DocumentCode :
3048191
Title :
Vector-valued image segmentation using region based active contour
Author :
Shahvaran, Zahra ; Kazemi, Kamran ; Helfroush, Mohammad Sadegh ; Golshaeyan, Narjes
Author_Institution :
Shiraz Univ. of Technol., Shiraz, Iran
fYear :
2013
fDate :
14-16 May 2013
Firstpage :
1
Lastpage :
4
Abstract :
In this paper we present our framework for object segmentation in vector-valued images with intensity non-uniformity and noise using region based level set method. The proposed framework extend the local Gaussian distribution fitting in which the local intensity is modeled by Gaussian distribution. Our experiments on synthetic images and simulated cerebral MR images show the advantages of the proposed method in comparison with applying scalar model.
Keywords :
Gaussian distribution; biomedical MRI; image segmentation; medical image processing; cerebral magnetic resonance images; intensity nonuniformity; local Gaussian distribution fitting; object segmentation; region based active contour; region based level set method; simulated cerebral MR images; synthetic images; vector-valued image segmentation; Active contours; Biological system modeling; Fitting; Gaussian distribution; Image segmentation; Level set; Noise; Intensity non-uniformity; Level Set; MR image; Segmentation; Vector-Valued image;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electrical Engineering (ICEE), 2013 21st Iranian Conference on
Conference_Location :
Mashhad
Type :
conf
DOI :
10.1109/IranianCEE.2013.6599702
Filename :
6599702
Link To Document :
بازگشت