Hand Gesture Recognition Based on a Nonconvex Regularization

TL;DR

This paper introduces a novel vision-based hand gesture recognition method utilizing nonconvex $ ext{l}_{1-2}$ regularization, solved efficiently with ADMM, demonstrating promising results on binary and grayscale datasets.

Contribution

It presents a new hand gesture recognition model based on $ ext{l}_{1-2}$ regularization, advancing sparse representation techniques in human-robot interaction.

Findings

Effective in recognizing hand gestures on binary and grayscale datasets

Outperforms traditional regularization methods in sparsity promotion

Demonstrates efficiency with ADMM optimization

Abstract

Recognition of hand gestures is one of the most fundamental tasks in human-robot interaction. Sparse representation based methods have been widely used due to their efficiency and low demands on the training data. Recently, nonconvex regularization techniques including the $\ell_{1-2}$ regularization have been proposed in the image processing community to promote sparsity while achieving efficient performance. In this paper, we propose a vision-based hand gesture recognition model based on the $\ell_{1-2}$ regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on binary and gray-scale data sets have demonstrated the effectiveness of this method in identifying hand gestures.