Back to search

University of North Texas

Human-Machine Interface Using Facial Gesture Recognition

Abstract

dc:description

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.

Degree

thesis:*
Grantor dc:publisher
University of North Texas
Year dc:date
2017

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Toure, Zikra Ibrahim
Contributors dc:contributor
  • Namuduri, Kamesh
  • Li, Xinrong, 1972-
  • Varanasi, Murali R.

Subjects

dc:subject × 7

Rights

dc:rights
Statement dc:rights
  • Public
  • Toure, Zikra Ibrahim
  • Copyright
  • Copyright is held by the author, unless otherwise noted. All rights Reserved.
Language dc:language
English

Identifiers

dc:identifier.*
Identifier
local-cont-no: submission_963
https://digital.library.unt.edu/ark:/67531/metadc1062841/
ark: ark:/67531/metadc1062841

Chain of custody

source
Harvested from
University of North Texas
Base URL
digital.library.unt.edu/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Toure, Zikra Ibrahim. Human-Machine Interface Using Facial Gesture Recognition. University of North Texas, 2017. https://doi.org/10.12794/metadc1062841