Automatic Segmentation of Blood Vessels in Retinal Image Based on Fuzzy K-Median Clustering

Author

Supot, Sookpotharom ; Thanapong, Chaichana ; Chuchart, Pintavirooj ; Manas, Sangworasil

Author_Institution

King Mongkut ´´s Inst. of Technol. Ladkrabang, Bangkok

fYear

2007

fDate

20-24 March 2007

Firstpage

584

Lastpage

588

Abstract

This paper presents an efficient method for automatic segmentation of blood vessels in retinal images. Specifically, we also delineate vascular intersections/crossovers. The proposed algorithm is composed of three steps: matched filter, fuzzy k-median (FKMED), and length filter. The segmentation results are compared with clinically generated vessel segmentation and are evaluated in terms of sensitivity and specificity. The results are encouraging and will be used for further application such as personal identification.

Keywords

blood vessels; eye; fuzzy systems; image segmentation; matched filters; median filters; medical image processing; automatic blood vessel segmentation; fuzzy k-median clustering; length filter; matched filter; retinal image; vascular intersection-crossover; Biomedical imaging; Blood vessels; Clustering algorithms; Diabetes; Diseases; Image edge detection; Image segmentation; Matched filters; Retina; Sensitivity and specificity; blood vessel; fuzzy c-mean; fuzzy k-median; matched filter; retinal image;

fLanguage

English

Publisher

ieee

Conference_Titel

Integration Technology, 2007. ICIT '07. IEEE International Conference on

Conference_Location

Shenzhen

Print_ISBN

1-4244-1092-4

Electronic_ISBN

1-4244-1092-4

Type

conf

DOI

10.1109/ICITECHNOLOGY.2007.4290384

Filename

4290384