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

TL;DR

This paper demonstrates that applying a Cahn-Hilliard based inpainting filter to damaged images significantly improves neural network classification accuracy, especially for low to moderate damage levels, using MNIST as a benchmark.

Contribution

The study introduces a modified Cahn-Hilliard inpainting method with a finite volume scheme for damaged image restoration before classification.

Findings

Increased prediction accuracy up to 50% with the filter

Significant improvement for low to moderate damage levels

Validated on MNIST dataset

Abstract

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 MNIST, which consists of binary images of handwritten digits and is a standard dataset to validate image-processing methodologies. 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% and is in general advantageous for low to moderate damage.