Title :
A hybrid algorithm for segmentation of MRI images based on edge detection
Author :
Taghizadeh, Moslem ; Hajipoor, Mahboobeh
Author_Institution :
Imam Hossein Univ., Tehran, Iran
Abstract :
The main disadvantage of traditional global thresholding techniques is that they do not have an ability to exploit information of the characteristics of target images that they threshold. In this paper, we propose a new approach based on combination of modified p-tile and edge detection algorithms to have more accurate object segmentation. Using our proposed method, it is shown that almost all of our experiments on MRI images resulted to better object segmentation than using traditional methods.
Keywords :
biomedical MRI; edge detection; image segmentation; medical image processing; MRI images; edge detection algorithms; global thresholding techniques; modified p-tile algorithms; object segmentation; Detectors; Image edge detection; Image segmentation; Magnetic resonance imaging; Noise; Pattern recognition; Shape; Canny; Edge detection; MRI Images Threshold; segmentation;
Conference_Titel :
Soft Computing and Pattern Recognition (SoCPaR), 2011 International Conference of
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-1195-4
DOI :
10.1109/SoCPaR.2011.6089123