IEEE Transactions on Pattern Analysis and Machine Intelligence
Corner detection and curve representation using cubic B-spline
Computer Vision, Graphics, and Image Processing
Image and Vision Computing
Localization and Noise in Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition
Some Defects in Finite-Difference Edge Finders
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing corners by fitting parametric models
International Journal of Computer Vision
A computational approach for corner and vertex detection
International Journal of Computer Vision
Junction classification by multiple orientation detection
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Graphical Models and Image Processing
SUSAN—A New Approach to Low Level Image Processing
International Journal of Computer Vision
Junctions: Detection, Classification, and Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Detection of General Edges and Keypoints
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Object-level structured contour map extraction
Computer Vision and Image Understanding
Object-level structured contour map extraction
Computer Vision and Image Understanding
Computer Vision and Image Understanding
Accurate junction detection and characterization in line-drawing images
Pattern Recognition
Accurate Junction Detection and Characterization in Natural Images
International Journal of Computer Vision
Hi-index | 0.00 |
A new junction characterization and validation method is proposed. Junction branches of volumetric objects are extracted at interest points in a 2D image, using a topologically constrained grouping process. This is followed by structural validation and position refinement of extracted junctions. An interesting feature of the proposed method is that all types of junctions are described uniformly and extracted using the same generic process. For instance, the size of the interest regions is kept constant despite local variations in contour density and curvature. Validation rate of real junctions is high and most false hypotheses are properly rejected. An experimental evaluation illustrates the capabilities of the proposed method in demanding situations.