基于列质量向量和SVM的步态识别

步态识别是根据人行走的方式来识别其身份，以其特有的优势作为一种身份识别手段。为了提高步态的识别率，提出了一种新方法，使用人体轮廓列质量向量表征特征信息，并使用支持向量机进行识别。根据人体轮廓的高度和宽度计算出步态周期，提取每个步态轮廓列质量向量，最后采用支持向量机进行分类识别。为了验证所提出方法的有效性，在CASIA步态数据库上进行了充足的实验，验证了该方法具有较高的识别率。

Gait recognition method based on column mass vector and support vector machine

Gait recognition is based on the walk way to identity, with its unique advantages as a means of identification. In order to improve the gait recognition rate, this paper presents a novel approach for gait recognition based on column mass vector of body contour as feature, with support vector machine together effectively. According to the height and width of body contour to calculate gait cycle, it extractes column mass of body contour, finally, using support vector machine for classification. To verify the effectiveness, a lot of experiments have been performed in the CASIA gait database. Experimental verification of proposed method has higher recognition rate.