Volume 5 Number 1 (Feb. 2013)
Home > Archive > 2013 > Volume 5 Number 1 (Feb. 2013) >
IJCEE 2013 Vol.5(1): 65-68 ISSN: 1793-8163 DOI: 10.7763/IJCEE.2013.V5.664

Analysis and Performance Comparison of the Feature Vectors in Recognition of Malaysian Sign Language

Yona Falinie A. Gaus, Farrah Wong, Renee Chin, Rosalyn R. Porle, and Ali Chekima
Abstract—In this paper, extraction of suitable feature vector as well as the analysis and performance comparison of the feature vectors using Hidden Markov Model (HMM) are presented. Extracting suitable features comprising of centroids, hand distance and hand orientations is a necessary step to represent isolated Malaysian Sign Language (MSL) to enable detection of right and left hand blobs. Then, each feature vector is modeled using HMM and trained to produce its gesture class. By increasing the number of states starting from 3 until 57 states, each feature vector is trained using HMM so that in the recognition phase it could give the maximum probability among all the other HMMs for a specific word. The system performance of the recognition step was evaluated for each feature vector from the trained model, starting from separated feature vector, followed by combined feature vectors and finally, the union feature vectors. In the experiments, we have tested our system to recognize 112 MSL and found that the union feature vector gives the best recognition rate, which is 83%.

Index Terms—Feature vector, gesture path, hand distance and orientation, hidden markov model.

The authors are with the School of Engineering and Information Technology, Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu, Sabah, Malaysia (e-mail: yonafalinie@gmail.com; farrah@ums.edu.my).

Cite: Yona Falinie A. Gaus, Farrah Wong, Renee Chin, Rosalyn R. Porle, and Ali Chekima, "Analysis and Performance Comparison of the Feature Vectors in Recognition of Malaysian Sign Language,"International Journal of Computer and Electrical Engineering vol. 5, no. 1, pp. 65-68, 2013.

General Information

ISSN: 1793-8163
Frequency: Quarterly
Editor-in-Chief: Prof. Yucong Duan
Abstracting/ Indexing: EI (INSPEC, IET), Ulrich's Periodicals Directory, Google Scholar, EBSCO, ProQuest, and Electronic Journals Library
E-mail: ijcee@iap.org

What's New

  • Mar 20, 2019 News!

    IJCEE Vol. 11, No. 1 is available online now.   [Click]

  • Aug 06, 2018 News!

    IJCEE Vol. 8, No. 4 - Vol. 9, No. 1 have been indexed by EI (Inspec) Inspec, created by the Institution of Engineering and Tech.!   [Click]

  • Mar 20, 2019 News!

    The dois of published papers in Vol. 9, No. 1- Vol. 10, No. 4 have been validated by Crossref.

  • Dec 29, 2018 News!

    IJCEE Vol. 10, No. 4 is available online now.   [Click]

  • Oct 12, 2018 News!

    IJCEE Vol. 10, No. 3 is available online now.   [Click]

  • Read more>>