DocumentCode :
3196976
Title :
Dental cyst delineation using live wire algorithm
Author :
Ulaganathan, G. ; Banumathi, A. ; Amutha, J.J. ; Jeevani Selvabala, A.
Author_Institution :
Dept. of Oral & Maxillofacial Surg., Best Dental Sci. Coll., Madurai, India
fYear :
2012
fDate :
14-15 Dec. 2012
Firstpage :
129
Lastpage :
132
Abstract :
This paper presents a segmentation algorithm for interactive delineation of various types of dental cysts using Live-wire, which is slightly modified from classical Live wire algorithm to segment dental X-ray images. The aim of this paper is to segment regions of dental cysts. It is necessary to choose suitable segmentation method because of adverse parameters of the regions. The regions of the cysts are of low contrast and the pixel intensity distribution is not homogenous, hence the semiautomatic live-wire method was chosen. Live-wire segmentation is an interactive tool for efficient, accurate boundary extraction which requires minimal user input with a mouse. This algorithm calculates the local cost [1] and then applies modified shortest path algorithm for better results. This approach to image segmentation is faster and more accurate than manual segmentation. It is very good compromise between simple manual edge tracing and automatic methods such as thresholding, watershed segmentation or other methods whose results must be post-processed.
Keywords :
X-ray imaging; dentistry; edge detection; image segmentation; interactive systems; medical image processing; boundary extraction; classical live wire algorithm; dental X-ray image segmentation; dental cyst delineation; interactive delineation; interactive tool; manual edge tracing; modified shortest path algorithm; mouse; pixel intensity distribution; region segmentation; semiautomatic live wire method; Dentistry; Image edge detection; Image segmentation; Laplace equations; Manuals; Teeth; Wires; boundary extraction; dental cyct identification; interactive delineation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Vision and Image Processing (MVIP), 2012 International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4673-2319-2
Type :
conf
DOI :
10.1109/MVIP.2012.6428777
Filename :
6428777
Link To Document :
بازگشت