Noorbakhsh Amiri Golilarz - Department of Electrical and Electronic Engineering, Eastern Mediterranean University, Cyprus
Niyifasha Robert - Center for Cyber Security, School of Computer Science and Engineering, University of Electronic Science and Technology of China, China
Jalil Addeh - Department of Electrical Engineering, Babol Noshirvani University of Technology, Iran
Amin Salehpour - Department of Electrical and Electronic Engineering, Eastern Mediterranean University, Cyprus

In this paper, a new type of thresholding function is introduced for wavelet based image de-noising. Here we combined the new smooth nonlinear improved thresholding function with translation invariant wavelet transform (TIWT). Unlike the common thresholding functions (hard and soft thresholding), the new proposed function is smooth and nonlinear. Applying this thresholding function on wavelet transform provides us with better resolution and higher peak signal to noise ratio (PSNR) in comparison with some other available techniques in image de-noising. The proposed method achieves up to 2.45 dB improvement over the state-of-the-art for de-noising ‘Boat’ image.

Image de-noising, Improved thresholding function, Translation invariant wavelet transform, Noise reduction