This Master thesis proposes a human-computer interface for individual with limited hand movements that incorporate the use of facial gesture as a means of communication. The system recognizes faces and extracts facial gestures to map them into Morse code that would be translated in English in real time. The system is implemented on a MACBOOK computer using Python software, OpenCV library, and Dlib library. The system is tested by 6 students. Five of the testers were not familiar with Morse code. They performed the experiments in an average of 90 seconds. One of the tester was familiar with Morse code and performed the experiment in 53 seconds. It is concluded that errors occurred due to variations in features of the testers, lighting conditions, and unfamiliarity with the system. Implementing an auto correction and auto prediction system will decrease typing time considerably and make the system more robust.
Identifer | oai:union.ndltd.org:unt.edu/info:ark/67531/metadc1062841 |
Date | 12 1900 |
Creators | Toure, Zikra |
Contributors | Namuduri, Kamesh, Li, Xinrong, Varanasi, Murali |
Publisher | University of North Texas |
Source Sets | University of North Texas |
Language | English |
Detected Language | English |
Type | Thesis or Dissertation |
Format | viii, 60 pages, Text |
Rights | Public, Toure, Zikra, Copyright, Copyright is held by the author, unless otherwise noted. All rights Reserved. |
Page generated in 0.0019 seconds