Presentation | 2019-09-19 Digital watermarking method against print-cam attack using deep learning for synchronization Hiroyuki Imagawa, Motoi Iwata, Koichi Kise, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose a novel watermarking method against print-cam attack. Digital watermarking is used to get information from a printed watermarked image by taking. In such applications, synchronization between a non-attacked watermarked image and print-cam attacked one needs high accuracy. To achieve this, we use deep learning which is used for image recognition, image detection, and semantic segmentation. We trained deep learning model whether watermarked image area or non-watermarked image area as semantic segmentation. For the detection, estimate a watermarked image area from the result predicted by the deep learning model. As a result of training, deep learning model with the data set which is consisted of warped watermarked and non-watermarked images got high accuracy of $99%$ mIoU. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Digital watermarking / Deep learning / Semantic segmentation / Print-cam |
Paper # | LOIS2019-12,IE2019-25,EMM2019-69 |
Date of Issue | 2019-09-12 (LOIS, IE, EMM) |
Conference Information | |
Committee | IE / EMM / LOIS / IEE-CMN / ITE-ME / IPSJ-AVM |
---|---|
Conference Date | 2019/9/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tokimeito, Niigata University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hideaki Kimata(NTT) / Masaki Kawamura(Yamaguchi Univ.) / Tomohiro Yamada(NEL) / Shun Morimura(CRIEPI) / 田川 憲男(首都大東京) / Sei Naito(KDDI Research, Inc.) |
Vice Chair | Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Motoi Iwata(Osaka Prefecture Univ.) / Tetsuya Kojima(NIT,Tokyo College) / Toru Kobayashi(Nagasaki Univ.) / Kouji Hirata(Kansai Univ) / 新井 啓之(日本工大) |
Secretary | Kazuya Kodama(NTT) / Keita Takahashi(NHK) / Motoi Iwata(NIT, Nagano College) / Tetsuya Kojima(Nagase) / Toru Kobayashi(Research Organization of Information and Systems) / Kouji Hirata(NTT) / 新井 啓之(Tokai Univ.) / (Doushisya Univ) |
Assistant | Kyohei Unno(KDDI Research) / Norishige Fukushima(Nagoya Inst. of Tech.) / Masaki Inamura(Tokyo Denki Univ.) / Kazuhiro Kono(Kansai Univ.) / Kenichi Arai(Nagasaki Univ.) / Yuuichi Shinohara(TEPCO Power Grid) / Akihiro Tanaka(CRIEPI) |
Paper Information | |
Registration To | Technical Committee on Image Engineering / Technical Committee on Enriched MultiMedia / Technical Committee on Life Intelligence and Office Information Systems / Technical Meeting on Communications / Technical Group on Media Engineering / Special Interest Group on Audio Visual and Multimedia Information Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Digital watermarking method against print-cam attack using deep learning for synchronization |
Sub Title (in English) | |
Keyword(1) | Digital watermarking |
Keyword(2) | Deep learning |
Keyword(3) | Semantic segmentation |
Keyword(4) | Print-cam |
1st Author's Name | Hiroyuki Imagawa |
1st Author's Affiliation | Osaka Prefecture University(Osaka Pref. Univ.) |
2nd Author's Name | Motoi Iwata |
2nd Author's Affiliation | Osaka Prefecture University(Osaka Pref. Univ.) |
3rd Author's Name | Koichi Kise |
3rd Author's Affiliation | Osaka Prefecture University(Osaka Pref. Univ.) |
Date | 2019-09-19 |
Paper # | LOIS2019-12,IE2019-25,EMM2019-69 |
Volume (vol) | vol.119 |
Number (no) | LOIS-205,IE-206,EMM-207 |
Page | pp.pp.31-36(LOIS), pp.31-36(IE), pp.31-36(EMM), |
#Pages | 6 |
Date of Issue | 2019-09-12 (LOIS, IE, EMM) |