DeepDeblur : text image recovery from blur to sharp

Digital images could be degraded by a variety of blur during the image acquisition (i.e. relative motion of cameras, electronic noise, capturing defocus, and so on). Blurring images can be computationally modeled as the result of a convolution process with the corresponding blur kernel and thus, ima...

Full description

Saved in:
Bibliographic Details
Main Authors: Mei, Jianhan, Wu, Ziming, Chen, Xiang, Qiao, Yu, Ding, Henghui, Jiang, Xudong
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/151740
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-151740
record_format dspace
spelling sg-ntu-dr.10356-1517402021-07-21T09:09:50Z DeepDeblur : text image recovery from blur to sharp Mei, Jianhan Wu, Ziming Chen, Xiang Qiao, Yu Ding, Henghui Jiang, Xudong School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Text Deblurring Convolutional Neural Network Digital images could be degraded by a variety of blur during the image acquisition (i.e. relative motion of cameras, electronic noise, capturing defocus, and so on). Blurring images can be computationally modeled as the result of a convolution process with the corresponding blur kernel and thus, image deblurring can be regarded as a deconvolution operation. In this paper, we explore to deblur images by approximating blind deconvolutions using a deep neural network. Different deep neural network structures are investigated to evaluate their deblurring capabilities, which contributes to the optimal design of a network architecture. It is found that shallow and narrow networks are not capable of handling complex motion blur. We thus, present a deep network with 20 layers to cope with text image blur. In addition, a novel network structure with Sequential Highway Connections (SHC) is leveraged to gain superior convergence. The experiment results demonstrate the state-of-the-art performance of the proposed framework with the higher visual quality of the delurred images. 2021-07-21T09:09:50Z 2021-07-21T09:09:50Z 2019 Journal Article Mei, J., Wu, Z., Chen, X., Qiao, Y., Ding, H. & Jiang, X. (2019). DeepDeblur : text image recovery from blur to sharp. Multimedia Tools and Applications, 78(13), 18869-18885. https://dx.doi.org/10.1007/s11042-019-7251-y 1380-7501 0000-0002-3510-2897 https://hdl.handle.net/10356/151740 10.1007/s11042-019-7251-y 2-s2.0-85061178285 13 78 18869 18885 en Multimedia Tools and Applications © 2019 Springer Science+Business Media, LLC, part of Springer Nature. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Text Deblurring
Convolutional Neural Network
spellingShingle Engineering::Electrical and electronic engineering
Text Deblurring
Convolutional Neural Network
Mei, Jianhan
Wu, Ziming
Chen, Xiang
Qiao, Yu
Ding, Henghui
Jiang, Xudong
DeepDeblur : text image recovery from blur to sharp
description Digital images could be degraded by a variety of blur during the image acquisition (i.e. relative motion of cameras, electronic noise, capturing defocus, and so on). Blurring images can be computationally modeled as the result of a convolution process with the corresponding blur kernel and thus, image deblurring can be regarded as a deconvolution operation. In this paper, we explore to deblur images by approximating blind deconvolutions using a deep neural network. Different deep neural network structures are investigated to evaluate their deblurring capabilities, which contributes to the optimal design of a network architecture. It is found that shallow and narrow networks are not capable of handling complex motion blur. We thus, present a deep network with 20 layers to cope with text image blur. In addition, a novel network structure with Sequential Highway Connections (SHC) is leveraged to gain superior convergence. The experiment results demonstrate the state-of-the-art performance of the proposed framework with the higher visual quality of the delurred images.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Mei, Jianhan
Wu, Ziming
Chen, Xiang
Qiao, Yu
Ding, Henghui
Jiang, Xudong
format Article
author Mei, Jianhan
Wu, Ziming
Chen, Xiang
Qiao, Yu
Ding, Henghui
Jiang, Xudong
author_sort Mei, Jianhan
title DeepDeblur : text image recovery from blur to sharp
title_short DeepDeblur : text image recovery from blur to sharp
title_full DeepDeblur : text image recovery from blur to sharp
title_fullStr DeepDeblur : text image recovery from blur to sharp
title_full_unstemmed DeepDeblur : text image recovery from blur to sharp
title_sort deepdeblur : text image recovery from blur to sharp
publishDate 2021
url https://hdl.handle.net/10356/151740
_version_ 1707050429786882048