Super-resolution of images based on local correlations

Abstract

An adaptive two-step paradigm for the superresolution 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 super-resolved 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.

Super-resolution: a comprehensive survey

“…Previous survey papers on SR algorithms have mostly considered these factors as well. [5], [6], [7], [8], [13], [14], [20] [49], [50], [51], [53], [55], [56], [57], [58], [60], [61], [62], [63], [64], [65], [66], [71], [72], [73], [74], [75], [76], [80], [81], [82] [99], [100], [102], [105], [107], [108], [109], [111], [112], [113], [115], [116], [117], [118], [121], [122], [123], [124], [125], …”

“…Examples of such networks are Linear Associative Memories (LAM) with single [61] and dual associative learning [192], Hopfield NN [96], [326], Probabilistic NN [130], [304], Integrated Recurrent NN [136], Multi Layer Perceptron (MLP) [196], [354], [385], [547], Feed Forward NN, [232], [233], and Radius Basis Function (RBF) [327], [607].…”

Image Magnification Based on the Human Visual Processing

“…Cubic convolution interpolation improved the loss of image like the nearest neighbor interpolation and bilinear interpolation. But it is slow as it uses the offset of 16 neighborhood pixels (Aoyama & Ishii, 1993;Candocia & Principe, 1999;Biancardi et al, 2002). A number of methods for magnifying images have been proposed to solve such problems.…”

A Learning-Based Method for Image Super-Resolution From Zoomed Observations

“…The prior term enforces the condition that the gradient of the super-resolved image should be equal to the gradient of the best matching training image. Candocia and Principe [38] address the problem of ill-posedness of the super-resolution by assuming that the correlated neighbors remain similar across scales, and this a priori information is learned locally from the available image samples across scales. When a new image is presented, a kernel that best reconstructs each local region is selected automatically, and the super-resolved image is reconstructed by simple convolution operation.…”