TechRxiv
Image-deblurring-super-resolution.pdf (1.77 MB)

Deep CNN with Skip Connection and Network in Network for Super-Resolving Blurry Text Images

Download (1.77 MB)
preprint
posted on 2022-05-25, 15:36 authored by Hala NejiHala Neji

Deep convolutional neural networks (Deep CNN) have achieved hopeful performancefor single image super-resolution. In particular, the Deep CNN skip Connection andNetwork in Network (DCSCN) architecture has been successfully applied to naturalimages super-resolution. In this work we propose an approach called SDT-DCSCN thatjointly performs super-resolution and deblurring of low-resolution blurry text imagesbased on DCSCN. Our approach uses subsampled blurry images in the input and origi-nal sharp images as ground truth. The used architecture is consists of a higher numberof filters in the input CNN layer to a better analysis of the text details. The quantitativeand qualitative evaluation on different datasets prove the high performance of our modelto reconstruct high-resolution and sharp text images. In addition, in terms of computa-tional time, our proposed method gives competitive performance compared to state ofthe art methods.

History

Email Address of Submitting Author

hala.neji@ieee.org

ORCID of Submitting Author

0000-0003-3595-005X

Submitting Author's Institution

REGIM-Lab, University of Sfax, Tunisia

Submitting Author's Country

  • Tunisia

Usage metrics

    Licence

    Exports