基于支持向量机的手势识别研究

Study on Gesture Recognition with Support Vector Machine

本文主要研究支持向量机在手势识别中模型的选择,包括多类模型和核函数的选择,提出基于径向基核函数和一对一多类方法的支持向量机模型是最佳分类模型。实验结果表明该方法具有很高的识别率,并且简单快速,可以用于实时的手势识别系统中。

The paper introduces the selection of SVM models including kernel functions and multi-class methods. The SVM with a RBF kernel function and One-against-one multi-class method is the best classifier for gesture identification. The experiments result shows that the recognition rate is high, we can applying this method to a real time gesture recognition system.