A Study on the Indirect Keyboard Control System based on the Gaze Tracing by Haar Classifiers
1
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
This paper describes on the indirect interface system which can assign the computer instructions via a eye typing, without using a mouse click event or a keyboard stroke. The web camera was used as a input system. The face and eye regions were extracted by the Open source Computer Vision Library (OpenCV). It automatically controls a mouse-movement by calculating the position on the monitor where the eyesight focuses on, and simulates a mouse-click event by detecting the eye blinking action. We use the Tracebox which consist of same length and width on the monitor to simulate a keyboard entry. Over 95% tracing accuracy was achieved when the size of a Tracebox per each character exceeds 25 pixels.
Abstract
This paper describes on the indirect interface system which can assign the computer instructions via a eye typing, without using a mouse click event or a keyboard stroke. The web camera was used as a input system. The face and eye regions were extracted by the Open source Computer Vision Library (OpenCV). It automatically controls a mouse-movement by calculating the position on the monitor where the eyesight focuses on, and simulates a mouse-click event by detecting the eye blinking action. We use the Tracebox which consist of same length and width on the monitor to simulate a keyboard entry. Over 95% tracing accuracy was achieved when the size of a Tracebox per each character exceeds 25 pixels.
참고문헌 (11)
- Yamoto, M, "Quick Button election with Eye Gazing for General GUI Environments", International Conference on Software: Theory and Practice (2000)
- "Open Computer Vision Library Reference Manual" (2001), Intel Corporation, USA
- Lienhart, R, "An extended set of Haar-like features for rapid object detection", IEEE ICIP 2002, 1, pp.900~903 (2002)
- Viola, P, "Rapid object detection using boosted cascade of simple features", IEEE Conference on Computer Vision and Pattern Recognition (2001)
- Gary Bradski, "Learning-Based Computer Vision with Intel’s Open Source Computer Vision Library", Intel Technology Journal, 9(2) (2005)
- Paul Viola, "Rapid Object Detection using a Boosted Cascade of Simple Features", accepted conference on computer vision and pattern recognition (2001)
- Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection, "Rainer Lienhart", MRL Technical Report, ~ (2002)
- Bo WU, "Fast Rotation Invariant Multi-View Face Detection Based on Real AdaBoost" (2004), Computer Society
- Päivi Majaranta, "Effects of feedback and dwell time on eye typing speed and accuracy", Springer-Verlag Universal Access in the Information Society, 5(2) (2006)
- Hirotaka Aoki, "Learning to interact with a computer by gaze", Taylor & Francis Behaviour & Information Technology, 27(4), pp.339~344 (2008)
- Kentaro Kotani, "Design of Eye-Typing Interface Using Saccadic Latency of Eye Movement", Taylor & Francis International Journal of Human-Computer Interaction, 26(4), pp.361~376 (2010)