Gait recognition based on KPCA and KNN

This paper presents a novel approach for human identification at a distance using gait recognition. The proposed work introduces a nonlinear machine learning method, Kernel Principal Component Analysis (KPCA), and K nearest neighbor classification (KNN) classifier for gait recognition. Kernel Principal Component Analysis (KPCA) is first applied to 1-dimension signals derived from a sequence of silhouette images to reduce its dimensionality. Then, we performed K nearest neighbor classification (KNN) for gait recognition. The experimental results show the KPCA and KNN based gait recognition algorithm is better than that based on PCA.