Abstract

This thesis concerns the use of spatial and tonal adaptivity in improving the resolution of aliased image sequences under scene or camera motion. Each of the five content chapters focuses on a different subtopic of super-resolution: image registration (chapter 2), image fusion (chapter 3 and 4), super-resolution restoration (chapter 5), and super-resolution synthesis (chapter 6). Chapter 2 derives the Cramer-Rao lower bound of image registration and shows that iterative gradient-based estimators achieve this performance limit. Chapter 3 presents an algorithm for image fusion of irregularly sampled and uncertain data using robust normalized convolution. The size and shape of the fusion kernel is adapted to local curvilinear structures in the image. Each data sample is assigned an intensity-related certainty value to limit the influence of outliers. Chapter 4 presents two fast implementations of the signal-adaptive bilateral filter. The xy-separable implementation filters the image along sampling axes, while the uv-separable implementation filters the image along gauge coordinates. Chapter 5 presents a robust image restoration method using Gaussian error norm rather than quadratic error norm. The robust solution resembles the maximum-likelihood solution under Gaussian noise, and it is not susceptible to outliers. A series of objective quality measures confirms the superiority of this solution to current super-resolution algorithms in the literature. Chapter 6 proposes a super-resolution synthesis algorithm in the DCT domain. The algorithm requires a high-resolution image of similar content to be used as texture source for the low-resolution input image.