Retinal Blood Vessel Segmentation with Optic Disc Pixels Exclusion

  • Cahya Wihandika R
  • Suciati N
N/ACitations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

The morphological changes of retinal blood vessels are important indicators used to diagnose and monitor the progression of various diseases. A number of retinal blood vessel segmentation methods have been introduced, including the line operator based methods, which have shown satisfactory results. However, the basic line operator method cannot discriminate the pixels around the retinal optic disc, resulting in false classification of those pixels. In this paper, we integrate the detection of pixels around the retinal optic disc to the line operator method so that those pixels can be excluded from the vessel pixels. The method is evaluated on the widely used retinal dataset, the DRIVE dataset. The results demonstrate that the proposed method has made improvements over the basic and the multi-scale line detector with accuracy and area under curve of 0.942 and 0.9521, respectively.

Cite

CITATION STYLE

APA

Cahya Wihandika, R., & Suciati, N. (2013). Retinal Blood Vessel Segmentation with Optic Disc Pixels Exclusion. International Journal of Image, Graphics and Signal Processing, 5(7), 26–33. https://doi.org/10.5815/ijigsp.2013.07.04

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free