A new attempt to gait-based human identification

The authors propose a simple but efficient approach to gait recognition. For each image sequence, an improved background subtraction procedure is first used to accurately extract spatial silhouettes of a walker from the background. Then, an eigenspace transformation to time-varying silhouette shapes is performed to realize feature extraction. The nearest neighbor classifier using spatio-temporal correlation or the normalized Euclidean distance measure is finally utilized in the lower-dimensional eigenspace for recognition, and some additional personalized physical properties are selected for the validation of final decision Experimental results on a small database show that the proposed algorithm has an encouraging recognition rate with relatively lower computational cost.