Text Image Super Resolution Using Deep Attention Neural Network

Yun Liu; Remina Yano; Hiroshi Watanabe; Takuya Suzuki; Takeshi Chujoh; Tomohiro Ikai

doi:10.1109/GCCE53005.2021.9621914

Text Image Super Resolution Using Deep Attention Neural Network

Yun Liu, Remina Yano, Hiroshi Watanabe, Takuya Suzuki, Takeshi Chujoh, Tomohiro Ikai

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called 'edge loss'. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.

Original language	English
Title of host publication	2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	280-282
Number of pages	3
ISBN (Electronic)	9781665436762
DOIs	https://doi.org/10.1109/GCCE53005.2021.9621914
Publication status	Published - 2021
Event	10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan Duration: 2021 Oct 12 → 2021 Oct 15

Publication series

Name	2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

Conference

Conference	10th IEEE Global Conference on Consumer Electronics, GCCE 2021
Country/Territory	Japan
City	Kyoto
Period	21/10/12 → 21/10/15

Keywords

Optical Character Recognition (OCR)
attention
convolutional neural network
super resolution
text image

ASJC Scopus subject areas

Computer Science Applications
Signal Processing
Biomedical Engineering
Electrical and Electronic Engineering
Media Technology
Instrumentation

Access to Document

10.1109/GCCE53005.2021.9621914

Cite this

Liu, Y., Yano, R., Watanabe, H., Suzuki, T., Chujoh, T., & Ikai, T. (2021). Text Image Super Resolution Using Deep Attention Neural Network. In 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021 (pp. 280-282). (2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE53005.2021.9621914

Text Image Super Resolution Using Deep Attention Neural Network. / Liu, Yun; Yano, Remina; Watanabe, Hiroshi et al.
2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 280-282 (2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Liu, Y, Yano, R, Watanabe, H, Suzuki, T, Chujoh, T & Ikai, T 2021, Text Image Super Resolution Using Deep Attention Neural Network. in 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021. 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021, Institute of Electrical and Electronics Engineers Inc., pp. 280-282, 10th IEEE Global Conference on Consumer Electronics, GCCE 2021, Kyoto, Japan, 21/10/12. https://doi.org/10.1109/GCCE53005.2021.9621914

Liu Y, Yano R, Watanabe H, Suzuki T, Chujoh T, Ikai T. Text Image Super Resolution Using Deep Attention Neural Network. In 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 280-282. (2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021). doi: 10.1109/GCCE53005.2021.9621914

@inproceedings{74908166749e45cbbe060f3ef31a378f,

title = "Text Image Super Resolution Using Deep Attention Neural Network",

abstract = "In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called 'edge loss'. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.",

keywords = "Optical Character Recognition (OCR), attention, convolutional neural network, super resolution, text image",

author = "Yun Liu and Remina Yano and Hiroshi Watanabe and Takuya Suzuki and Takeshi Chujoh and Tomohiro Ikai",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 10th IEEE Global Conference on Consumer Electronics, GCCE 2021 ; Conference date: 12-10-2021 Through 15-10-2021",

year = "2021",

doi = "10.1109/GCCE53005.2021.9621914",

language = "English",

series = "2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "280--282",

booktitle = "2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021",

}

TY - GEN

T1 - Text Image Super Resolution Using Deep Attention Neural Network

AU - Liu, Yun

AU - Yano, Remina

AU - Watanabe, Hiroshi

AU - Suzuki, Takuya

AU - Chujoh, Takeshi

AU - Ikai, Tomohiro

PY - 2021

Y1 - 2021

N2 - In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called 'edge loss'. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.

AB - In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called 'edge loss'. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.

KW - Optical Character Recognition (OCR)

KW - attention

KW - convolutional neural network

KW - super resolution

KW - text image

UR - http://www.scopus.com/inward/record.url?scp=85123464621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85123464621&partnerID=8YFLogxK

U2 - 10.1109/GCCE53005.2021.9621914

DO - 10.1109/GCCE53005.2021.9621914

M3 - Conference contribution

AN - SCOPUS:85123464621

T3 - 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

SP - 280

EP - 282

BT - 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th IEEE Global Conference on Consumer Electronics, GCCE 2021

Y2 - 12 October 2021 through 15 October 2021

ER -

Text Image Super Resolution Using Deep Attention Neural Network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this