Image Denoising with Color Scheme by Using Autoencoders

摘要

Image denoising autoencoder is classical issue in the field of digital image processing where compression and decompression function are lossy and data specific. In this paper, we use autoencoder technique on RGB (Red, Green and Blue) color scheme dataset, we added Gaussian noise on CIFER-10 dataset then encode by using 2D convolutional neutral network. Similarly, we decode noisy dataset to train our model. After training, the proposed method can learn denoising data and returns effective results.