| Presentation | 2019-12-06 Analysis of an intermediate layer for perceptual hashing using a convolutional neural network Ken Nakatani, Meng Zhaoxiong, Tetsuya Morizumi, Hirotsugu Kinoshita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This research aims to improve the digital watermark technology that embeds evidence information by using content redundancy in order to search for new copyright management methods for digital content that achieve both safety and convenience. It is.There are two major technical problems with digital watermarking in current content distribution. First, digital content is secondarily created, processed, and edited after distribution, and a digital watermark may be embedded each time. There is a risk that the watermark information is extracted and used for another content. In order to solve these problems, a multi-watermark management system using a blockchain that does not assume a reliable third party and an intermediate layer of deep learning to prevent the watermark information from being reused for other contents A watermark information generation method based on perceptual hash using state is proposed. In addition, watermarkThis paper proposes a digital watermark construction method using perceptual hashing that improves the tolerance of image quality and prevents image quality degradation. These can be said to be next-generation technologies that can be applied to objective image quality evaluation methods and image retrieval systems. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Perceptual Hash / Machine Learning / Digital Watermark / Digital rights management |
| Paper # | SITE2019-80 |
| Date of Issue | 2019-11-29 (SITE) |
| Conference Information | |
| Committee | SITE |
|---|---|
| Conference Date | 2019/12/6(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tetsuya Morizumi(Kanagawa Univ.) |
| Vice Chair | Masaru Ogawa(Kobe Gakuin Univ.) / Takushi Otani(Kibi International Univ.) |
| Secretary | Masaru Ogawa(Toyo Eiwa Univ.) / Takushi Otani(KDDI Research) |
| Assistant | Nobuyuki Yoshinaga(Yamaguchi Pref Univ.) / Daisuke Suzuki(Hokuriku Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Social Implications of Technology and Information Ethics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis of an intermediate layer for perceptual hashing using a convolutional neural network |
| Sub Title (in English) | |
| Keyword(1) | Perceptual Hash |
| Keyword(2) | Machine Learning |
| Keyword(3) | Digital Watermark |
| Keyword(4) | Digital rights management |
| 1st Author's Name | Ken Nakatani |
| 1st Author's Affiliation | Kanagawa University(Kanagawa Univ.) |
| 2nd Author's Name | Meng Zhaoxiong |
| 2nd Author's Affiliation | Kanagawa University(Kanagawa Univ.) |
| 3rd Author's Name | Tetsuya Morizumi |
| 3rd Author's Affiliation | Kanagawa University(Kanagawa Univ.) |
| 4th Author's Name | Hirotsugu Kinoshita |
| 4th Author's Affiliation | Kanagawa University(Kanagawa Univ.) |
| Date | 2019-12-06 |
| Paper # | SITE2019-80 |
| Volume (vol) | vol.119 |
| Number (no) | SITE-329 |
| Page | pp.pp.1-6(SITE), |
| #Pages | 6 |
| Date of Issue | 2019-11-29 (SITE) |