Premium
A neural network‐based nonlinear filter for image enhancement
Author(s) -
Zhang S.,
Salari E.
Publication year - 2002
Publication title -
international journal of imaging systems and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.359
H-Index - 47
eISSN - 1098-1098
pISSN - 0899-9457
DOI - 10.1002/ima.10009
Subject(s) - sharpening , computer science , impulse noise , gaussian noise , artificial neural network , filter (signal processing) , noise (video) , nonlinear system , enhanced data rates for gsm evolution , artificial intelligence , image (mathematics) , algorithm , computer vision , pixel , physics , quantum mechanics
This paper explores a novel neural network‐based nonlinear filter that has the ability to remove mixed noises and sharpen the edges in noise‐corrupted digital images. The noise is assumed to be a mixture of both Gaussian and impulse types. Initially, a nonlinear filter is used to reduce the noise. The smoothed image is then combined with the output of an edge detector using a synthesizer to provide the effect of noise reducing and edge sharpening. The smoother and synthesizer are designed by using layered neural networks. Simulation results show that the proposed filter can effectively remove the mixed Guassian and impulsive noises and sharpen the edges. It can adapt itself to the various noise environments by learning during the training process. © 2002 Wiley Periodicals, Inc. Int J Imaging Syst Technol 12, 56–62, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.10009