Text Composing Software for Disabled People, Using Blink and Motion Detection
We presentate a pc software to give disabled persons the possibility of writing texts without mouse and keyboard. Single letters and words are presented, scrolling over the screen. The suggested words are chosen from a self-learning database by frequency of their use. Although different kinds of binary input signals can be used, we focused on blink detection for choosing letters and words. Algorithms based on Haar Cascades are used for finding the eyes. We aim on low-cost realisation, therefore a state-of-the-art Windows based computer and a commercially available webcam is used. As an alternative input device we used a acceleration sensor for motion detection. We could successfully demonstrate quick text writing with different test persons.
Keywordstext composing blink detection acceleration sensor OpenCV disabled persons
Unable to display preview. Download preview PDF.
- 1.Morris, T., Blenkhorn, P., Zaidi, F.: Blink detection for real-time eye tracking. Journal of Network and Computer Applications (JNCA) 25, 129–143 (2002), doi:10.1006/jnca.2002Google Scholar
- 2.Chau, M., Betke, M.: Real Time Eye Tracking and Blink Detection with USB Cameras. In: Boston University Computer Science, Technical Report No. 2005-12 (2005)Google Scholar
- 3.Söllner, M., Hofmann, P., Pösl, J.: Using Triaxial Acceleration Sensors as Input Devices for Disabled Persons. In: ICCHP 2010, Computers Helping People with Special Needs Springer, Berlin (2010)Google Scholar
- 5.Wilson, P.I., Fernandez, J.: Facial feature detection using Haar classifiers. Journal of Computing Sciences in Colleges 21(4), 127–133 (2006); ISSN:1937-4771Google Scholar