Finding junctions using the image gradient
David Beymer · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2002
The author proposes a junction detector that works by filling in gaps at junctions in edge maps. It uses the image gradient to guide extensions of disconnected edges at junctions. A novel representation for the gradient, the bow tie map, is used to implement the endpoint growing rules, which include following gradient ridges and using saddle points in the gradient magnitude. The authors demonstrate the junction detector on real imagery.>
Cited by 28 works. doi:10.1109/cvpr.1991.139798
Authors
References
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- A Computational Approach to Edge Detection
- Theory of edge detection
- Edge and Curve Detection for Visual Scene Analysis
- SCALE-SPACE FILTERING
- Perceptual organization and visual recognition
- On seeing things
- Understanding Line drawings of Scenes with Shadows
- Digital Step Edges from Zero Crossing of Second Directional Derivatives
- On Edge Detection