Junctions: Detection, Classification, and Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision and Image Understanding
Introductory Techniques for 3-D Computer Vision
Introductory Techniques for 3-D Computer Vision
Steerable-Scalable Kernels for Edge Detection and Junction Analysis
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Kona: A Multi-junction Detector Using Minimum Description Length Principle
EMMCVPR '97 Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Segmentation by Grouping Junctions
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
This paper describes a new simple and fast method, elaborated and tested by authors, for corner orientation detection. The conventional L-, T-, Y- and X- corner or junctions are important dominant features belonging to object patterns in digital images. A small set of locally defined parameters: position, orientation, scale, phase and curvature can characterize these elementary structures. "Orientation" in 2D plan of corners is a strong feature. It was successfully utilized for pattern recognition in 2D images. They provide significant information regarding objects under translation, rotation and scale change. However, when compared to the number of corner detection methods for junction location, a a limited number of solution allow for determining spatial orientation. Our proposed method, described in this paper, is simple, practical and efficient. The accuracy of the corner detector algorithm was tested with synthetic and natural images. Similar to other known methods, the elaborated algorithm may be useful to image pre-processing, object recognition applications and vision systems, particularly for scenes that contain polygonal objects.