| Project/Area Number |
18K11373
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | Saitama Institute of Technology (2019-2020)
Kyushu University (2018) |
|---|
Principal Investigator |
Ohyama Wataru 埼玉工業大学, 工学部, 教授 (10324550)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2019: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | バイオメトリクス / 署名照合 / 機械学習 / パターン認識 |
|---|
| Outline of Final Research Achievements |
The main challenges in signature verification are (1) improving verification accuracy, (2) improving learnability, and (3) increasing language diversity. In this study, we addressed these issues by (1) improving the performance of the combinational verification method, (2) introducing a new machine learning method, and (3) introducing a signature feature extraction method based on deep learning to achieve a highly practical signature verification method. Through experiments using an international performance evaluation database, we confirmed that each of the proposed methods outperformed the conventional methods.
|
| Academic Significance and Societal Importance of the Research Achievements |
署名照合は国際的には社会的に広く受け入れられている本人確認手法である．本研究の成果は，署名照合の自動化に残されていた上述の課題を解決する糸口となることが期待される．
|
