EM-based simultaneous registration, restoration, and interpolation of super-resolved images

We present a maximum likelihood (Ml) solution to the problem of obtaining high-resolution images from sequences of noisy, blurred, and low-resolution images. In our formulation, the registration parameters of the low-resolution images, the degrading blur, and noise varianceare unknown. Our algorithm has the advantage that all unknownparameters are obtained simultaneously using all of the available data. An efficient implementation is presented in the j-equency domain, based on the Expectation Maximization (EM algorithm. Simulations demonstrate the eflectiseness of the algorithm.

• Type: Conference
• Year: 2003
• Where: ICIP
• Authors: Nathan A. Woods, Nikolas P. Galatsanos, Aggelos K. Katsaggelos
• Keywords: EM Algorithm, Expectation Maximization, ICIP 2003, Image Processing, Low-resolution Images