| Presentation | 2019-03-13 [Poster Presentation] Relationship between error correcting capability for error correction codes and basin of attraction in associative memory models Akinobu Oshikawa, Masaki Kawamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We proposed a digital watermarking method using an auto-associative memory model (AMM), which can correct errors of watermarks inside a basin of attraction of the model. ?In the conventional watermarking methods, messages are encoded to watermarks by using error-correcting codes in preparation for attacks. ?In order to decode the messages correctly, the methods with high error correction capability are required. ?We focused on the auto-associative memory model, since it has large basin of attraction. ?That is, it has high ability for error correction. ?The proposed method consists of an encoder network and a decoder network with an auto-associative memory model. ?The encoder is a randomly connected network.?The messages are converted to the codewords. ?The generated codewords are stored in synaptic connections of the AMM.?Therefore, the AMM can retrieve the stored codeword correctly from a damaged codeword. ?The retrieved codeword is inversely converted to the message in the decoder. ?In order to evaluate the error correction capability of the proposed method, the basins of attraction are calculated by computer simulations. As a result, we found that the proposed method could decode messages correctly even from small initial overlap $m^0=0.02$ when the loading rate is small enough. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | watermarking / associative memory model / error correction code / neural network |
| Paper # | EMM2018-101 |
| 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] Relationship between error correcting capability for error correction codes and basin of attraction in associative memory models |
| Sub Title (in English) | |
| Keyword(1) | watermarking |
| Keyword(2) | associative memory model |
| Keyword(3) | error correction code |
| Keyword(4) | neural network |
| 1st Author's Name | Akinobu Oshikawa |
| 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 # | EMM2018-101 |
| Volume (vol) | vol.118 |
| Number (no) | EMM-494 |
| Page | pp.pp.51-56(EMM), |
| #Pages | 6 |
| Date of Issue | 2019-03-06 (EMM) |