Combing KNN with LCSS for dynamic hand gesture recognition

This data was imported from Scopus:

Authors: Cheng, K., Li, W., Tong, R., Chang, J. and Zhang, J.

Journal: Journal of Computational Information Systems

Volume: 11

Issue: 21

Pages: 7759-7767

ISSN: 1553-9105

DOI: 10.12733/jcis15897

Copyright © 2015 Binary Information Press. We propose a dynamic hand gesture recognition system based on Nguyen-Dinh's longest common subsequence (LCSS) based method, and improve the recognition accuracy from two aspects. First, in order to provide discrete features which characterize gesture movement for LCSS, this paper presents a spherical direction discretization (SDD) method to encode gesture features which can show the differences of each gesture. Second, taking into account different people have different speeds, trajectories and spatial positions to perform the same gesture, this paper combines K nearest neighbors (KNN) with the LCSS to solve the different habits of users. The experiment results show that SDD+KNN+LCSS outperformed k-means+LCSS by 13: 45% (F1-score).

The data on this page was last updated at 05:24 on October 24, 2020.