Presentation | 2019-03-13 [Poster Presentation] Digital watermarking method using CNN including a robust extractor neural network against rotation? Ippei Hamamoto, Masaki Kawamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a digital watermarking method using neural networks, which can learn robust embedding and extraction processes against rotation and JPEG compression. ?The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, a rotation propagation layer, and an additive noise layer.?The rotation propagation layer and the additive noise layer simulate the rotation attack and the JPEG compression attack in the layers, respectively. Therefore, the stego-image generator can learn the robust embedding against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of stego-images can be improved by using the stego-image discriminator, which is one of adversarial networks. ?We evaluated the robustness of watermarks and image quality. As a result, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained so as to embed watermarks robustly and extract them correctly against rotation and JPEG compression attacks.?We also showed that the robustness and image quality can be adjusted by strength of simulated noise in the noise layer. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | digital watermark / neural network / CNN / rotation / JPEG compression |
Paper # | EMM2018-92 |
Date of Issue | 2019-03-06 (EMM) |
Conference Information | |
Committee | EMM |
---|---|
Conference Date | 2019/3/13(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | TBD |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image and Sound Quality, Metrics for Perception and Recognition, Human Auditory and Visual System, etc. |
Chair | Keiichi Iwamura(TUC) |
Vice Chair | Minoru Kuribayashi(Okayama Univ.) / Tetsuya Kojima(NIT,Tokyo College) |
Secretary | Minoru Kuribayashi(NIT, Tokyo) / Tetsuya Kojima(Tyukyo Univ.) |
Assistant | Hiroko Akiyama(NIT, Nagano College) / キタヒロ カネダ(CANON) |
Paper Information | |
Registration To | Technical Committee on Enriched MultiMedia |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Digital watermarking method using CNN including a robust extractor neural network against rotation? |
Sub Title (in English) | |
Keyword(1) | digital watermark |
Keyword(2) | neural network |
Keyword(3) | CNN |
Keyword(4) | rotation |
Keyword(5) | JPEG compression |
1st Author's Name | Ippei Hamamoto |
1st Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
2nd Author's Name | Masaki Kawamura |
2nd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
Date | 2019-03-13 |
Paper # | EMM2018-92 |
Volume (vol) | vol.118 |
Number (no) | EMM-494 |
Page | pp.pp.7-12(EMM), |
#Pages | 6 |
Date of Issue | 2019-03-06 (EMM) |