Image Denoising using Auto Encoders and Decoders

This paper presents the denoising of images using the convolutional neural network (CNN) model in deep learning. It has become an important task to remove noise from the image and restore a high-quality image in order to process the image further for purposes like object segmentation, detection, tracking etc. This analysis is done by adding 1% to 10% noise to the image and then applying the CNN model to denoise it. Further, qualitative and quantitative analysis of the denoised image is performed. Here the CNN model mainly consists of the encoder and decoder layers that will help in making the image to be denoised. The results from the analysis and experiment show that the CNN model can efficiently remove noise and restore the image details and data than any other traditional/standard image filtering technique.

Keywords: Image denoising, noise, convolutional neural network, Auto encoders and decoders, Deep Learning