Radial Meixner moments for rotational invariant pattern recognition
Mostafa El Mallahi, Amal Zouhri, Jaouad El-Mekkaoui, Hassan Qjidaa · 2017
This paper proposes the discrete orthogonal radial Meixner moments in the polar coordinate, there is the better descriptor in image processing applications and pattern recognition. However, the translation and scale invariant property of these moments haven't studied due to its complexity of the problem. In this paper, we present an algorithm to compute a new set of rotation invariants extracted from radial Meixner moments, named radial Meixner moment invariants (MIω). Experimental results show the efficiency and the robustness to reconstruction error (MSE) and CPU time of the proposed method.