Digital Image RestorationAggelos Konstantinos Katsaggelos The field of digital image restoration is concerned with the reconstruction or estimation of uncorrupted images from noisy, blurred ones. This blurring may be caused by optical distortions, object motion during imaging, or atmospheric turbulence. There are existing or potential applications of image restoration in many scientific and engineering fields, e.g. aerial imaging, remote sensing electron microscopy, and medical imaging. This book describes recent advances and provides a survey of the field. New research results are presented on the formulation of the restoration problem, the implementation of restoration algorithms using artificial neural networks, the derivation and application of nonstationary mathematical image models, the development of simultaneous image and blur parameter identification and restoration algorithms, and the development of algorithms for restoring scanned photographic images. Special attention is paid to issues of numerical instrumentation. A large number of illustrations demonstrate the performance of the restoration approaches. |
Other editions - View all
Common terms and phrases
ACAM approach assumed Biemond blur identification blur PSF CD_xy algorithm complete data compound GMRF model computed constraint convergence convex convex set covariance cross entropy defined degraded image denotes density domain deterministic dual EM algorithm equation exposure domain Gaussian gray level Hopfield network IEEE IEEE Trans image and blur image estimation image model Image Processing image restoration implementation iterations J. W. Woods Kalman filter Katsaggelos least-squares library vectors likelihood function linear M₁ MAP estimate Markov random field matrix maximum likelihood method minimization minimum minimum phase model parameters multiplicative noise neural network nonlinear observation noise observed image obtained optical density optimal original image parameter identification perceptron photographic film photographic images pixels power spectrum Proc random field recursive region restoration algorithms restoration problem restoration results restored image ROMKF samples Sect shown in Fig simulated annealing solution spatial stationary techniques Tekalp update values variance Wiener filter window