Retinal Image Matching Using Hierarchical Vascular Features

摘要

We propose a method for retinal image matching that can be used in image matching for personidentification 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 featurevectors 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 thecorresponding images for comparing the desired feature(s). Initial results are encouraging and demonstratethat the proposed method is suitable for image matching and patient longitudinal study.