English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

We assess the benefit of including an image inpainting filter before passingdamaged images into a classification neural network. For this we employ amodified Cahn-Hilliard equation as an image inpainting filter, which is solvedvia a finite volume scheme with reduced computational cost and adequateproperties for energy stability and boundedness. The benchmark dataset employedhere is MNIST, which consists of binary images of handwritten digits and is astandard dataset to validate image-processing methodologies. We train a neuralnetwork based of dense layers with the training set of MNIST, and subsequentlywe contaminate the test set with damage of different types and intensities. Wethen compare the prediction accuracy of the neural network with and withoutapplying the Cahn-Hilliard filter to the damaged images test. Our resultsquantify the significant improvement of damaged-image prediction due toapplying the Cahn-Hilliard filter, which for specific damages can increase upto 50% and is in general advantageous for low to moderate damage.

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