Search results for " Inpainting"
showing 4 items of 4 documents
On the use of Denoising Autoencoders and Deep Convolutional Adversarial Networks for Automated Removal of Date Stamps
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 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 d…
Face Inpainting via Nested Generative Adversarial Networks
2019
Face inpainting aims to repaired damaged images caused by occlusion or cover. In recent years, deep learning based approaches have shown promising results for the challenging task of image inpainting. However, there are still limitation in reconstructing reasonable structures because of over-smoothed and/or blurred results. The distorted structures or blurred textures are inconsistent with surrounding areas and require further post-processing to blend the results. In this paper, we present a novel generative model-based approach, which consisted by nested two Generative Adversarial Networks (GAN), the sub-confrontation GAN in generator and parent-confrontation GAN. The sub-confrontation GAN…
Filling-in Gaps in Textured Images Using Bit-Plane Statistics
2008
In this paper we propose a novel approach for the texture analysis-synthesis problem, with the purpose to restore missing zones in greyscale images. Bit-plane decomposition is used, and a dictionary is build with bit-blocks statistics for each plane. Gaps are reconstructed with a conditional stochastic process, to propagate texture global features into the damaged area, using information stored in the dictionary. Our restoration method is simple, easy and fast, with very good results for a large set of textured images. Results are compared with a state-of-the-art restoration algorithm.
Restoration of Digitized Damaged Photos using Bit-Plane Slicing
2007
Digital image restoration aims to recover damaged zones of a digital image, using surrounding information. In this paper we propose a novel approach, based on bit-plane slicing decomposition, with the purpose to make information analysis and reconstruction process easy, fast and effective. Tests have been made on digitized damaged old photos to restore several classes of typical defects in old photographic prints.