Video Denoising using Surfacelet Transform By Optimised Entropy Thresholding
Mohammed Khalid1, P. Sajith Sethu2

1Mohammed Khalid, Department of Electronics and Communication Engineering, Sree Chitra Thirunal College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
2P. Sajith Sethu, Assistant Professor, Department of Electronics and Communication Engineering, Sree Chitra Thirunal College of Engineering Pappanamcode, Trivandrum (Kerala), India.

Manuscript received on 13 August 2016 | Revised Manuscript received on 20 August 2016 | Manuscript Published on 30 August 2016 | PP: 42-45 | Volume-5 Issue-6, August 2016 | Retrieval Number: F4679085616/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The primary aim of all video denoising systems is to remove noise from a corrupted video sequence. A video is corrupted often due to the limitations of the acquisition and processing devices. Most of the conventional video denoising schemes employ the technique of motion estimation or the optical flow estimation. Motion estimation is mostly an arduous technique particularly in conditions with lighting variations. Motion estimation step is also worsened due to the aperture problem of the optical flow estimation. This limitation of motion estimation paved the way for wavelet transform based video denoising techniques. Unfortunately, those systems resulted in videos with jittery edges and curves. Surfacelet transform is a potential tool used for the processing of multidimensional data. Video signals, which can be dealt as a different type of 3D signal, can be processed using surfacelet transform which preserves the visual quality and edge information. Entropy thresholding optimized using Artificial Bee Colony(ABC) is used to threshold the surfacelet coefficients which can be used to reconstruct the video signal with improved visual quality and with a higher peak signal to noise ratio(PSNR) and structural similarity(SSIM) index.
Keywords: Surfacelet Transform, Artificial Bee Colony Algorithm, Entropy Threshold, NDFB, PSNR, SSIM.

Scope of the Article: Algorithm Engineering