Image Denoising Based on Dual-tree Complex Wavelet Transform and Convolutional Neural Network

Abstract In view of the problem that noise in image will have a negative impact on subsequent processing, this paper proposes reduction algorithm based dual-tree complex wavelet transform and convolutional neural network by using characteristics DTCWT CNN. Firstly, two-dimensional is decomposed into two parallel trees double tree transform, which forms six high-frequency detail parts same low-frequency different directions. Then, it put designed deep convolution for training, Finally, components one are recombined after inverse wavelet. The simulation results show PSNR MS-SSIM better than other algorithms, details original can be restored well while reduction. It has practical application value case collected large due to various reasons.