2022 Fiscal Year Final Research Report
Detection of unnatural writing behavior by analyzing the appearance of handwritten strokes
| Project/Area Number |
18K11516
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61060:Kansei informatics-related
|
|---|
| Research Institution | National Research Institute of Police Science |
|---|
Principal Investigator |
Akao Yoshinori 科学警察研究所, 法科学第四部, 室長 (30356159)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Keywords | 筆跡 / 質感 / ソフトバイオメトリクス / 偏角反射特性 / 熟練者 |
|---|
| Outline of Final Research Achievements |
A method for detecting unnatural handwriting by observing the handwriting was studied. As a representative example of unnatural handwriting, we focused on traced handwriting. Firstly, we investigated the kind of texture of the strokes an expert would pay attention to when examining handwriting. Secondly, the relationship with writing dynamics such as speed and pressure at the pen tip was studied. Lastly, we introduced a polarized compound-eye camera to capture physical characteristics such as color and gloss by imaging handwriting strokes. As a result, the pixel value of the polarization ratio image was effective to detect the stagnation of strokes at the beginning and end of the stroke line. Combined with the uniformity of pixel value within the stroke line, detecting the traced handwriting would be achieved.
|
| Free Research Field |
情報科学
|
| Academic Significance and Societal Importance of the Research Achievements |
人間が見て感じる質感について，測定に基づいた客観化を試みた研究である．質感は，見る人によって感じ方が異なるため，説明指標としての利用が困難であった．筆跡を題材とし，専門家の知見を積極的に活用することにより，画線の物理的特性との関連を明らかにし，測定による評価を可能とした．研究成果は，犯罪鑑識における筆跡鑑定の客観性向上に直接的に役立つ．さらに，行動的特徴に基づくバイオメトリック個人認証の研究とも位置付けられ，情報システムのユーザー個人を適切に認証し，セキュリティを維持する技術への波及も期待できる．
|
