Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
QianliFengMasterThesis2.pdf (884.1 KB)
ETD Abstract Container
Abstract Header
Automatic American Sign Language Imitation Evaluator
Author Info
Feng, Qianli
ORCID® Identifier
http://orcid.org/0000-0002-7550-2019
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=osu1461233570
Abstract Details
Year and Degree
2016, Master of Science, Ohio State University, Electrical and Computer Engineering.
Abstract
Imitation and evaluation procedure is important for ASL learning and teaching. However, the current online ASL learning resources do not provide affordable and convenient imitation-evaluation function. To solve this problem, we propose an Automatic American Sign Language Imitation Evaluator (AASLIE) to evaluate the hand movement in the imitation. The proposed AASLIE system extracts 3D trajectory of the centroid of the hand by first applying a two-stage algorithm for 2D hand detection and tracking allowing possible hand-face overlaps. The 3D trajectory is extracted using a Structure from Motion algorithm with the point correspondences calculated from minimizing an affine transformation. The evaluation contains two parts, recognition and quantitative evaluation, for giving more sensitive feedback than the current sign language recognition systems. The recognition is achieved by a classification algorithm. The quantitative evaluation score, which indicates the goodness of imitation, is given by a weighted sum of point-wise distance between the imitation trajectory and the standard trajectory. Experiments were conducted for testing the recognition and quantitative evaluation functionality proposed in the system. The results show that the AASLIE system recognizes the trajectories with an average accuracy 0.8581 (±0.05) and the score accurately captures the different levels of goodness of imitation.
Committee
Aleix Martinez, PhD (Advisor)
Yuejie Chi, PhD (Committee Member)
Pages
54 p.
Subject Headings
Computer Science
;
Electrical Engineering
Keywords
American Sign Language analysis
;
imitation evaluation
;
hand detection
;
3D trajectory reconstruction
;
trajectory recognition
;
quantitative evaluation score
;
Linear Discriminant Analysis
;
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Feng, Q. (2016).
Automatic American Sign Language Imitation Evaluator
[Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1461233570
APA Style (7th edition)
Feng, Qianli.
Automatic American Sign Language Imitation Evaluator.
2016. Ohio State University, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=osu1461233570.
MLA Style (8th edition)
Feng, Qianli. "Automatic American Sign Language Imitation Evaluator." Master's thesis, Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1461233570
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
osu1461233570
Download Count:
464
Copyright Info
© 2016, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.