Journal of Medical Systems

, Volume 36, Issue 3, pp 1997–2004

Automated Identification of Exudates and Optic Disc Based on Inverse Surface Thresholding

Authors

    • Electrical Engineering Department, Faculty of EngineeringUniversity of Malaya
    • School of Mechatronic EngineeringUniversity Malaysia Perlis
  • Hamzah Arof
    • Electrical Engineering Department, Faculty of EngineeringUniversity of Malaya
  • Hazlita Mohd Isa
    • National University Hospital of Malaysia
ORIGINAL PAPER

DOI: 10.1007/s10916-011-9659-4

Cite this article as:
Yazid, H., Arof, H. & Isa, H.M. J Med Syst (2012) 36: 1997. doi:10.1007/s10916-011-9659-4

Abstract

This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms a method based on watershed segmentation.

Keywords

Diabetic retinopathyExudatesBiomedical applicationsInverse surface thresholding

Copyright information

© Springer Science+Business Media, LLC 2011