Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies

Li Jyun Chen; Chih Ying Chen; Hung Yu Chen; Guan Yu Chen; Yen Wen Chen

doi:10.1109/iCMLDE49015.2019.00013

Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies

Li Jyun Chen, Chih Ying Chen, Hung Yu Chen, Guan Yu Chen, Yen Wen Chen

Department of Communication Engineering

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

Abstract

This paper proposes the intelligent system to assist the visually-impaired people in reading printed Chinese document. As the document may consist of the combination of text and photos, the proposed system first applies the text frame detection scheme to identify the text parts of the document, and utilizes the Optical Character Recognition (OCR) to convert the text image into pure text file. The aim of this paper is to implement the automatic text summarization algorithm to get the brief meaning of the whole text. And the visually-impaired people can listen to the summary of the document through the existing text to voice tool. In the system, the neural network model is adopted to find out text blocks before recognizing text, and to optimize the Chinese automatic text summarization system. The performance of the proposed scheme is also evaluated by the TextRank with Word2Vec. The proposed system can assist the visually-impaired people especially in daily life when it is applied in the wearable devices.

Original language	English
Title of host publication	Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019
Editors	Phill Kyu Rhee, Kuo-Yuan Hwa, Tun-Wen Pai, Daniel Howard, Rezaul Bashar
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7-12
Number of pages	6
ISBN (Electronic)	9781728104041
DOIs	https://doi.org/10.1109/iCMLDE49015.2019.00013
State	Published - Dec 2019
Event	2019 International Conference on Machine Learning and Data Engineering, iCMLDE 2019 - Taipei, Taiwan Duration: 2 Dec 2019 → 4 Dec 2019

Publication series

Name	Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019

Conference

Conference	2019 International Conference on Machine Learning and Data Engineering, iCMLDE 2019
Country/Territory	Taiwan
City	Taipei
Period	2/12/19 → 4/12/19

Keywords

Automatic text summarization
Neural network
Object detection

Access to Document

10.1109/iCMLDE49015.2019.00013

Cite this

Chen, L. J., Chen, C. Y., Chen, H. Y., Chen, G. Y., & Chen, Y. W. (2019). Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies. In P. K. Rhee, K.-Y. Hwa, T.-W. Pai, D. Howard, & R. Bashar (Eds.), Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019 (pp. 7-12). Article 8995759 (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/iCMLDE49015.2019.00013

Chen, Li Jyun ; Chen, Chih Ying ; Chen, Hung Yu et al. / Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies. Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019. editor / Phill Kyu Rhee ; Kuo-Yuan Hwa ; Tun-Wen Pai ; Daniel Howard ; Rezaul Bashar. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 7-12 (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019).

@inproceedings{a2be0399291748fab32bd2af715b53aa,

title = "Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies",

abstract = "This paper proposes the intelligent system to assist the visually-impaired people in reading printed Chinese document. As the document may consist of the combination of text and photos, the proposed system first applies the text frame detection scheme to identify the text parts of the document, and utilizes the Optical Character Recognition (OCR) to convert the text image into pure text file. The aim of this paper is to implement the automatic text summarization algorithm to get the brief meaning of the whole text. And the visually-impaired people can listen to the summary of the document through the existing text to voice tool. In the system, the neural network model is adopted to find out text blocks before recognizing text, and to optimize the Chinese automatic text summarization system. The performance of the proposed scheme is also evaluated by the TextRank with Word2Vec. The proposed system can assist the visually-impaired people especially in daily life when it is applied in the wearable devices.",

keywords = "Automatic text summarization, Neural network, Object detection",

author = "Chen, {Li Jyun} and Chen, {Chih Ying} and Chen, {Hung Yu} and Chen, {Guan Yu} and Chen, {Yen Wen}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Conference on Machine Learning and Data Engineering, iCMLDE 2019 ; Conference date: 02-12-2019 Through 04-12-2019",

