This paper presents a novel approach to identify complex shapes based on the Radon transform. We propose an adaptation of Radon transform called $\mathcal R$-transform which is invariant to common geometrical transformations. Moreover, to improve the uniqueness of the approach, a binary shape is projected into the Radon space for different levels of the Chamfer distance transform. The accuracy and the efficiency of the proposed algorithm in the presence of a variety of transformations are evaluated within a shape recognition process.
Salvatore Tabbone, Laurent Wendling, Jean-Pierre Salmon. A new shape descriptor defined on the Radon transform. Computer Vision and Image Understanding, 2006,102 (1), pp.42--51. ⟨10.1016/j.cviu.2005.06.005⟩. ⟨inria-00000643⟩
Citations
APA
A new shape descriptor defined on the Radon transform. (2006). In Computer Vision and Image Understanding. https://api.istex.fr/ark:/67375/6H6-DJMZ8TG8-X/fulltext.pdf?sid=hal
MLA
“A New Shape Descriptor Defined on the Radon Transform.” Computer Vision and Image Understanding, Apr. 2006, https://api.istex.fr/ark:/67375/6H6-DJMZ8TG8-X/fulltext.pdf?sid=hal.
Chicago
“A New Shape Descriptor Defined on the Radon Transform.” 2006. Computer Vision and Image Understanding. https://api.istex.fr/ark:/67375/6H6-DJMZ8TG8-X/fulltext.pdf?sid=hal.
Harvard
“A new shape descriptor defined on the Radon transform” (2006) Computer Vision and Image Understanding. Available at : https://api.istex.fr/ark:/67375/6H6-DJMZ8TG8-X/fulltext.pdf?sid=hal.
ISO 690
A new shape descriptor defined on the Radon transform, 2006. [en ligne]. Disponible à l'adresse : https://api.istex.fr/ark:/67375/6H6-DJMZ8TG8-X/fulltext.pdf?sid=hal