Scene Text Eraser

Toshiki Nakamura, Anna Zhu, Keiji Yanai, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished byaCNNmodelthroughconvolutiontodeconvolutionwithinterconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images.

Original languageEnglish
Title of host publicationProceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
PublisherIEEE Computer Society
Pages832-837
Number of pages6
ISBN (Electronic)9781538635865
DOIs
Publication statusPublished - Jan 25 2018
Event14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 - Kyoto, Japan
Duration: Nov 9 2017Nov 15 2017

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume1
ISSN (Print)1520-5363

Other

Other14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
CountryJapan
CityKyoto
Period11/9/1711/15/17

Fingerprint

Telephone
Teaching
Pixels
Color
Neural networks
Testing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Nakamura, T., Zhu, A., Yanai, K., & Uchida, S. (2018). Scene Text Eraser. In Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 (pp. 832-837). (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 1). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2017.141

Scene Text Eraser. / Nakamura, Toshiki; Zhu, Anna; Yanai, Keiji; Uchida, Seiichi.

Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017. IEEE Computer Society, 2018. p. 832-837 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakamura, T, Zhu, A, Yanai, K & Uchida, S 2018, Scene Text Eraser. in Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 1, IEEE Computer Society, pp. 832-837, 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, Kyoto, Japan, 11/9/17. https://doi.org/10.1109/ICDAR.2017.141
Nakamura T, Zhu A, Yanai K, Uchida S. Scene Text Eraser. In Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017. IEEE Computer Society. 2018. p. 832-837. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). https://doi.org/10.1109/ICDAR.2017.141
Nakamura, Toshiki ; Zhu, Anna ; Yanai, Keiji ; Uchida, Seiichi. / Scene Text Eraser. Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017. IEEE Computer Society, 2018. pp. 832-837 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).
@inproceedings{fae316f67aa74cc0851032624b1b246d,
title = "Scene Text Eraser",
abstract = "The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished byaCNNmodelthroughconvolutiontodeconvolutionwithinterconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images.",
author = "Toshiki Nakamura and Anna Zhu and Keiji Yanai and Seiichi Uchida",
year = "2018",
month = "1",
day = "25",
doi = "10.1109/ICDAR.2017.141",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",
pages = "832--837",
booktitle = "Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017",
address = "United States",

}

TY - GEN

T1 - Scene Text Eraser

AU - Nakamura, Toshiki

AU - Zhu, Anna

AU - Yanai, Keiji

AU - Uchida, Seiichi

PY - 2018/1/25

Y1 - 2018/1/25

N2 - The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished byaCNNmodelthroughconvolutiontodeconvolutionwithinterconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images.

AB - The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished byaCNNmodelthroughconvolutiontodeconvolutionwithinterconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images.

UR - http://www.scopus.com/inward/record.url?scp=85045197884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045197884&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2017.141

DO - 10.1109/ICDAR.2017.141

M3 - Conference contribution

AN - SCOPUS:85045197884

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 832

EP - 837

BT - Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017

PB - IEEE Computer Society

ER -