Recently the tensor voting framework (TVF), proposed by Medioni at al., has proved its effectiveness in perceptual grouping of arbitrary dimensional data. In the computer vision field, this algorithm has been applied to solve various problems as stereo-matching, boundary inference, and image inpainting. In the last decade the TVF was augmented with new saliency features, like curvature and first order tensors. In this paper a new curvature estimation technique is described and its effectiveness, when used with the saliency functions proposed in [1], is demonstrated. Results are shown for synthetic datasets in spaces of different dimensionalities.
Curvature Estimation and Curve Inference with Tensor Voting: a New Approach / G. Lombardi, E. Casiraghi, P. Campadelli - In: Advanced Concepts for Intelligent Vision Systems : 10th International Conference, ACIVS 2008, Juan-les-Pins, France, October 20-24, 2008 : Proceedings / [a cura di] Jacques Blanc-Talon Salah Bourennane, Wilfried Philips Dan Popescu, Paul Scheunders. - Berlin : Springer, 2008. - ISBN 978-3-540-88457-6. - pp. 613-624 (( Intervento presentato al 10. convegno Advanced Concepts for Intelligent Vision Systems tenutosi a Juan-les-Pins, France nel 2008 [10.1007/978-3-540-88458-3_55].
Curvature Estimation and Curve Inference with Tensor Voting: a New Approach
G. Lombardi;E. Casiraghi;P. Campadelli
2008
Abstract
Recently the tensor voting framework (TVF), proposed by Medioni at al., has proved its effectiveness in perceptual grouping of arbitrary dimensional data. In the computer vision field, this algorithm has been applied to solve various problems as stereo-matching, boundary inference, and image inpainting. In the last decade the TVF was augmented with new saliency features, like curvature and first order tensors. In this paper a new curvature estimation technique is described and its effectiveness, when used with the saliency functions proposed in [1], is demonstrated. Results are shown for synthetic datasets in spaces of different dimensionalities.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
