Segmentation and classification of features in retinal images

Author

Gowsalya, P. ; Vasanthi, S.

Author_Institution

K.S. Rangasamy Coll. of Technol., Tiruchengode, India

fYear

2014

fDate

3-5 April 2014

Firstpage

1869

Lastpage

1873

Abstract

This paper presents segmentation of retinal features such as Optic Disc (OD) and blood vessels for screening the eye diseases. An optic disc is only the brightest region in retina through which blood vessels are entering and leaving from the eye. So that analyzing these features aids to diagnose various retinal diseases. First, the blood vessel features are segmented and it is classified using an ensemble classifier then the performance of the classifier is evaluated.Second, the fully automated segmentation algorithm localizes the Optic Disc (OD) using template matching. Then it is segmented using level set segmentation method and morphological filter is used to remove the artifacts other than the OD.

Keywords

biomedical optical imaging; blood vessels; diseases; eye; feature extraction; filtering theory; image classification; image matching; image segmentation; medical image processing; patient diagnosis; OD; blood vessel features segmentation; blood vessels; classifier performance; ensemble classifier; eye diseases screening; features classification; fully automated segmentation algorithm; level set segmentation method; morphological filter; optic disc; retinal diseases diagnosis; retinal features segmentation; retinal images; template matching; Algorithm design and analysis; Classification algorithms; Image segmentation; Optical imaging; Retina; Retinopathy; Support vector machine classification; Blood Vessels; Ensemble Classification; Optic Disc (OD); Segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing (ICCSP), 2014 International Conference on

Conference_Location

Melmaruvathur

Print_ISBN

978-1-4799-3357-0

Type

conf

DOI

10.1109/ICCSP.2014.6950169

Filename

6950169