2001 Fiscal Year Final Research Report Summary
Human Interface that detects user's intentions and emotions from their gestures and facial expressions
| Project/Area Number |
11832012
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Institution | Shizuoka University |
|---|
Principal Investigator |
NAKATANI Hiromasa Shizuoka University, Department of Computer Science ; Professor, 情報学部, 教授 (80109131)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
ITOH Toshihiko Shizuoka University, Department of Computer Science ; Assistant, 情報学部, 助手 (20313926)
SAJI Hitoshi Shizuoka University, Department of Computer Science ; Associate Professor, 情報学部, 助教授 (10283334)
|
|---|
| Project Period (FY) |
1999 – 2001
|
| Keywords | Interface / Face / Gesture / Finger / Hand / Motion / Image / 3D |
|---|
| Research Abstract |
Conventional interactions between humans and machines are performed mainly by keyboards or special pointing devices. In this project, we have investigated human interface that analyzes user's gestures and facial expressions and identifies their intentions and emotions. The main subjects of this projects are as follows :
1. 3D facial motion measuring system
We have developed a method for measuring three- dimensional moving facial shapes. The system uses two light sources and a slit pattern projector. Natural facial motions can be entered to the system with the sampling rate up to 2/15 sec.
2. Human detection
We have investigated human detection techniques for the system to know the presence of the users. We have presented a moving objects detection technique using edge vectors and edge reliability measures, and a human detection technique using color indexing.
3. Tracking and recognizing facial expressions
We have investigated techniques for tracking and recognizing user's facial expressions. The technique is based on anatomical knowledge on locations and orientations of facial muscles, so that the system can enter the image features from natural facial motions.
4. Gesture analysis
Hands and fingers play an important role in indicating an object. We have developed a stereo method for tracking three-dimensional motions of a hand, and a method for identifying which fingers are stretched.
|
