DeepAI AI Chat
Log In Sign Up

Enhancement of damaged-image prediction through Cahn-Hilliard Image Inpainting

by   José A. Carrillo, et al.
University of Oxford
Imperial College London

We assess the benefit of including an image inpainting filter before passing damaged images into a classification neural network. For this we employ a modified Cahn-Hilliard equation as an image inpainting filter, which is solved via a finite volume scheme with reduced computational cost and adequate properties for energy stability and boundedness. The benchmark dataset employed here is the MNIST dataset, which consists in binary images of digits. We train a neural network based of dense layers with the training set of MNIST, and subsequently we contaminate the test set with damage of different types and intensities. We then compare the prediction accuracy of the neural network with and without applying the Cahn-Hilliard filter to the damaged images test. Our results quantify the significant improvement of damaged-image prediction due to applying the Cahn-Hilliard filter, which for specific damages can increase up to 50


page 8

page 9

page 10


Uncertainty quantification of modified Cahn-Hilliard equation for image inpainting

In this paper, we review modified Cahn-Hilliard equation for image inpai...

Deep Stacked Networks with Residual Polishing for Image Inpainting

Deep neural networks have shown promising results in image inpainting ev...

Analysis on DeepLabV3+ Performance for Automatic Steel Defects Detection

Our works experimented DeepLabV3+ with different backbones on a large vo...

Light-weight pixel context encoders for image inpainting

In this work we propose Pixel Content Encoders (PCE), a light-weight ima...

AIM 2020 Challenge on Image Extreme Inpainting

This paper reviews the AIM 2020 challenge on extreme image inpainting. T...

Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs

Blind inpainting algorithms based on deep learning architectures have sh...

Semi-parametric Image Inpainting

This paper introduces a semi-parametric approach to image inpainting for...