1 Super - Resolution of Images Based on Local Correlations

An adaptive two step paradigm for the super-resolution of optical images is developed in this paper. The procedure locally projects image samples onto a family of kernels that are learned from image data. First, an unsupervised feature extraction is performed on local neighborhood information from a training image. These features are then used to cluster the neighborhoods into disjoint sets for which an optimal mapping relating homologous neighborhoods across scales can be learned in a supervised manner. A superresolved image is obtained through the convolution of a low resolution test image with the established family of kernels. Results demonstrate the effectiveness of the approach. TNN A043 Rev, Resubmitted to the IEEE Transactions on Neural Networks for publication Corresponding author: Jose C. Principe, Ph.D. BellSouth Professor Dept. of Electrical and Computer Engineering University of Florida 451 Engineering Building PO Box 116130 University of Florida Gainesville, FL. 32611-6130 Tel: (352) 392-2662 Fax: (352) 392-0044 email: [email protected]