Dual LMCs fusion for recognition of isolated Arabic sign language words

S. Aliyu; M. Mohandes; M. Deriche

doi:10.1109/SSD.2017.8167010

Dual LMCs fusion for recognition of isolated Arabic sign language words

S. Aliyu^*
, M. Mohandes
, M. Deriche

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

In this paper, we propose a Dual-Leap Motion Controllers (DLMC) based Arabic Sign Language recognition system. More particularly, we propose to use both front and side controllers to cater for the challenges of finger occlusions and missing data. For feature extraction, we select an optimum set of geometric features extracted from both controllers, while for classification, we used both a Bayesian approach with a Gaussian Mixture Model (GMM) and a simple Linear Discriminant Analysis (LDA) approach. Though this paper focused only on the GMM approach. Data was collected from a native adult signer, for 100 isolated Arabic words. Ten observations were collected for each of the signs. The proposed framework uses an intelligent strategy to handle the case of missing data from one or both controllers. A recognition accuracy of 94.63% was achieved, with the proposed system. The proposed system outperforms glove-based systems and a single-LMC based techniques.

Original language	English
Title of host publication	2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	611-614
Number of pages	4
ISBN (Electronic)	9781538631751
DOIs	https://doi.org/10.1109/SSD.2017.8167010
State	Published - 4 Dec 2017

Publication series

Name	2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017
Volume	2017-January

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Keywords

Arabic sign langauge recognition
electronic glove
image-based system
leap motion controller
machine learning

ASJC Scopus subject areas

Computer Science Applications
Signal Processing
Control and Optimization
Instrumentation

Access to Document

10.1109/SSD.2017.8167010

Cite this

Aliyu, S., Mohandes, M., & Deriche, M. (2017). Dual LMCs fusion for recognition of isolated Arabic sign language words. In 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017 (pp. 611-614). (2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD.2017.8167010

@inproceedings{a585d88d329e4c1ca56f2c5d3700b0c7,

title = "Dual LMCs fusion for recognition of isolated Arabic sign language words",

abstract = "In this paper, we propose a Dual-Leap Motion Controllers (DLMC) based Arabic Sign Language recognition system. More particularly, we propose to use both front and side controllers to cater for the challenges of finger occlusions and missing data. For feature extraction, we select an optimum set of geometric features extracted from both controllers, while for classification, we used both a Bayesian approach with a Gaussian Mixture Model (GMM) and a simple Linear Discriminant Analysis (LDA) approach. Though this paper focused only on the GMM approach. Data was collected from a native adult signer, for 100 isolated Arabic words. Ten observations were collected for each of the signs. The proposed framework uses an intelligent strategy to handle the case of missing data from one or both controllers. A recognition accuracy of 94.63\% was achieved, with the proposed system. The proposed system outperforms glove-based systems and a single-LMC based techniques.",

keywords = "Arabic sign langauge recognition, electronic glove, image-based system, leap motion controller, machine learning",

author = "S. Aliyu and M. Mohandes and M. Deriche",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2017",

month = dec,

day = "4",

doi = "10.1109/SSD.2017.8167010",

language = "English",

series = "2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "611--614",

booktitle = "2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017",

address = "United States",

}

Aliyu, S, Mohandes, M & Deriche, M 2017, Dual LMCs fusion for recognition of isolated Arabic sign language words. in 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017. 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 611-614. https://doi.org/10.1109/SSD.2017.8167010

Dual LMCs fusion for recognition of isolated Arabic sign language words. / Aliyu, S.; Mohandes, M.; Deriche, M.
2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 611-614 (2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dual LMCs fusion for recognition of isolated Arabic sign language words

AU - Aliyu, S.

AU - Mohandes, M.

AU - Deriche, M.

PY - 2017/12/4

Y1 - 2017/12/4

N2 - In this paper, we propose a Dual-Leap Motion Controllers (DLMC) based Arabic Sign Language recognition system. More particularly, we propose to use both front and side controllers to cater for the challenges of finger occlusions and missing data. For feature extraction, we select an optimum set of geometric features extracted from both controllers, while for classification, we used both a Bayesian approach with a Gaussian Mixture Model (GMM) and a simple Linear Discriminant Analysis (LDA) approach. Though this paper focused only on the GMM approach. Data was collected from a native adult signer, for 100 isolated Arabic words. Ten observations were collected for each of the signs. The proposed framework uses an intelligent strategy to handle the case of missing data from one or both controllers. A recognition accuracy of 94.63% was achieved, with the proposed system. The proposed system outperforms glove-based systems and a single-LMC based techniques.

AB - In this paper, we propose a Dual-Leap Motion Controllers (DLMC) based Arabic Sign Language recognition system. More particularly, we propose to use both front and side controllers to cater for the challenges of finger occlusions and missing data. For feature extraction, we select an optimum set of geometric features extracted from both controllers, while for classification, we used both a Bayesian approach with a Gaussian Mixture Model (GMM) and a simple Linear Discriminant Analysis (LDA) approach. Though this paper focused only on the GMM approach. Data was collected from a native adult signer, for 100 isolated Arabic words. Ten observations were collected for each of the signs. The proposed framework uses an intelligent strategy to handle the case of missing data from one or both controllers. A recognition accuracy of 94.63% was achieved, with the proposed system. The proposed system outperforms glove-based systems and a single-LMC based techniques.

KW - Arabic sign langauge recognition

KW - electronic glove

KW - image-based system

KW - leap motion controller

KW - machine learning

UR - https://www.scopus.com/pages/publications/85046649103

U2 - 10.1109/SSD.2017.8167010

DO - 10.1109/SSD.2017.8167010

M3 - Conference contribution

AN - SCOPUS:85046649103

T3 - 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017

SP - 611

EP - 614

BT - 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Aliyu S, Mohandes M, Deriche M. Dual LMCs fusion for recognition of isolated Arabic sign language words. In 2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 611-614. (2017 14th International Multi-Conference on Systems, Signals and Devices, SSD 2017). doi: 10.1109/SSD.2017.8167010

Dual LMCs fusion for recognition of isolated Arabic sign language words

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this