A Signal Processing Algorithm Based on Parametric Dynamic Programming
A new algorithm for low-level signal processing is proposed based on dynamic programming principle. It is shown that it is possible to extend the dynamic programming procedure to the case of continuous variables by introducing the parametric family of Bellman functions, represented as a minimum of a set of quadratic functions. The procedure can take into account a wide range of prior assumptions about the sought-for result, and leads to the effective algorithms of data analysis.
Keywordsdynamic programming edge-preserving smoothing separable optimization
- 1.Mottl, V., Kopylov, A., Blinov, A., Kostin, A..: Optimization techniques on pixel neighborhood graphs for image processing. In: Graph-Based Representations in Pattern Recognition. Computing, vol. (suppl. 12), pp. 135–145. Springer-Verlag/Wien (1998)Google Scholar
- 2.Kopylov, A.V.: Parametric dynamic programming procedures for edge preserving in signal and image smoothing. Pattern Recognition and Image Analysis 15(1), 227–230 (2005)Google Scholar
- 4.Szeliski, R., Zabih, R., Scharstein, D., Veskler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 30(6), 1068–1080 (2008)CrossRefGoogle Scholar