Abstract
Many image processing applications requires Impulsive noise elimination. Windyga’s peak-and-valley filter used to remove impulsive noise, its main disadvantage is that it works only for low density of noises. In this Paper, a variation of the two dimensional peak-and-valley filters is proposed to overcome this problem. It is based on minimum/maximum values present in the noisy image, which replaces the noisy pixel with a value based on neighborhood information based on the outcomes of PCNN (Pulse Coupled Neural Network). This method preserves constant and edge areas even under high impulsive noise probability. Extensive Computer simulations show that the proposed approach outperforms other filters in the noise reduction and the image details preservation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Johnson, J.L.: PCNN Models and Applications. IEEE Trans. Neural Networks 10(3), 480–498 (1999)
Chan, R.H., Hu, C., Nikolova, M.: An iterative procedure for removing random valued impulse noise. IEEE Signal Process. Lett. 11(12), 921–924 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dhiraj, K., Kumar, E.A., Baliar Singh, R., Rath, S.K. (2009). PCNN Based Hybrid Approach for Suppression of High Density of Impulsive Noise. In: Prasad, S.K., Routray, S., Khurana, R., Sahni, S. (eds) Information Systems, Technology and Management. ICISTM 2009. Communications in Computer and Information Science, vol 31. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00405-6_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-00405-6_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00404-9
Online ISBN: 978-3-642-00405-6
eBook Packages: Computer ScienceComputer Science (R0)