The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Recentemente, a demanda pela digitalização de mangás aumentou. Então, no caso de um mangá antigo onde as imagens originais foram perdidas, temos que digitalizá-lo a partir dos quadrinhos. Porém, o fenômeno de transparência seria causado pela digitalização dos quadrinhos, uma vez que são representados como imagens frente e verso. Esta carta propõe o método de cancelamento transparente do mangá baseado na rede neural convolucional profunda (CNN). Os resultados numéricos mostram a eficácia do método proposto.
Taku NAKAHARA
Tokyo University of Science
Kazunori URUMA
Kogakuin University
Tomohiro TAKAHASHI
Tokai University
Toshihiro FURUKAWA
Tokyo University of Science
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Taku NAKAHARA, Kazunori URUMA, Tomohiro TAKAHASHI, Toshihiro FURUKAWA, "Deep Convolutional Neural Networks for Manga Show-Through Cancellation" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 11, pp. 2844-2848, November 2018, doi: 10.1587/transinf.2018EDL8051.
Abstract: Recently, the demand for the digitization of manga is increased. Then, in the case of an old manga where the original pictures have been lost, we have to digitize it from comics. However, the show-through phenomenon would be caused by scanning of the comics since it is represented as the double sided images. This letter proposes the manga show-through cancellation method based on the deep convolutional neural network (CNN). Numerical results show that the effectiveness of the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8051/_p
Copiar
@ARTICLE{e101-d_11_2844,
author={Taku NAKAHARA, Kazunori URUMA, Tomohiro TAKAHASHI, Toshihiro FURUKAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Deep Convolutional Neural Networks for Manga Show-Through Cancellation},
year={2018},
volume={E101-D},
number={11},
pages={2844-2848},
abstract={Recently, the demand for the digitization of manga is increased. Then, in the case of an old manga where the original pictures have been lost, we have to digitize it from comics. However, the show-through phenomenon would be caused by scanning of the comics since it is represented as the double sided images. This letter proposes the manga show-through cancellation method based on the deep convolutional neural network (CNN). Numerical results show that the effectiveness of the proposed method.},
keywords={},
doi={10.1587/transinf.2018EDL8051},
ISSN={1745-1361},
month={November},}
Copiar
TY - JOUR
TI - Deep Convolutional Neural Networks for Manga Show-Through Cancellation
T2 - IEICE TRANSACTIONS on Information
SP - 2844
EP - 2848
AU - Taku NAKAHARA
AU - Kazunori URUMA
AU - Tomohiro TAKAHASHI
AU - Toshihiro FURUKAWA
PY - 2018
DO - 10.1587/transinf.2018EDL8051
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2018
AB - Recently, the demand for the digitization of manga is increased. Then, in the case of an old manga where the original pictures have been lost, we have to digitize it from comics. However, the show-through phenomenon would be caused by scanning of the comics since it is represented as the double sided images. This letter proposes the manga show-through cancellation method based on the deep convolutional neural network (CNN). Numerical results show that the effectiveness of the proposed method.
ER -