A Collaborative Nonlocal-Means Super-resolution Algorithm Using Zernike Monments

Super-resolution (SR) with probabilistic motion estimation is a successful algorithm to circumvent the limitation of motion estimation upon conventional superresolution methods. However, the algorithm can’t match similar patches with rotation or scale. This paper presents an efficient improved algorithm by introducing Zernike moments as representation of image invariant features into similarity measure. A collaborative strategy is proposed combining the moment based proximity and the bilateral proximity of nonlocal means (NL-means) algorithm for joint determination of weights. For the invariant property of Zernike moments, structure-similar pixels with rotation or scale can also be matched for computation of weights. Furthermore, the collaborative mechanism ensures higher accuracy of weights for a better estimation of each pixel in SR images. Experimental results indicate the proposed method is able to handle general video sequences with superior performance in SR reconstruction to the compared algorithms.