Retinal Vessel Segmentation Using A New Topological Method
arXiv:1608.01339v1
Originality Synthesis-oriented
AI Analysis
This addresses retinal image analysis for medical diagnostics, but appears incremental as it builds on existing topological approaches without specifying broad improvements.
The paper tackled retinal vessel segmentation by introducing a novel topological method that represents blood vessels as connected regions with shape-related properties, and reported results on the DRIVE database.
A novel topological segmentation of retinal images represents blood vessels as connected regions in the continuous image plane, having shape-related analytic and geometric properties. This paper presents topological segmentation results from the DRIVE retinal image database.