Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27404
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Song, H | - |
dc.contributor.author | Ma, H | - |
dc.contributor.author | Si, Y | - |
dc.contributor.author | Gong, J | - |
dc.contributor.author | Meng, H | - |
dc.contributor.author | Lai, Y | - |
dc.date.accessioned | 2023-10-17T15:56:28Z | - |
dc.date.available | 2023-10-17T15:56:28Z | - |
dc.date.issued | 2023-10-12 | - |
dc.identifier | ORCID iD: Heping Song https://orcid.org/0000-0002-8583-2804 | - |
dc.identifier | ORCID iD: Jingyao Gong https://orcid.org/0009-0009-5907-5836 | - |
dc.identifier | ORCID iD: Hongying Meng https://orcid.org/0000-0002-8836-1382 | - |
dc.identifier | 108965 | - |
dc.identifier.citation | Song, H. et al. (2023) 'Back projection deep unrolling network for handwritten text image super resolution', Computers and Electrical Engineering, 111, 108965, pp. 1 - 12. doi: 10.1016/j.compeleceng.2023.108965. | en_US |
dc.identifier.issn | 0045-7906 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/27404 | - |
dc.description | Data availability: Data will be made available on request. | en_US |
dc.description.abstract | 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. | en_US |
dc.description.sponsorship | National Natural Science Foundation of China (Grant Nos. 62172193, 62272051); General Project of Science and Technology Plan of Beijing Municipal Commission of Education (No. KM201910009014). | en_US |
dc.format.extent | 1 - 12 | - |
dc.format.medium | Print-Electronic | - |
dc.language | en | - |
dc.language.iso | en_US | en_US |
dc.publisher | Elsevier | en_US |
dc.rights | Crown Copyright © 2023. Published by Elsevier Ltd. This manuscript version is made available under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/). The version of record is available online at: https://doi.org/10.1016/j.compeleceng.2023.108965 (see: https://www.elsevier.com/about/policies/sharing). | - |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | - |
dc.subject | super resolution | en_US |
dc.subject | handwritten text image | en_US |
dc.subject | back projection | en_US |
dc.subject | deep unrolling | en_US |
dc.title | Back projection deep unrolling network for handwritten text image super resolution | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1016/j.compeleceng.2023.108965 | - |
dc.relation.isPartOf | Computers and Electrical Engineering | - |
pubs.publication-status | Published | - |
pubs.volume | 111 | - |
dc.rights.holder | Crown | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Embargoed Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Embargoed until 12 October 2024 | 1.53 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License