A Dynamic Hand Gesture Recognition System Incorporating Orientation-based Linear Extrapolation Predictor and Velocity-assisted Longest Common Subsequence Algorithm

• Min Yuan,
• Heng Yao,
• Chuan Qin,
• Ying Tian,

Vol. 11, No. 9, September 29, 2017
10.3837/tiis.2017.09.017, Download Paper (Free):

• Dynamic gesture recognition
• adaptive linear extrapolation
• longest common subsequence (LCS)
• velocity information

Abstract

The present paper proposes a novel dynamic system for hand gesture recognition. The approach involved is comprised of three main steps: detection, tracking and recognition. First, the gesture contour captured by a 2D-camera is detected by combining the three-frame difference method and skin-color elliptic boundary model. Then, the trajectory of the hand gesture is extracted via a gesture-tracking algorithm based on an occlusion-direction oriented linear extrapolation predictor, where the gesture coordinate in next frame is predicted by the judgment of current occlusion direction. Finally, to overcome the interference of insignificant trajectory segments, the longest common subsequence (LCS) is employed with the aid of velocity information. Besides, to tackle the subgesture problem, i.e., some gestures may also be a part of others, the most probable gesture category is identified through comparison of the relative LCS length of each gesture, i.e., the proportion between the LCS length and the total length of each template, rather than the length of LCS for each gesture. The gesture dataset for system performance test contains digits ranged from 0 to 9, and experimental results demonstrate the robustness and effectiveness of the proposed approach.

Statistics

Cite this article