Skip to Main content Skip to Navigation
Journal articles

Measuring rectangularity using GR-signature. Advances in pattern recognition

Abstract : Object recognition often operates by making decisions based on the values of several shapes properties measured from an image of the object. In this paper, we propose a new exploitation of the Radon Transform using the gradient measurement to generate a new signature (GR-signature) which provides global information of a binary shape regardless its form. We also develop a new method for measuring the rectangularity based on GR-signature. This original approach looks very promising and has several useful properties that keep fundamental geometrical transformations like scale, rotation and translation.
Document type :
Journal articles
Complete list of metadatas
Contributor : Rosine Schlumberger <>
Submitted on : Monday, September 19, 2011 - 4:33:39 PM
Last modification on : Tuesday, November 24, 2020 - 10:50:13 AM


  • HAL Id : halshs-00624753, version 1



Jihen Hentati, Mohamed Naouai, Atef Hamouda, Christiane Weber. Measuring rectangularity using GR-signature. Advances in pattern recognition. Lecture Notes in Computer Science, Springer, 2011, 6718, pp.136-145. ⟨halshs-00624753⟩



Record views