Super resolution image reconstruction using weighted combined Pseudo-Zernike moment invariants

This paper proposes a multi-image super resolution reconstruction method to estimate a high resolution (HR) image without performing exact image registration, de-blurring and de-noising of available low resolution images. Pixels in the HR image are estimated based on the weighted average of the neighborhood pixels. The weights in the averaging process measure the correlation between pixels and are calculated using a set of feature vectors based on weighted combined Pseudo-Zernike moment invariants (WCPZMIs) of optimum order. WCPZMIs are those reliable Pseudo-Zernike moment invariants (PZMIs) which are simultaneously insensitive to geometric transformations (rotation, scaling, and translation) as well as degradations (blur) and are relatively weighted according to their reconstruction capability. An energy minimization scheme is employed to select the optimal order of WCPZMIs which makes a trade-off between the quality of reconstruction and robustness to noise. An efficient way of weighting the feature vectors and the recursive approach for the computation of PZMIs are utilized to reduce the computational overload of the reconstruction process. Besides, an appropriate square-to-circle mapping followed by a radial geometric moment-to-PZM approximation is adopted to reduce the geometric and the numerical error respectively. Experimental results of the proposed method outperform as compared to similar contributions in literature.