| Summary: | 碩士 === 國立東華大學 === 應用數學系 === 97 === In this paper, we explore blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that
a degraded image is linear convolution of an original source image through a linear shift-invariant (LSI) blurring matrix. Now, we employ learning an RBF (radial basis functions) neural network to construct an embedded recursive function within a blurring image, try to extract non-deterministic component of an original source image, and use them to estimate hyper parameters of a linear image degradation model. Based on the estimated blurring matrix, we further apply an annealed Hopfield neural network to reconstruct an original source image from a blurred image. By numerical simulations, the proposed novel method is shown e ective for faithful estimation of an unknown blurring matrix and restoration of an original source image.
|
|---|
