Back projection deep unrolling network for handwritten text image super resolution

Current super-resolution (SR) methods have demonstrated exceptional advancements in the domain of natural image processing. Nevertheless, these approaches do not fully address the open issues of edge blurring and distortion. In order to address the aforementioned challenges, we propose a novel deep...

Full description

Saved in:
Bibliographic Details
Published in:Computers & electrical engineering 2023-11, Vol.111, p.108965, Article 108965
Main Authors: Song, Heping, Ma, Hui, Si, Yixiong, Gong, Jingyao, Meng, Hongying, Lai, Yuping
Format: Article
Language:English
Subjects:
Back projection
Deep unrolling
Handwritten text image
Super resolution
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current super-resolution (SR) methods have demonstrated exceptional advancements in the domain of natural image processing. Nevertheless, these approaches do not fully address the open issues of edge blurring and distortion. In order to address the aforementioned challenges, we propose a novel deep unrolling model, coined back projection deep unrolling network (BPDUN), for super-resolution of handwritten text images leveraging the Algorithm Unrolling paradigm. We design the network model of BPDUN by unfolding and truncating the traditional iterative back projection algorithm (IBPA). We unroll IBPA into a cascade operation of three building blocks (deep denoising module, low-frequency reconstruction module, and residual projection module). BPDUN inherits the interpretability of the iterative optimization algorithm and is also designed to make the reconstructed text image more realistic and natural. Moreover, we propose a new benchmark dataset to address challenging SR problems of handwritten text image (HDT300). Extensive experiments show that BPDUN obtains an enhanced balance between the performance (quantified by PSNR and SSIM) and the cost (as measured by network parameters). Notably, BPDUN sets new benchmarks on the HDT300 dataset, surpassing previous state-of-the-art approaches by achieving up to 0.2 dB gains in PSNR. •BPDUN, a deep unrolling network is proposed to solve the super-resolution problems.•A benchmark dataset HDT300 is constructed for handwritten image super-resolution.•BPDUN is on par with the SOTA models and achieves new SOTA results on HDT300.
ISSN:0045-7906
1879-0755
DOI:10.1016/j.compeleceng.2023.108965