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.