A Gait Recognition Method Based on Features Fusion and SVM

The algorithm based on multi-feature and SVM is proposed. The paper firstly uses wavelet de-noising for gait images. The text offers to use width descriptors as gait features and combines lower angle features. The Kernel-based fisher criterion and support vector machine is combined to classification and identification. The gait characteristic is extracted by KFDA, which can obtain the best projection direction and enhance the capacity of data classification. Then the support vector machine (SVM) models are trained by the decomposed feature vectors. The gaits are classified by the trained SVM models. The paper tries using wavelet kernel and obtains better result. This algorithm is applied to a data-set including thirty individuals. Extensive experimental results demonstrate that the proposed algorithm performs at an encouraging recognition rate of 91% and at a relatively lower computational cost.