Optimised surfacelet transform based approach for video denoising

Video denoising systems aims at the removal of noise within each frames. Most of the video denoising systems employ spatial filtering, wavelet decomposition or by utilizing the temporal coherence by motion estimation. Unfortunately, these denoising systems distorts edges, lines and curves. The drawbacks of temporal correlation based schemes are that they suffer due to aperture problems in optical flow and lighting variations. Surfacelet transform is a potent tool for the processing of multidimensional data. Video signals can be treated as a type of 3D signal and therefore can be represented using surfacelet transform which preserves the edge information and visual quality. In the proposed system, the advantages of surfacelet transform were consolidated with Artificial Bee Colony optimization technique for threshold optimization. The denoised video sequences delivered extraordinary results in terms of peak signal to noise ratio(PSNR) and structural similarity(SSIM) index.