Title: An adaptive-size median filter for impulse noise removal using neural network-based detector

Authors: R. Rashidha; Philomina Simon

Addresses: Department of Computer Science, Muslim Association College of Engineering, Trivandrum, Kerala, India ' Department of Computer Science, University of Kerala, Kariavattom, Trivandrum, Kerala, India

Abstract: In this paper, a neural network-based Adaptive-Size Median (ASMED) filter is proposed for impulse noise removal. This method consists of two stages: noise detection and noise filtering. Noise detection is performed by a neural network-based detector, and filtering is applied only to corrupt pixels in the noisy image. Extensive experimental analysis shows that the proposed technique can be used for images with different impulse noise models. Both quantitative and qualitative analyses show the superiority of the proposed filter over other existing filters. The proposed method is applied to both colour images and greyscale images, and better results are obtained.

Keywords: neural networks; adaptive sized median filters; image denoising; noise models; impulse noise removal; salt and pepper noise; random-valued noise; noise detection; noise filtering; colour images; greyscale images; image processing.

DOI: 10.1504/IJSISE.2016.078254

International Journal of Signal and Imaging Systems Engineering, 2016 Vol.9 No.4/5, pp.305 - 310

Received: 01 Apr 2013
Accepted: 24 Apr 2014

Published online: 10 Aug 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article