Extracting Multiple Features for Dynamic Hand Gesture Recognition
Suni S. S1, K. Gopakumar2
1Suni S S* , Research Scholar, LBS Centre for Science and Technology, University of Kerala, Thiruvananthapuram, Kerala, India.
2K Gopakumar, Professor, TKM College of Engineering, Kollam, Kerala, India
Manuscript received on March 22, 2021. | Revised Manuscript received on April 05, 2021. | Manuscript published on April 30, 2021. | PP: 71-75 | Volume-10 Issue-4, April 2021. | Retrieval Number: 100.1/ijeat.D23430410421 | DOI: 10.35940/ijeat.D2343.0410421
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In this work a framework based on histogram of orientation of optical flow (HOOF) and local binary pattern from three orthogonal planes (LBP_TOP) is proposed for recognizing dynamic hand gestures. HOOF algorithm extracts local shape and dynamic motion information of gestures from image sequences and local descriptor LBP is extended to three orthogonal planes to create an efficient motion descriptor. These features are invariant to scale, translation, illumination and direction of motion. The performance of the new framework is tested in two different ways. The first one is by fusing the global and local features as one descriptor and the other is using features separately to train the multi class support vector machine. Performance analysis shows that the proposed approach produces better results for recognizing dynamic hand gestures when compared with state of the art methods.
Keywords: Hand gesture recognition, Histogram of orientation of optical flow, local binary pattern, Multiclass support vector machine, Scale invariant feature.
Scope of the Article: Software engineering decision support