An Efficient Algorithm for Fast Computation of Pseudo-Zernike Moments

Pseudo-Zernike moments have better feature representation capabilities and are more robust to image noise than the conventional Zernike moments. However, pseudo-Zernike moments have not been extensively used as feature descriptors due to the computational complexity of the pseudo-Zernike radial polynomials. This paper discusses the drawbacks of the existing methods, and proposes an efficient recursive algorithm to compute the pseudo-Zernike moments. The algorithm consists of a two-stage recurrence relation for radial polynomials and coefficients of the polynomials, which are specifically derived for fast computation of pseudo-Zernike moments. The performance of the algorithm is experimentally examined using both binary and grayscale images, and it shows that the computational speed of pseudo-Zernike moments has been substantially improved over the present methods.