Abstract—The automatic extraction of objects from data and images has been a topic of research for decades. In this paper, we present a novel approach for object recognition based on the Radon Transform (RT). A new exploitation of the Radon Transform is proposed to extract only one projection according to an angle. This projection will be chosen in the way that contains the necessary information to recognize an object (a shape descriptor). This descriptor (called Rθ-signature) provides global information of a binary shape regardless its form. The signature allows keeping fundamental geometrical transformation like scale, translation and rotation. After that, we use this signature in the automatic extraction of buildings in high-resolution satellite imagery.
Index Terms—Shape descriptor, radon transform, Rθ-signature, building extraction.
The authors are with Laboratory of Computing in Programming, Algorithmic and Heuristic, Faculty of Sciences of Tunis, Campus Universities - Tunis - 1060, Tunisia (e-mail: atef_hammouda@yahoo.fr; e-mail: hmida.rjb@gmail.com).
Cite: A. Hamouda and H. Rojbani, "Rθ-Signature: a New Signature Based on Radon Transform and its Application," International Journal of Modeling and Optimization vol. 2, no. 1, pp. 58-63, 2012.
Copyright © 2008-2024. International Journal of Modeling and Optimization. All rights reserved.
E-mail: ijmo@iacsitp.com