Sign Language Gesture Recognition System for Hearing Impaired People

Print
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2018
Authors:
Uttam Prabhu Dessai, Amita Dessai
10.5120/ijca2018917131

Uttam Prabhu Dessai and Amita Dessai. Sign Language Gesture Recognition System for Hearing Impaired People. International Journal of Computer Applications 179(45):17-20, May 2018. BibTeX

@article{10.5120/ijca2018917131,
	author = {Uttam Prabhu Dessai and Amita Dessai},
	title = {Sign Language Gesture Recognition System for Hearing Impaired People},
	journal = {International Journal of Computer Applications},
	issue_date = {May 2018},
	volume = {179},
	number = {45},
	month = {May},
	year = {2018},
	issn = {0975-8887},
	pages = {17-20},
	numpages = {4},
	url = {http://www.ijcaonline.org/archives/volume179/number45/29435-2018917131},
	doi = {10.5120/ijca2018917131},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

The hand gesture is one of a powerful means of communication among human. Sign language is an essential and natural expressive mean of communication for the deaf people. American sign language helps the hearing-impaired people to communicate with the world as well as the computer. This paper proposes a technique for the recognition of American alphabet sign language. The technique of image processing, that is singular value decomposition (SVD), is applied in order to extract characteristics of the hand images performing individual alphabet of American sign language. The decomposed singular values extracted from the image are used to classify the image into one of the ASL alphabets. These SV features are then applied to SVM classifier for gesture recognition. The totals of 26 American sign language gestures are used in the experiments. This procedure is executed on a database with a total of 899 images of static American sign language gestures taken under different background and lighting conditions. The recognition rate of the proposed technique at about 74 % is achieved.

References

  1. HGR1 database, http://sun.aei.polsl.pl/~mkawulok/gestures/
  2. C.V Soumya, Muzameel Ahmed,” Artificial Neural Network based Identification and Classification of images of Bharatanatyam Gestures”, International Conference on Innovative Mechanisms for Industry Applications 2017.
  3. Sruthi Upendran, Thamizharasi A, “American Sign Language Interpreter for Deaf and Dumb Individuals”, International Conference on Control, Instrumentation, Communication and Computational Technologies 2014.
  4. Tin Hninn Hninn Maung,” Real Time Tracking and Gesture Recognition System using Neural Networks”, International Journal of Computer, Electrical, Automation, Control and Information Engineering 2009.
  5. Md R Ahsan, Muhammed I. Ibrahimy, Othman O. Khalifa,” Hand motion detection from EMG signals by using ANN based classifier for human computer interaction”, International Conference on Innovative Mechanisms for Industry Applications 2011.
  6. Yuh Rau Wang, Jia Liang Syu, Hsin Ting Li, Ling Yang,”, Fast hand detection and gesture recognition”, International conference on machine learning and cybernetics 2015.
  7. Ankita Saxena, Deepak Kumar Jain, Ananya Singhal, “Hand gesture recognition using an android device”, International conference on communication systems, and network technologies,2014.
  8. Rahat Yasir, Riasat Azim Khan,” Two handed hand gesture recognition for Bangla sign language using LDA and ANN”, International Conference on Innovative Mechanisms for Industry Applications 2015.
  9. Khan Mohammad Irteza, Sheikh Md. Masudul Ahsan, Razib Chandra Deb,” Recognition of Hand Gesture Using Hidden Markov Model”, International Conference on Control, Instrumentation, Communication and Computational Technologies 2014.

Keywords

American sign language, Singular value decomposition , Support vector machine.