| Presentation | 2022-03-08 Improve Method of Signature Classification with Machine Learning on Poor Written Environment Daiki Goto, Ryuya Uda, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In the real world, it is difficult to obtain characteristics such as the angle or the pressure of the pen. And there is the difference between the position where the pen is placed and where the line is drawn. In addition, it is necessary to extract elements that show more characteristics, because it is possible that a person with the same name and writing style exists by chance. In this paper, a single signature is classified into three types of lines. The LSTM was trained using the sign data obtained in a normal environment, and the identification of 100 signs in the aforementioned environment was identified, and the accuracy of individual identification was improved by about 10%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Writer identification / Machine Learning / Special Environments |
| Paper # | EMM2021-113 |
| Date of Issue | 2022-02-28 (EMM) |
| Conference Information | |
| Committee | EMM |
|---|---|
| Conference Date | 2022/3/7(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | (Primary: Online, Secondary: On-site) |
| 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 | Ryoichi Nishimura(NICT) |
| Vice Chair | Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) |
| Secretary | Masaaki Fujiyoshi(Utsunomiya Univ.) / Masatsugu Ichino(NICT) |
| Assistant | Shoko Imaizumi(Chiba Univ.) / Youichi Takashima(Kaishi Professional Univ.) |
| 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) | Improve Method of Signature Classification with Machine Learning on Poor Written Environment |
| Sub Title (in English) | |
| Keyword(1) | Writer identification |
| Keyword(2) | Machine Learning |
| Keyword(3) | Special Environments |
| 1st Author's Name | Daiki Goto |
| 1st Author's Affiliation | Tokyo University of Technology Graduate School(Tokyo Univ. of Tech. Graduate School) |
| 2nd Author's Name | Ryuya Uda |
| 2nd Author's Affiliation | Tokyo University of Technology Graduate School(Tokyo Univ. of Tech. Graduate School) |
| Date | 2022-03-08 |
| Paper # | EMM2021-113 |
| Volume (vol) | vol.121 |
| Number (no) | EMM-417 |
| Page | pp.pp.112-117(EMM), |
| #Pages | 6 |
| Date of Issue | 2022-02-28 (EMM) |