We assess the benefit of including an image inpainting filter before passing damaged images into a classification neural network. We employ an appropriately modified Cahn-Hilliard equation as an image inpainting filter which is solved numerically with a finite-volume scheme exhibiting reduced computational cost and the properties of energy stability and boundedness. The benchmark dataset employed is Modified National Institute of Standards and Technology (MNIST) dataset, which consists of binary images of handwritten digits and is a standard dataset to validate image-processing methodologies. We train a neural network based on dense layers with MNIST, and subsequently we contaminate the test set with damages 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 by applying the Cahn-Hilliard filter, which for specific damages can increase up to 50% and is advantageous for low to moderate damage.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8131946PMC
http://dx.doi.org/10.1098/rsos.201294DOI Listing

Publication Analysis

Top Keywords

image inpainting
12
neural network
12
damaged-image prediction
8
inpainting filter
8
damaged images
8
applying cahn-hilliard
8
cahn-hilliard filter
8
enhancement damaged-image
4
cahn-hilliard
4
prediction cahn-hilliard
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!