Retracted: Complex image denoising framework with CNN‐wavelet under concurrency scenarios for informatics systems

Abstract

Image denoising based on convolutional neural networks and wavelet transform is a novel approach for the applications. In the image acquisition process, images are often contaminated by noise, which affects the image quality; therefore, it is necessary to eliminate noise before analyzing and using images. Wavelet analysis is a local analysis method with multi-resolution characteristics, which is developed on the basis of short-time Fourier transform. It can be used for the multi-scale analysis of signals by means of expansion, translation and other operations, and extracting effective information from signals, which is a powerful tool for analyzing non-stationary signals. Wavelet has good time-frequency local characteristics, low entropy, and decorrelation. In this paper, we propose MRI image denoising framework based on convolutional neural networks and wavelet transform, and the experiment results show that the proposed method can keep the edge and curvature structure better while denoising. Compared with the other novel methodologies, the proposed algorithm can provide the higher robustness. In the future research, we will try the implementations of the methodologies.