Region-based MRF model with optimized initial regions for image segmentation

Author

Zheng, Chen ; Wang, Leiguang ; Hu, Yijun ; Qin, Qianqing

Author_Institution

Sch. of Math. & Stat., Wuhan Univ., Wuhan, China

fYear

2011

fDate

24-26 June 2011

Firstpage

3354

Lastpage

3357

Abstract

In this paper, we propose a region-based MRF model with optimized initial regions (RMRF-OIR) for image segmentation. In the RMRF-OIR, a modified mean shift is introduced to get the optimized initial over segmented regions. Then, a region-based MRF is used to model these initial regions on the region adjacency graph. Finally, the segmentation results will be obtained by using a region merging scheme for the region-based MRF model. Experiment results of remote sensing images prove a high accuracy and efficiency of RMRF-OIR compared with the non-optimized region-based MRF and the pixel-based MRF.

Keywords

Markov processes; graph theory; image segmentation; remote sensing; Markov random field; image segmentation; modified mean shift; nonoptimized region-based MRF; optimized initial regions; pixel-based MRF; region adjacency graph; region merging scheme; region-based MRF model; remote sensing images; Accuracy; Computational modeling; Image segmentation; Mathematical model; Merging; Pixel; Remote sensing; optimization; random field; region; segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Remote Sensing, Environment and Transportation Engineering (RSETE), 2011 International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4244-9172-8

Type

conf

DOI

10.1109/RSETE.2011.5965031

Filename

5965031