How to overcome perceptual aliasing in ASIFT?
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
A probabilistic grouping principle to go from pixels to visual structures
DGCI'11 Proceedings of the 16th IAPR international conference on Discrete geometry for computer imagery
Transportation Distances on the Circle
Journal of Mathematical Imaging and Vision
SIAM Journal on Imaging Sciences
Space-Efficient approximation scheme for circular earth mover distance
LATIN'12 Proceedings of the 10th Latin American international conference on Theoretical Informatics
Beyond Independence: An Extension of the A Contrario Decision Procedure
International Journal of Computer Vision
Adaptive structure from motion with a contrario model estimation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Accurate Junction Detection and Characterization in Natural Images
International Journal of Computer Vision
On the Role of Contrast and Regularity in Perceptual Boundary Saliency
Journal of Mathematical Imaging and Vision
Hi-index | 0.00 |
This paper focuses on the matching of local features between images. Given a set of query descriptors and a database of candidate descriptors, the goal is to decide which ones should be matched. This is a crucial issue, since the matching procedure is often a preliminary step for object detection or image matching. In practice, this matching step is often reduced to a specific threshold on the Euclidean distance to the nearest neighbor. Our first contribution is a robust distance between descriptors, relying on the adaptation of the Earth Mover's Distance to circular histograms. It is shown that this distance outperforms classical distances for comparing SIFT-like descriptors, while its time complexity remains reasonable. Our second and main contribution is a statistical framework for the matching procedure, which yields validation thresholds automatically adapted to the complexity of each query descriptor and to the diversity and size of the database. The method makes it possible to detect multiple occurrences, as well as to deal with situations where the target is not present. Its performances are tested through various experiments on a large image database.