Sign Language Recognition using Hybrid Neural Networks
Shaminder Singh1, Anuj Kumar Gupta2, Tejwant Singh3
1Shaminder Singh*, Ph. D. Scholar, IKG Punjab Technical University, Kapurthala, India.
2Anuj Kumar Gupta, Professor, Chandigarh Group of Colleges, Landran, India.
3Tejwant Singh, Dean (Retd.), College of Basic Sciences and Humanities PAU, Ludhiana, India.
Manuscript received on November 16, 2019. | Revised Manuscript received on 27 November, 2019. | Manuscript published on December 10, 2019. | PP: 1092- 1098 | Volume-9 Issue-2, December 2019. | Retrieval Number: L33491081219/2019©BEIESP | DOI: 10.35940/ijitee.L3349.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Language has a prime role in communication between persons, in learning, in distribution of concepts and in preserving public contacts. The hearing-impaired have to challenge communication obstacles in a mostly hearing-capable culture. There are hundreds Sign Languages that are used all around the world today .The Sign Languages are established depending on the country and area of the deaf public. The aim of sign language recognition is to offer an effectual and correct tool to transcribe hand gesture into text. It can play a vital role in the communiqué between deaf and hearing society. Sign language recognition (SLR), as one of the significant research fields of human–computer interaction (HCI), has produced more and more interest in HCI society. Since, artificial neural networks are best suited for automated pattern recognition problems; they are used as a classification tool for this research. Back propagation is the most important algorithm for training neural networks. But, it easily gets trapped in local minima leading to inaccurate solutions. Therefore, some global search and optimization techniques were required to hybridize with artificial neural networks. One such technique is Genetic algorithms that imitate the principle of natural evolution. So, in this article, a hybrid intelligent system is proposed for sign language recognition in which artificial neural networks are merged with genetic algorithms. Results show that proposed hybrid model outperformed the existing back propagation based system.
Keywords: Hand Gesture; Sign Language Recognition, Artificial Neural Networks, Hybrid Neural Networks; Genetic Algorithms.
Scope of the Article: Natural Language Processing