| Project/Area Number |
17K00273
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Human interface and interaction
|
|---|
| Research Institution | Tottori University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 空中手書き文字 / ジェスチャインタフェース / NUI / ジェスチャ・セグメンテーション / 筆記軌跡 / 文字分割 / リザーバコンピューティング / エコーステートネットワーク / ジェスチャ入力 / ヒューマンインターフェース / 入力システム / ユーザインターフェース |
|---|
| Outline of Final Research Achievements |
We have proposed an aerial handwritten character (AHC) input system as a character input method using hand gestures. In the previous research, the trajectory of finger movement was treated as two-dimensional data on a writing plane. The purpose of this research is to improve the accuracy of AHC segmentation by using a three-dimensional writing trajectory considering the depth direction.
In the proposed method, Step1) characters are divided into strokes, and Step2) characters written continuously are divided by using the property of strokes.According to the initial plan, we were able to improve the character division accuracy in Step 2. However, the stroke division accuracy in Step 1 could not be improved.
In order to improve Step 1, we changed the research plan and proposed a new method using the technique of reservoir computing, which is a new type of neural network. By this method, we succeeded in improving the accuracy of stroke division in Step 1.
|
| Academic Significance and Societal Importance of the Research Achievements |
自然な動作で機器を操作するNatural User Interfaceが多数提案されている現在、連続して行われる人間のジェスチャを自動で分割(セグメンテーション)することは重要なキーとなる技術である。空中に指文字を描くという限られたシチュエーションとはいえ、ユーザの指動作をユーザからの明示的な操作なく自動で分割する手法を提案し、その精度を向上できたことは一つの成果といえる。
|
