DocumentCode :
2139080
Title :
The Brain Image Segmentation by Markov Field and Normal Distribution Curve
Author :
Guan, Yi-hong ; Lv, Liang ; Duan, Rui ; Ji, Yun-Hai
Author_Institution :
Dept. of Phys. Electron., Kunming Univ. of Sci. & Technol., Kunming, China
fYear :
2009
fDate :
17-19 Oct. 2009
Firstpage :
1
Lastpage :
5
Abstract :
Because of magnetic resonance images (MRI) was impacted of thermal/electrical noise, we found that the distribution of the brain tissue is normal distribution according to the observation and study. This paper presents a theory based on Markov field to extract brain tissue and used fuzzy clustering theory to build a normal distribution curve on the histogram of the brain tissue image to segmentation MRI. This paper is divided into two parts: First of all, using simulated annealing based on Markov random field to obtain global energy minimization of the brain image then using threshold method extract objectives( brain bone and brain tissue ) and background; Secondly, using the histogram and fuzzy clustering method to build a normal distribution curve to achieve a better segmentation result.
Keywords :
Markov processes; biomedical MRI; brain; feature extraction; fuzzy set theory; image segmentation; medical image processing; minimisation; simulated annealing; MRI; Markov field; brain bone; brain image segmentation; brain tissue distribution; fuzzy clustering; global energy minimization; magnetic resonance image; normal distribution curve; simulated annealing; threshold method extract objectives; Brain modeling; Gaussian distribution; Histograms; Image segmentation; Magnetic noise; Magnetic resonance; Magnetic resonance imaging; Markov random fields; Minimization methods; Simulated annealing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing, 2009. CISP '09. 2nd International Congress on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4244-4129-7
Electronic_ISBN :
978-1-4244-4131-0
Type :
conf
DOI :
10.1109/CISP.2009.5303479
Filename :
5303479
Link To Document :
بازگشت