An innovate approach for retinal blood vessel segmentation using mixture of supervised and unsupervised methods
We propose a pathology-robust blood veesel segmentation method that combines supervised and unsupervised techniques with two new descriptors—local Haar pattern and a modified SURF. On DRIVE, STARE, and CHASE DB1, it outperforms state-of-the-art baselines, ~1% over the best supervised method and ~2% over Nguyen et al.’s.
Sep 30, 2020
Retinal blood vessel segmentation: A semi-supervised approach
Jan 1, 2019
A semi-supervised approach to segment retinal blood vessels in color fundus photographs
Jan 1, 2019