Abstract: An embedded hidden Markov model(e-HMM) human recognition scheme based on gait energy image(GEI) is proposed. First a preprocess technique is used to segment the moving silhouette from the walking figure. The algorithm obtains the gait quasi-periodicity through analyzing the width information of the lower limbs’ gait contour edge, and the mean GEI is calculated from gait periodic. It makes use of an optimized set of observation vectors obtained from the two dimensional discrete cosine transform(2D-DCT) coefficients of the mean GEI regions. The e-HMM is trained and used for the gait recognition. The proposed algorithm is evaluated on USF and CASIA Gait Database. The experimental result shows that the proposed approach is valid and has encouraging recognition performance.

Key words: computer application, biometrics recognition, embedded hidden Markov models, gait energy image