| Presentation | 2020-01-10 Hybrid authentication model using handwritten images by Siamese Network and dynamic information Daisuke Hayashi, Taisuke Kawamata, Toru Kano, Takako Akakura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Since the common examinee authentication method in Web-testing is based only on the ID and password at the beginning of the test, it is easy to spoof during the test. To solve this problem, we proposed an examinee authentication method based on dynamic information such as pen pressure and pen tilt when the examinee wrote the answer characters on a tablet PC. However, the accuracy of our previous research was insufficient. Hence, it waspractically difficult to apply the examinee authentication method of previous research to Web-testing. One reason for this is because authentication was performed using only dynamic information. In this research, we proposed a hybrid authentication model using handwritten images model by siamese network and dynamic information model by MLP. Therefore, our hybrid authentication model obtained better accuracy than using handwritten images modeland dynamic information model alone. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Siamese Network / MLP / Writing authentication / Image processing / DTW |
| Paper # | IBISML2019-28 |
| Date of Issue | 2020-01-02 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2020/1/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | ISM |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Machine learning, etc. |
| Chair | Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Hybrid authentication model using handwritten images by Siamese Network and dynamic information |
| Sub Title (in English) | |
| Keyword(1) | Siamese Network |
| Keyword(2) | MLP |
| Keyword(3) | Writing authentication |
| Keyword(4) | Image processing |
| Keyword(5) | DTW |
| 1st Author's Name | Daisuke Hayashi |
| 1st Author's Affiliation | Tokyo University of Science(TUS) |
| 2nd Author's Name | Taisuke Kawamata |
| 2nd Author's Affiliation | Tokyo University of Science(TUS) |
| 3rd Author's Name | Toru Kano |
| 3rd Author's Affiliation | Tokyo University of Science(TUS) |
| 4th Author's Name | Takako Akakura |
| 4th Author's Affiliation | Tokyo University of Science(TUS) |
| Date | 2020-01-10 |
| Paper # | IBISML2019-28 |
| Volume (vol) | vol.119 |
| Number (no) | IBISML-360 |
| Page | pp.pp.67-74(IBISML), |
| #Pages | 8 |
| Date of Issue | 2020-01-02 (IBISML) |