A Novel Image Denoising Algorithm Based on Wavelet and Akamatsu Transforms Using Particle Swarm Optimization

Nowadays, advanced devices such as mobile phones, allow us to easily take digital photos. But sometimes, the result doesn't come out as expected due to corruption by various noises. Here is where the image denoising methods can play an important role. In this paper, we present a novel image denoising algorithm based on Wiener filter, discrete wavelet transforms (DWT) and Akamatsu transform. The Wiener filtering is used as a pre filter block and the combination of DWT and Akamatsu transform along with usage of crucial factors optimum values obtained using particle swarm optimization (PSO) helps this method to have high performance in image restoration. The proposed method was applied to four gray scale 512 x 512 size standard images corrupted by Gaussian and Salt & Pepper noises and the algorithm outcomes were within acceptable range. Peak signal to noise ratio (PSNR) is used to compare the performance of our new algorithm with some of the other existing schemes. Simulation results proved that the proposed algorithm works well and has better performance in image denoising than some of its counterparts presented in the literature in the case of PSNR improvement.