Title: Fitting superellipses to incomplete contours
Authors: Osian, Mihai
Tuytelaars, Tinne
Van Gool, Luc #
Issue Date: 2004
Host Document: CVPR workshop on perceptual organization in computer vision - POCV '04 vol:4 pages:49
Conference: IEEE workshop on perceptual organization in computer vision - POCV '04 location:Washington, DC, USA date:June 28
Abstract: Affine invariant regions have proved a powerful feature for object recognition and categorization. These features heavily rely on object textures rather than shapes, however. Typically, their shapes have been fixed to ellipses or parallelograms. The paper proposes a novel affine invariant region type, that is built up from a combination of fitted superellipses. These novel features have the advantage of offering a much wider range of shapes through the addition of a very limited number of shape parameters, with the traditional ellipses and parallelograms as subsets. The paper offers a solution for the robust fitting of superellipses to partial contours, which is a crucial step towards the implementation of the novel features.
Description: Proceedings IEEE workshop on perceptual organization in computer vision - POCV '04, 8 pp., June 28, 2004, Washington, DC, USA
Publication status: published
KU Leuven publication type: IC
Appears in Collections:ESAT - PSI, Processing Speech and Images
# (joint) last author

Files in This Item:
File Status SizeFormat
Osian_Tuytelaars_VanGool-superellipses-pocv2004.pdf Published 436KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.