Color image super-resolution reconstruction based on IMED

摘要

In this paper, a novel color image super-resolution reconstruction algorithm based on IMage Euclidean Distance (IMED) and manifold learning is proposed. Firstly, the wavelet decomposition is used to extract features from training images. Then IMED is adopted for the computation of distances between pairs of small patches. Finally, the color high resolution image is reconstructed in YCbCr space in the framework of locally linear embedding. Experimental results demonstrate that the proposed method has better performance in comparison with the manifold learning method that is not combined with IMED.