Neural based Post Processing Filtering Technique for Image Quality Enhancement

R. Pushpavalli, G. Sivaradje, E. Srinivasan, S.Himavathi S.Himavathi
2012 International Journal of Computer Applications  
Digital images are often affected by impulse noise during image acquisition and/or transmission over communication channel. A Neural Based Post Processing Technique for Image Quality Enhancement (NBPPTIQE) for enhancing digital images corrupted by impulse noise is proposed in this paper. The proposed filter is an intelligent filter obtained by aptly combining a Nonlinear Filter (NF), Modified Canny Edge Detector (MCED) and a Feed forward Adaptive Neural (FAN) Network. The internal parameters of
more » ... the Feed Forward Neural Network are adaptively optimized by training of well known images. The most distinctive feature of the proposed filter offers good line, edge, and fine detail preservation performance and also effectively removes impulse noise from the image. Extensive simulation results show that the proposed Post Processing Technique can be used for efficient enhancement of digital images corrupted by impulse noise without distorting useful information in the image. The performance of proposed filter is compared with median based filter and Neural Filter and shown to be more effective in terms of eliminating impulse noise and preserving edges and fine details of digital images.
doi:10.5120/4591-6787 fatcat:u7ev6rs55fay3jnv7puswsrflu