Retinal image matching using hierarchical vascular features.

Journal Article (Journal Article)

We propose a method for retinal image matching that can be used in image matching for person identification or patient longitudinal study. Vascular invariant features are extracted from the retinal image, and a feature vector is constructed for each of the vessel segments in the retinal blood vessels. The feature vectors are represented in a tree structure with maintaining the vessel segments actual hierarchical positions. Using these feature vectors, corresponding images are matched. The method identifies the same vessel in the corresponding images for comparing the desired feature(s). Initial results are encouraging and demonstrate that the proposed method is suitable for image matching and patient longitudinal study.

Full Text

Duke Authors

Cited Authors

  • Bhuiyan, A; Lamoureux, E; Nath, B; Ramamohanarao, K; Wong, TY

Published Date

  • 2011

Published In

Volume / Issue

  • 2011 /

Start / End Page

  • 749054 -

PubMed ID

  • 22013434

Pubmed Central ID

  • PMC3195514

Electronic International Standard Serial Number (EISSN)

  • 1687-5273

Digital Object Identifier (DOI)

  • 10.1155/2011/749054


  • eng

Conference Location

  • United States