An Efficient Preprocessing Step for Retinal Vessel Segmentation via Optic Nerve Head Exclusion

Title

An Efficient Preprocessing Step for Retinal Vessel Segmentation via Optic Nerve Head Exclusion

Creator

Wahid F.F.; Raju G.

Description

Retinal vessel segmentation plays a significant role for accurate diagnostics of ophthalmic diseases. In this paper, a novel preprocessing step for retinal vessel segmentation via optic nerve head exclusion is proposed. The idea relies in the fact that the exclusion of brighter optic nerve head prior to contrast enhancement process can better enhance the blood vessels for accurate segmentation. A histogram based intensity thresholding scheme is introduced in order to extract the optic nerve head which is then replaced by its surrounding background pixels. The efficacy of the proposed preprocessing step is established by segmenting the retinal vessels from the optic nerve head excluded image enhanced using CLAHE algorithm. Experimental works are carried out with fundus images from DRIVE database. It shows that 1%3% of improvement in terms of TPR measure is achieved. 2019, Springer Nature Singapore Pte Ltd.

Source

Communications in Computer and Information Science, Vol-1046, pp. 228-239.

Date

2019-01-01

Publisher

Springer Verlag

Subject

Fundus image enhancement; Optic nerve head; Preprocessing; Retinal vessel segmentation

Coverage

Wahid F.F., Department of Information Technology, Kannur University, Kannur, 670567, Kerala, India; Raju G., Department of CSE, Faculty of Engineering, Christ (Deemed to be University), Bengaluru, 560764, Karnataka, India

Rights

Restricted Access

Relation

ISSN: 18650929; ISBN: 978-981139941-1

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-13-9942-8_22

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85070225817&doi=10.1007%2f978-981-13-9942-8_22&partnerID=40&md5=eb318c9659a6f21fa9fa481e480fffa4