year = "2019",

month = dec,

doi = "10.1109/iCMLDE49015.2019.00013",

language = "???core.languages.en_GB???",

series = "Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019",

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

pages = "7--12",

editor = "Rhee, {Phill Kyu} and Kuo-Yuan Hwa and Tun-Wen Pai and Daniel Howard and Rezaul Bashar",

booktitle = "Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019",

}

Chen, LJ, Chen, CY, Chen, HY, Chen, GY & Chen, YW 2019, Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies. in PK Rhee, K-Y Hwa, T-W Pai, D Howard & R Bashar (eds), Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019., 8995759, Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019, Institute of Electrical and Electronics Engineers Inc., pp. 7-12, 2019 International Conference on Machine Learning and Data Engineering, iCMLDE 2019, Taipei, Taiwan, 2/12/19. https://doi.org/10.1109/iCMLDE49015.2019.00013

Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies. / Chen, Li Jyun; Chen, Chih Ying; Chen, Hung Yu et al.
Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019. ed. / Phill Kyu Rhee; Kuo-Yuan Hwa; Tun-Wen Pai; Daniel Howard; Rezaul Bashar. Institute of Electrical and Electronics Engineers Inc., 2019. p. 7-12 8995759 (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019).

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

TY - GEN

T1 - Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies

AU - Chen, Li Jyun

AU - Chen, Chih Ying

AU - Chen, Hung Yu

AU - Chen, Guan Yu

AU - Chen, Yen Wen

PY - 2019/12

Y1 - 2019/12

N2 - This paper proposes the intelligent system to assist the visually-impaired people in reading printed Chinese document. As the document may consist of the combination of text and photos, the proposed system first applies the text frame detection scheme to identify the text parts of the document, and utilizes the Optical Character Recognition (OCR) to convert the text image into pure text file. The aim of this paper is to implement the automatic text summarization algorithm to get the brief meaning of the whole text. And the visually-impaired people can listen to the summary of the document through the existing text to voice tool. In the system, the neural network model is adopted to find out text blocks before recognizing text, and to optimize the Chinese automatic text summarization system. The performance of the proposed scheme is also evaluated by the TextRank with Word2Vec. The proposed system can assist the visually-impaired people especially in daily life when it is applied in the wearable devices.

AB - This paper proposes the intelligent system to assist the visually-impaired people in reading printed Chinese document. As the document may consist of the combination of text and photos, the proposed system first applies the text frame detection scheme to identify the text parts of the document, and utilizes the Optical Character Recognition (OCR) to convert the text image into pure text file. The aim of this paper is to implement the automatic text summarization algorithm to get the brief meaning of the whole text. And the visually-impaired people can listen to the summary of the document through the existing text to voice tool. In the system, the neural network model is adopted to find out text blocks before recognizing text, and to optimize the Chinese automatic text summarization system. The performance of the proposed scheme is also evaluated by the TextRank with Word2Vec. The proposed system can assist the visually-impaired people especially in daily life when it is applied in the wearable devices.

KW - Automatic text summarization

KW - Neural network

KW - Object detection

UR - http://www.scopus.com/inward/record.url?scp=85080904806&partnerID=8YFLogxK

U2 - 10.1109/iCMLDE49015.2019.00013

DO - 10.1109/iCMLDE49015.2019.00013

M3 - 會議論文篇章

AN - SCOPUS:85080904806

T3 - Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019

SP - 7

EP - 12

BT - Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019

A2 - Rhee, Phill Kyu

A2 - Hwa, Kuo-Yuan

A2 - Pai, Tun-Wen

A2 - Howard, Daniel

A2 - Bashar, Rezaul

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Conference on Machine Learning and Data Engineering, iCMLDE 2019

Y2 - 2 December 2019 through 4 December 2019

ER -

Chen LJ, Chen CY, Chen HY, Chen GY, Chen YW. Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies. In Rhee PK, Hwa KY, Pai TW, Howard D, Bashar R, editors, Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 7-12. 8995759. (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2019). doi: 10.1109/iCMLDE49015.2019.00013

Implementation of chinese reader aid for visually-impaired by using neural network and text summarization technologies

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this