Directional feature detection and correspondence

Authors:
Wen-Hao Wang;Fu-Jen Hsiao;Tsuhan Chen
Affiliations:
Industrial Technology Research Institute, Taiwan;Industrial Technology Research Institute, Taiwan;Carnegie Mellon University, US
Venue:
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part II
Year:
2005

Citing 5
Cited 0

In Defense of the Eight-Point Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Design of steerable filters for feature detection using canny-like criteria

IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method is proposed to detect useful directional feature points other than corner points considering that the number of corner points may not be sufficient in a scene. This is achieved by directional analysis of properties of image points by virtue of the proposed gradient operators with different direction topologies. A matching criterion is also proposed to find the initial correspondence by using the feature vectors that are acquired from the results of directional analysis. For the purpose of improving the final correspondence, four constraints are employed in the system to seek and refine the correspondence.