Abstract A method for gait recognition using human silhouette analysis is proposed. For each image sequence, the binary silhouettes of a walking figure are firstly obtained by background subtraction. An intensity difference algorithm over all color channels is introduced for shadow removal. The shape context descriptors are then employed in silhouette analysis for providing the shape feature. Modified Hausdorff distance gives an idea of the similarity measure between feature vectors of silhouettes. A set of key stances that occur during the walk cycle of an individual is chosen. Combined with window shift technology, distances of silhouettes between key stance sets are computed for subject classification and recognition. The proposed approach is applied to CASIA gait database and Soton database. The correct classification rates of 91.25% and 86.97% are achieved respectively, which illustrate that the proposed method outperforms the existing methods. Experimental results also indicate that the recognition rate maximizes when the number of sample points is 200.
[1] Wang Liang, Tan Tienin, Ning Huazhong, et al. Silhouette AnalysisBased Gait Recognition for Human Identification. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(12): 15051518 [2] Mowbray S D, Nixon M S. Automatic Gait Recognition via Fourier Descriptors of Deformable Objects // Proc of the 4th International Conference on Audio and VideoBased Biometric Person Authentication. Guildford, UK, 2003: 566573 [3] Lee L, Grimson W E L. Gait Analysis for Recognition and Classification // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 148155 [4] Phillips P J, Sarkar S, Robledo I, et al. Baseline Results for the Challenge Problem of Human ID Using Gait Analysis // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 137143 [5] Collins R T, Gross R, Shi Jianbo. SilhouetteBased Human Identification from Body Shape and Gait // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 351356 [6] Belongie S, Malik J, Puzicha J. Shape Matching and Object Recognition Using Shape Contexts. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(4): 509522 [7] Dubuisson M P, Jain A K. A Modified Hausdorff Distance for Object Matching // Proc of the 12th International Conference on Pattern Recognition. Jerusalem, Israel, 1994, Ⅰ: 566568 [8] CASIA Gait Database [DB/OL]. [20060104]. http://www.sinobiometrics.com [9] Shutler J D, Grant M G, Nixon M S, et al. On a Large SequenceBased Human Gait Database // Proc of the 4th International Conference on Recent Advances in Soft Computing. Nottingham, UK, 2002: 6671 [10] Phillips P J, Hyeonjoon M, Rizvi S A, et al. The FERET Evaluation Methodology for FaceRecognition Algorithms. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(10): 10901104 [11] BenAbdelkader C, Cutler R, Nanda H, et al. Eigengait: MotionBased Recognition of People Using Image SelfSimilarity // Proc of the 3rd International Conference on Audioand VideoBased Biometric Person Authentication. Halmstad, Sweden, 2001: 284294 [12] Foster J P, Nixon M S, PrugelBennett A. Automatic Gait Recognition Using AreaBased Metrics. Pattern Recognition Letters, 2003, 24(14): 24892497 [13] Wagg D K, Nixon M S. On Automated ModelBased Extraction and Analysis of Gait // Proc of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, Korea, 2004: 1116 [14] Boyd J. Synchronization of Oscillations for Machine Perception of Gaits. Computer Vision and Image Understanding, 2004, 96(1): 3559
2007, Vol. 20 
