Gait Recognition Based on KPCA and SVM

摘要：

An appearance-based approach to the problem of gait recognition is proposed. The vector data scanned from horizon, vertical and diagonal direction to the binarized silhouette of a walking person are chosen as initial gait features. The nonlinear components of the initial feature are extracted based on Kernel Principal Component Analysis (KPCA). Then the multi-class linear Support Vector Machine (SVM) models are trained by the decomposed nonlinear features, and the gaits are classified by the trained SVM models at last. This approach is applied to a 30 individuals dataset (outside environment), extensive experimental results demonstrate that the proposed algorithm performs an encouraging recognition rate (93％).

关键词： Biometrics Gait Recognition Silhouette Projection Kernel Principal Component Analysis (KPCA) Support Vector Machine (SVM)

作者: Bo Ye Yumei Wen

作者单位: the Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Coll he Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Colle

会议类型: 国际会议

会议名称: The Second International Symposium on Intelligence Computation and Applications(ISICA 2007)(第二届智能计算及其应用国际会议)

会议地点: 武汉

会议语种:英文

在线出版日期: 2007-09-21（万方平台首次上网日期，不代表论文的发表时间）