Publication Date
5-2017
Date of Final Oral Examination (Defense)
5-15-2017
Type of Culminating Activity
Thesis
Degree Title
Master of Science in Computer Science
Department
Computer Science
Supervisory Committee Chair
Steven M. Cutchin, Ph.D.
Supervisory Committee Co-Chair
Jerry Alan Fails, Ph.D.
Supervisory Committee Member
Maria Soledad Pera, Ph.D.
Supervisory Committee Member
Casey Kennington, Ph.D.
Abstract
Sign Language is a language which allows mute people to communicate with other mute or non-mute people. The benefits provided by this language, however, disappear when one of the members of a group does not know Sign Language and a conversation starts using that language. In this document, I present a system that takes advantage of Convolutional Neural Networks to recognize hand letter and number gestures from American Sign Language based on depth images captured by the Kinect camera. In addition, as a byproduct of these research efforts, I collected a new dataset of depth images of American Sign Language letters and numbers, and I compared the presented method for image recognition against a similar dataset but for Vietnamese Sign Language. Finally, I present how this work supports my ideas for the future work on a complete system for Sign Language transcription.
DOI
https://doi.org/10.18122/B2B136
Recommended Citation
Vazquez Lopez, Iker, "Hand Gesture Recognition for Sign Language Transcription" (2017). Boise State University Theses and Dissertations. 1285.
https://doi.org/10.18122/B2B136