Markov image modeling
- 1 October 1978
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 23 (5) , 846-850
- https://doi.org/10.1109/tac.1978.1101866
Abstract
The theory of two-dimensional spectral factorization is reviewed in the context of recursive modeling. The role of the Markov random field in recursive image modeling is then presented. Since spectral factorization in two or higher dimensions generally results in infinite-order factors, it is necessary to perform Markov modeling after spectral factorization. The above concepts are then applied to the problem of Kalman filtering of images.Keywords
This publication has 13 references indexed in Scilit:
- Design of stable 2-D half-plane recursive filters using spectral factorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Kalman filtering in two dimensionsIEEE Transactions on Information Theory, 1977
- A Fast Karhunen-Loeve Transform for a Class of Random ProcessesIEEE Transactions on Communications, 1976
- Two-dimensional spectral factorization with applications in recursive digital filteringIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Comments on "Two dimensional Bayesian estimate of images"Proceedings of the IEEE, 1976
- Stability of DPCM Coders for TelevisionIEEE Transactions on Communications, 1975
- Image Coding Via a Nearest Neighbors Image ModelIEEE Transactions on Communications, 1975
- Modeling of two-dimensional covariance functions with application to image restorationIEEE Transactions on Automatic Control, 1974
- Recursive Image Enhancement--Vector ProcessingIEEE Transactions on Communications, 1973
- Two-dimensional discrete Markovian fieldsIEEE Transactions on Information Theory, 1972