Image Resolution Enhancement Using a Hopfield Neural Network
Shuangteng Zhang, LU Yi-hong · 2007
This paper presents a neural network-based method for image super-resolution. In this technique, the super-resolution is considered as an ill-posed inverse problem which is solved by minimizing an evaluation function established based on an observation model that closely follows the physical image acquisition process. A Hopfield neural network is created to obtain an optimal solution to the problem. Not like some other single-frame super-resolution techniques, this technique takes into consideration PSF (point spread function) blurring as well as additive noise and generates high-resolution images with more preserved or restored image details. Experimental results demonstrate that the high-resolution images obtained by this technique have a very high quality in terms of PSNR (peak signal-to-noise ratio) and visually look more pleasant