Hand Gesture Recognition System using Deep Learning
B. Hemanth1, K. Sai Venkat2, Y. Bhaskar Rao3
1B.Hemanth, Student, Department of ECE SSE, SIMATS, Chennai (Tamil Nadu), India.
2K.Sai Venkat, Student, Department of ECE SSE, SIMATS, Chennai (Tamil Nadu), India.
3Mr.Y. Bhaskar Rao, Assistant Professor, Department of ECE SSE, SIMATS, Chennai (Tamil Nadu), India.
Manuscript received on 15 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 06 September 2019 | PP: 240-245 | Volume-8 Issue- 6S, August 2019 | Retrieval Number: F10480886S19/19©BEIESP | DOI: 10.35940/ijeat.F1048.0886S19
Open Access | Editorial and Publishing 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: Hand motion acknowledgment is a characteristic method for human PC association and a zone of dynamic research in PC vision and AI. This is a zone with a wide range of conceivable applications, giving clients an easier and increasingly normal approach to speak with robots/frameworks interfaces, without the requirement for additional gadgets. Along these lines, the essential objective of signal acknowledgment explore connected to Human-Computer Interaction (HCI) is to make frameworks, which can distinguish explicit human motions and use them to pass on data or controlling gadgets. For that, vision-based hand signal interfaces require quick and incredibly strong hand discovery, and motion acknowledgment continuously. This paper introduces an answer, sufficiently nonexclusive, with the assistance of deep learning, permitting its application in a wide scope of human-PC interfaces, for ongoing motion acknowledgment. Investigations did demonstrated that the framework had the capacity to accomplish a precision of 99.4% as far as hand act acknowledgment and a normal exactness of 93.72% as far as unique signal acknowledgment.
Keywords: Hand Posture Recognition, Hand Gesture Recognition, Computer Vision, Neural Network, Human-Computer Interaction.
Scope of the Article: DeepLearning