A Novel Filtering Scheme for Impulse Noise Cancellation

Abstract

This paper proposes a novel filtering scheme to denoise images contaminated by impulse noise of high densities. This scheme utilizes two stage operations. In the first stage, corrupted image is passed through the Artificial Neural Network (ANN) detector to identify the noisy pixels by considering their surrounding neighborhood. The corrupted pixels are passed through the Discrete Wavelet Transform (DWT) based pre-filter and the filtered pixels are replaced back in the image. The pre-filtered image is further passed through the ANN detector to capture any residual corruption. A novel selective spatial filtering scheme is proposed for the corrupted pixels. The proposed scheme is simulated using standard images under different noise conditions. The comparative performance study shows the superiority of the proposed scheme over the existing standard filtering schemes both in terms of noise rejection and edge retention capability even under high noise conditions.

Indexing terms:

• Impulse noise
• Pre-filtering
• Discrete wavelet transform
• ANN detector
• Spatial filtering

Additional information

Notes on contributors

G Panda

Ganapati Panda obtained his BE degree in Electrical Engg with First Class Honours in 1971, MSc Engg in Communication Systems in 1977 from Sambalpur University and PhD degree in Digital Signal Processing from IIT, Kharagpur in 1982. He was a Common Wealth Fellow at University of Edinburgh during 1984–86 specializing in Adaptive Signal Processing. He was a Lecturer (University College of Engg Burla, Orissa) during 1972–79, Reader (University College of Engg Burla, Orissa) in electronics during 1979–88. He joined as the founder Head of Applied Electronics and Insnt Engg at Regional Engg College, Rourkela in 1988 and continuing till date. He has published more than 160 research papers in referred National and International Journals and Conferences. He is a Fellow National Academy of Engineering (FNAE), Fellow of Institute of Engg, India, Fellow of IETE, New Delhi, Life member of ISTE and a Senior Member of IEEE, USA. He has successfully completed many R&D projects sponsored by different agencies. He has visited UK, USA, Japan, France and Singapore on academic assignments. He acts as reviewer to various Research Journals of IETE (India), CSI (India), IEE(UK) and IEEE(USA). His research interests are in Digital Signal Processing, Data Communication, Soft Computing, and Intelligent Instrumentation.

B Majhi

B Majhi obtained his MCA degree in 1988, ME degree in Computer Sc & Engg in 1997 from Sambalpur University and currently working as an Asst Professor in the Computer Science department in Regional Engineering College, Rourkela. He has 3 years industry experience in leading industries and 10 years of teaching experience. He has published more than 12 research papers in various National Journals and International Conferences. He is a Life member of CSI, Fellow of IETE (India). His research interests are in the field of Image Processing, Soft-Computing, and E-Commerce.

S K Meher

S K Meher has completed his doctoral work in Digital Data Compression and is working as a lecturer in GIET, Gunupur since 2001. He has published many research papers in various Journals and conferences. His areas of research interest are Digital Signal Processing and Data Communication.

P K Dash

P K Dash has taken superannuation as a professor in Electrical Engineering and Chairman, Centre for Intelligent systems, Regional Engineering College, Rourkela in 2001. He is educated at the Utkal University, IISc, Bangalore, and the University of Calgory, Canada. Professor has held several visiting appointments in the universities of Canada, USA and Singapore. He has worked with Poristol Aerospace, Canada and BBC Brown, Broveri Switzerland. To his credit, Professor Dash has published more than 200 technical papers in referenced International Journals & Conferences. His interests are in the areas of Al applications to power & Signal Processing.