Research Article Open Access

Automatic Detection of Exudates in Retinal Images using Region-Based, Neighborhood and Block Operation

Kittipol Wisaeng1 and Worawat Sa-Ngiamvibool2
  • 1 Mahasarakarm University, Thailand
  • 2 Mahasarakham University, Thailand

Abstract

Exudates detection is one of the research areas attracting great attention of physicians and scientists. A region-based, neighborhood, block operation and optimal global thresholding are proposed as new methods to exudates detection. The exudates are coarse and fine segmentation following preprocessing steps, i.e., color mapping, image contrast enhancement, fuzzy filtering and optic disc localization. To classify the retinal images into non-exudates and exudates, a set of features such as texture, color, size and the edge is extracted. The exudates procedure succeeded in an overall generalization accuracy of 98.62% with 98.18% sensitivity and 98.32% specificity in local databases. Moreover, the results are presented to show the advantage of the proposed method in a public database with an accuracy of 92.14.

Journal of Computer Science
Volume 14 No. 4, 2018, 438-452

DOI: https://doi.org/10.3844/jcssp.2018.438.452

Submitted On: 21 October 2017 Published On: 21 February 2018

How to Cite: Wisaeng, K. & Sa-Ngiamvibool, W. (2018). Automatic Detection of Exudates in Retinal Images using Region-Based, Neighborhood and Block Operation. Journal of Computer Science, 14(4), 438-452. https://doi.org/10.3844/jcssp.2018.438.452

  • 3,353 Views
  • 2,050 Downloads
  • 5 Citations

Download

Keywords

  • Retinal Images
  • Exudates
  • Block Processing
  • Optimal Global Thresholding