1109/MWSCAS.2000.952896 |
DOI | 10.1109/MWSCAS.2000.952896 |