Search

Abstract: Super-resolution image reconstruction is the process of producing a high-resolution image from a set of low-resolution images of the same scene. For the applications of performing face evaluation and/or recognition from low-resolution video surveillance, in the past, super-resolution image reconstruction was mainly used as a separate preprocessing step to obtain a high-resolution image in the pixel domain that is later passed to a face feature extraction and recognition algorithm. Such three-stage approach suffers a high degree of computational complexity. A low-dimensional morphable model space based face super-resolution reconstruction and recognition algorithm is proposed in this paper. The approach tries to construct the high-resolution information both required by reconstruction and recognition directly in the low dimensional feature space. We show that comparing with generic pixel domain algorithms, the proposed approach is more robust and more computationally efficient. [Copyright &y& Elsevier]

Abstract: Super-resolution image reconstruction produces a high-resolution image from a set of shifted, blurred, and decimated versions thereof. Previously published papers have not addressed the computational complexity of this ill-conditioned large scale problem adequately. In this paper, the computational complexity of MAP-based multiframe super-resolution algorithms is studied, and a new fast algorithm, as well as methods for parallel image reconstruction is also presented. The proposed fast algorithm splits the multiple input low-resolution images into several subsets according to their translation relations, and then applies normal MAP algorithm to each subset, the reconstructed images are processed subsequently at a successive level until the desired resolution is achieved. Experiment results are also provided to demonstrate the efficiency of the proposed techniques. [Copyright &y& Elsevier]