FEATURE EXTRACTION AND CLASSIFICATION OF FUNDUS IMAGES FOR DETECTIONS OF MICROANEURYSMS

  • Unique Paper ID: 155280
  • Volume: 9
  • Issue: 1
  • PageNo: 679-682
  • Abstract:
  • Diabetes increases the risk of developing any deterioration in the blood vessels that supply the retina an ailment known as diabetic retinopathy (DR). Since this disease is asymptomatic, it can only be diagnosed by an ophthalmologist consequently, this work proposes a new approach for MA detection based on deduction of non-uniform illumination; normalization of image gray scale content to improve dependence of images from different contexts; application of the Top hat transform to leave reddish regions intact while suppressing bright objects; binarization of the image of interest with the result that objects corresponding to MAs, blood vessels from the ROIs; the features are extracted from a candidate to distinguish real MAs from FPs, is characterized by values obtained from sensitivity and specificity. The proposed approach is tested on publicly available database Messidar. The proposed MA detection method achieves good results in detecting MA’s.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 9
  • Issue: 1
  • PageNo: 679-682

FEATURE EXTRACTION AND CLASSIFICATION OF FUNDUS IMAGES FOR DETECTIONS OF MICROANEURYSMS

Related Articles