Textual Deblurring using Convolutional Neural Network
preprintposted on 2021-10-16, 00:43 authored by Muhammad Shahroz NadeemMuhammad Shahroz Nadeem, Sibt Hussain, Fatih Kurugollu
This paper solves the textual deblurring problem, In this paper we propose a new loss function, we provide empirical evaluation of the design choices based on which a memory friendly CNN model is proposed, that performs better then the state of the art CNN method.
Email Address of Submitting AuthorM.Nadeem@derby.ac.uk
ORCID of Submitting Author0000-0001-5835-1602
Submitting Author's InstitutionUniversity of Derby
Submitting Author's Country
- United Kingdom