Work

Deformable kernels for early vision

Year: 2002

Type: conference-paper

Abstract: A technique is presented that allows (1) computing the best approximation of a given family using linear combinations of a small number of basis functions; and (2) describing all finite-dimensional families, i.e. the families of filters for which a finite-dimensional representation is possible with no error. The technique is general and can be applied to generating filters in arbitrary dimensions. Experimental results that demonstrate the applicability of the technique to generating multi-orientation multiscale 2-D edge-detection kernels are presented. The implementation issues are also discussed.>

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr.1991.139691

Author: P. Perona

Institutions: University of Padua, Massachusetts Institute of Technology

Language: English

Topic: Mathematical Analysis and Transform Methods

Subfield: Applied Mathematics

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funder: Army Research Office

OpenAlex ID: W2111782371

FWCI: 5.669

Cites: 56

Cited by: 54

Related to: 10