DocumentCode :
454887
Title :
Mumford-Shah Model with Fast Algorithm on Lattice
Author :
Yu, Lu ; Wang, Qiao ; Wu, Lenan ; Xie, Jun
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing
Volume :
2
fYear :
2006
fDate :
14-19 May 2006
Abstract :
Mumford-Shah piecewise smooth functional is a variational PDE model widely used in image segmentation and smoothing. An analogous discrete model which models image as an MRF has also been built. In this paper, we propose another discrete Mumford-Shah piecewise smooth model on lattice from a different perspective. We present a discrete objective functional, as well as the method to find the solution. Only two simple and deterministic optimization techniques, that is, derivation and greedy algorithm are used in the model to seek the solution. Compared with traditional continuous model, the model in this paper is much simpler and the approach is much easier and faster
Keywords :
greedy algorithms; image segmentation; optimisation; partial differential equations; Mumford-Shah model; Mumford-Shah piecewise smooth functional; deterministic optimization techniques; greedy algorithm; image segmentation; lattice; variational PDE model; Automation; Boundary conditions; Greedy algorithms; Image communication; Image processing; Image segmentation; Lattices; Level set; Programmable logic arrays; Smoothing methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1660434
Filename :
1660434
Link To Document :
بازگشت