Interest point detection using imbalance oriented selection
Pattern Recognition
Image alignment and stitching: a tutorial
Foundations and Trends® in Computer Graphics and Vision
Multiobjective design of operators that detect points of interest in images
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Local invariant feature detectors: a survey
Foundations and Trends® in Computer Graphics and Vision
Corner validation based on extracted corner properties
Computer Vision and Image Understanding
Corner detection based on gradient correlation matrices of planar curves
Pattern Recognition
Interest points of general imbalance
IEEE Transactions on Image Processing
Feature points detection using combined character along principal orientation
MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
A crossing detector based on the structure tensor
ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
On interest point detection under a landmark-based medical image registration context
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Interest point detection through multiobjective genetic programming
Applied Soft Computing
Accurate Junction Detection and Characterization in Natural Images
International Journal of Computer Vision
| Hi-index | 0.00 |
This paper presents an axiomatic approach to corner detection. In the first part of the paper we review five currently used corner detection methods (Harris-Stephens, Förstner, Shi-Tomasi, Rohr, and Kenney et al. ) for graylevel images. This is followed by a discussion of extending these corner detectors to images with different pixel dimensions such as signals (pixel dimension one) and tomographic medical images (pixel dimension three) as well as different intensity dimensions such as color or LADAR images (intensity dimension three). These extensions are motivated by analyzing a particular example of optical flow in pixel and intensity space with arbitrary dimensions. Placing corner detection in a general setting enables us to state four axioms that any corner detector might reasonably be required to satisfy. Our main result is that only the Shi-Tomasi (and equivalently the Kenney et al. 2-norm detector) satisfy all four of the axioms