A survey of thresholding techniques
Computer Vision, Graphics, and Image Processing
Zero-crossing interval correction in tracing eye-fundus blood vessels
Pattern Recognition
Performance study of several global thresholding techniques for segmentation
Computer Vision, Graphics, and Image Processing
Fast raster scan distance propagation on the discrete rectangular lattice
CVGIP: Image Understanding
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
We propose a novel approach to blood vessel detection in retinal images using shape-based multi-threshold probing. On an image set with hand-labeled ground truth our algorithm quantitatively demonstrates superior performance over the basic thresholding and another method recently reported in the literature. The core of our algorithm, classification-based multi-threshold probing, represents a general framework of segmentation that has not been explored in the literature thus far. We expect that the framework may be applied to a variety of other tasks.