IJBTT

Analysis of Various Features of Hand Gestures using Leap Motion Controller for Indian Sign Language Interpretation

	International Journal of Engineering Trends and Technology (IJETT)
	© 2018 by IJETT Journal
	Volume-61 Number-1
	Year of Publication : 2018
	Authors : Archana Ghotkar, Pujashree Vidap
	DOI :  10.14445/22315381/IJETT-V61P203

Citation 

MLA Style: Archana Ghotkar, Pujashree Vidap"Analysis of Various Features of Hand Gestures using Leap Motion Controller for Indian Sign Language Interpretation" International Journal of Engineering Trends and Technology 61.1 (2018): 14-19.

APA Style:Archana Ghotkar, Pujashree Vidap, (2018). Analysis of Various Features of Hand Gestures using Leap Motion Controller for Indian Sign Language InterpretationInternational Journal of Engineering Trends and Technology, 61(1), 14-19.

Abstract
Hand gesture recognition for sign language interpretation is an active research currently going on. As a computer vision application, varieties of sensors/cameras with notable features are available for capturing live gesture. In this paper, real time hand gesture recognition has been done with Leap motion sensor. The main objective of this research is to do analysis of various derived (hand) features provided by leap motion with different classifier and select notable features with tested classifier for the further study. Indian sign language (ISL) dataset of alphabets and numbers are considered for performance analysis. Here, total 68 features for both hands (34 for each hand) are derived and tested with nearest neighbourhood, Logistic regression, Support Vector Machine (SVM) and nearest mean classifier. The fusion vector of 68 features are created and tested with different classifier to check the performance. Result shows that, SVM classifier giving better result of 96.19% for ISL alphabets and 100 % for ISL numbers with fusion vector. The detailed analysis shows that selection of hand orientation features instead of distance features are also a good choice for hand gesture recognition.

Reference
[1] Gajanan K. Kharate and Archana S. Ghotkar, “Vision based Multi-Feature Hand Gesture Recognition for Indian Sign Language Manual Signs”, International Journal on Smart sensing and intelligent systems, Vol.9 (1), March 2016, pp.124-147.
[2] Archana S. Ghotkar and Gajanan K. Kharate, “Dynamic Hand Gesture Recognition and Novel Sentence Interpretation Algorithm for Indian sign language Using Microsoft Kinect Sensor”, Journal of Pattern Recognition Research, Volume 10, No.1, August 2015, pp. 24-38.
[3] U. Zeshan, M. Vasishta, M. Sethna, “Implementation of Indian Sign Language in Educational Setting,” Asia pacific Disability Rehabilitation Journal,Vo.16, No.1, pp.16-39, 2005.
[4] Archana S. Ghotkar, Gajanan K. Kharate, “Study of Vision based Hand Gesture Recognition Using Indian Sign Language” , International Journal on Smart Sensing and Intelligent System, Volume. 7, No.1, March 2014. pp. 96-115.
[5] C. Vogler, D. Metaxas, “A Framework for Recognizing the Simultaneous Aspects of American Sign Language,” Computer Vision and Image Understanding, pp. 358-384, 2001
[6] Archana Ghotkar, Pujashree Vidap and Kshitish Deo, “Dynamic Hand Gesture Recognition using Hidden Markov Model by Microsoft Kinect Sensor”, International Journal of Computer Application, Vol. 150(5), PP. 5-9, Sept. 2016
[7] Lionel Pigou, Sander Dieleman, Pieter-Jan Kindermans, and Benjamin Schrauwen “Sign Language Recognition Using Convolutional Neural Networks”. Springer International Publishing Switzerland 2015. pp 572-578.
[8] Leigh Ellen Potter, Jake Araullo, Lewis Carter, “The Leap Motion controller: A view on sign language”. Proceedings of the 25th Australian Computer-Human Interaction Conference: Augmentation, Application, Innovation, Collaboration. pp 175-178
[9] D. Naglot, M. Kulkarni. “ANN based Indian Sign Language Numerals Recognition using the Leap Motion Controller”.International Conference on Inventive Computation Technologies (ICICT), Vol 3 ,August-2016
[10] D. Naglot, M. Kulkarni, “Real Time Sign Language Recognition using the Leap Motion Controller”, International Conference on Inventive Computation Technologies (ICICT), Vol 3, August-2016
[11] Rajesh B. Mapari, Govind Kharat, “Analysis of Multiple Sign Language Recognition Using Leap Motion Sensor”, International Journal of Research in Advent Technology (IJRAT), March 2017.
[12] Makiko Funasaka, Yu Ishikawa, Masami Takata, and Kazuki Joe, “Sign Language Recognition using Leap Motion Controller” International conference on Parallel/Distributed Processing Tech/ Appls PDPTA`15.
[13] Midarto Dwi Wibowo, Ingrid Nurtanio ,Amil Ahmad Ilham, “Indonesian sign language recognition using leap motion controller”. 11th International Conference on Information & Communication Technology and System (ICTS), 2017.
[14] M. Mohandes, S. Aliyu and M. Derich, “Arabic Sign Language Recognition using the Leap Motion Controller”, IEEE 23rd International Symposium on Industrial Electronics (ISIE) 2014. pp 960-965.
[15] Ching-Hua Chuan, Eric Regina, Caroline Guardino. “American Sign Language Recognition Using Leap Motion Sensor”, 13th International Conference on Machine Learning and Applications. pp541-544
[16] Archana S. Ghotkar, Gajanan K. Kharate, “Study of Vision based Hand Gesture Recognition Using Indian Sign Language,” International Journal on Smart Sensing and Intelligent System, Volume. 7, No.1, March 2014. pp. 96-115.
[17] Archana S. Ghotkar, Gajanan K. Kharate, “Vision based Real time Hand Gesture Recognition Techniques for HCI,” International Journal of computer Application, Volume. 70, No. 16, Foundation of Computer Science, New York, USA, 2013, pp.1-6
[18] Leap Motion, http://www.leapmotion.com

Keywords
Indian Sign Language, 3D Leap Motion sensor, Pattern recognition, k-nearest neighbor, Logistic regression, Support vector machine, Nearest mean classifier.