Blood vessel segmentation in retinal images based on the nonsubsampled contourlet transform

Author

Chien-Cheng Lee ; Shih-Che Ku

Author_Institution

Dept. of Commun. Eng., Yuan Ze Univ., Taoyuan, Taiwan

fYear

2012

fDate

14-16 Aug. 2012

Firstpage

337

Lastpage

340

Abstract

This paper presents a method for blood vessel segmentation in retinal images based on the nonsubsampled contourlet transform (NSCT). The method uses a line detector and different directions of the NSCT subbands to detect the direction of blood vessel for each NSCT level. Then, the method computes three kinds of features using the orthogonal direction of blood vessel of the NSCT coefficients. After pixel classification, we present three kinds of post-processing procedures to correct the optic disk, the field of view mask, lesion areas, and noise. The performance is evaluated on the DRIVE database. The average accuracy of the DRIVE databases evaluation is 0.9423.

Keywords

blood vessels; eye; feature extraction; image classification; image resolution; image segmentation; medical image processing; object detection; transforms; DRIVE database; NSCT coefficients; NSCT level; blood circulation system diagnosis; blood vessel direction detection; blood vessel segmentation method; lesion areas correction; line detector; noise correction; nonsubsampled contourlet transform; optic disk correction; pixel classification; retinal images; retinal imaging diagnosis; view mask correction; Adaptive optics; Biomedical imaging; Blood vessels; Feature extraction; Image segmentation; Optical imaging; Retina; blood vessel; nonsubsampled contourlet transform; retinal image;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Security and Intelligence Control (ISIC), 2012 International Conference on

Conference_Location

Yunlin

Print_ISBN

978-1-4673-2587-5

Type

conf

DOI

10.1109/ISIC.2012.6449775

Filename

6449775