On the use of Denoising Autoencoders and Deep Convolutional Adversarial Networks for Automated Removal of Date Stamps

Abstract

This thesis investigates to what extent the deep learning models such as DenoisingAutoencoder (DAE) and Deep Convolution General Adversarial Net (DCGAN)automate the removal of the date stamps from images with high resolution whilepreserving the rest of the images. Both DAE and DCGAN algorithms are im-plemented with Convolutional Neural Networks (CNN). The DAE algorithm canperform this task with entirely satisfactory results. The DAE can reconstruct theoriginal images from corrupted inputs with date stamps. While DCGAN deliverspoor yet interesting results. The images generated by the DCGAN are quite dif-ferent from the reference images. All performed experiments in this thesis thatthe quality of output images produced by DAE is far superior to that of the resultsgenerated by DCGAN.Keywords: Blind Image Inpainting, DAE, DCGAN, automated date stamp re-moval