人類走路之步態已經被心理學家證明是對於每個人而言是唯一的。因此，它對於應用在身份辨識是一個有用的特徵。然而，使用步態特徵作身份辨識仍然有一些問題。在這篇論文中，我們將重點放在步態受到衣著影響變化之改善。首先，我們利用沒有受到衣著影響變化之步態，學出不受衣著影響變化之步態特性，並且將此特性模組化。我們稱此模組為正常情況模組。藉由這個正常情況模組，我們可以偵測出在步態中有受到衣著影響變化的部分並且除去之。我們將利用正常情況模組進行除去衣著影響變化之過程，稱之為正常情況相減法。從本篇論文的實驗結果中，我們提出的正常情況相減法的確能夠在人類身份辨識之應用中，比其他現有設法解決衣著影響變化之方法還要有更高的辨識精確度。

Human gait has been shown to be unique and could be treated as a useful signature for human identification. Nevertheless there are still some problems when using the gait for human identification. In this thesis, we focus on the improvement of the clothing-variation problem. First, we model the characteristics of human gait which suffers no clothing-variation as the normal case model. Next, we detect and remove the clothing-variation parts of a gait based on this model. The process of removing the clothing-variation using the normal case model is called the normal case subtraction. The experimental results show that our proposed normal case subtraction outperforms other existing approaches of solving the clothing-variation problem in human identification.

[1] L. Wang, H. Ning, T. Tan, and W. Hu, “Fusion of Static and Dynamic Body Biometrics for Gait Recognition,” IEEE Trans. Circuits and Systems for Video Technology, vol. 14, no. 2, pp. 149-158, Feb. 2004.
[2] D. K. Wagg and M. S. Nixon, “Automated Markerless Extraction of Walking People Using Deformable Contour Models,” Comput. Animation Virtual Worlds, vol. 15, no. 3/4, pp. 399-406, Jul. 2004.
[3] I. Bouchrika and M. S. Nixon, “Model-Based Feature Extraction for Gait Analysis and Recognition,” Proceedings of Mirage: Computer Vision / Computer Graphics Collaboration Techniques and Applications, pp. 150-160, 2007.
[4] D. Kim, D. Kim, and J. Paik, “Gait Recognition Using Active Shape Model and Motion Prediction,” IET Computer Vision, vol. 4, no. 1, pp. 25-36, 2010.
[5] J. Hayfron-Acquah, M. S. Nixon, and J. Carter, “Automatic Gait Recognition by Symmetry Analysis,” Proc. Int’l Conf. Audio-and-Video-Based Biometric Person Authentication, pp. 272-277, 2001.
[6] A. Kale, N. Cuntoor, B. Yegnanarayana, A. N. Rajagopalan, and R. Chellappa, “Gait Analysis for Human Identification,” Proc. Int’l Conf. Audio-and-Video-Based Biometric Person Authentication, pp. 706-714, 2004.
[7] Y. Makihara, R. Sagawa, Y. Mukaigawa, T. Echigo, and Y. Yagi, “Gait Recognition Using a View Transformation Model in the Frequency Domain,” ECCV 2006.
[8] J. Han and B. Bhanu, “Individual Recognition Using Gait Energy Image,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 2, pp. 316-322, Feb. 2006.

[9] S. Sarkar, P.J. Phillips, Z. Liu, I.R. Vega, P.Grother, and K.W. Bowyer, “The HumanID Gait Challenge Problem: Data Sets, Performance, and Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 2, pp. 162-177, Feb. 2005.
[10] M. A. Hossain, Y. Makihara, W. Junqui, and Y, Yagi, “Clothes-Invariant Gait Identification Using Part-Based Adaptive Weight Control,” ICPR 2008.
[11] S. Singh and K.K. Biswas, “Spatio-temporal Energy based Gait Recognition,” IEEE International Conference on Data Mining, pp. 998-1003, 2009.
[12] Y. Pratheepan, J.V. Condell and G. Prasad, “The use of Dynamic and Static Characteristics of Gait for Individual Identification,” IEEE International Machine Vision and Image Processing, pp. 111-116, 2009.
[13] X. Yang, Y. Zhou, T. Zhang, G. Shu, and J. Yang, “Gait Recognition Based on Dynamic Region Analysis,” Signal Processing, vol. 88, no. 9, pp. 2350-2356, 2008.
[14] R. E. Bellman, “Adaptive Control Processes,” Princeton University Press, Princeton, NJ, 1961.
[15] The CASIA Gait Database http://www.cbsr.ia.ac.cn/
[16] The LIBSVM tools http://www.csie.ntu.edu.tw/~cjlin/libsvm/
[17] P. J. Phillips, H. Moon, S. Rizvi, and P. Rauss, “The FERET Evaluation Methodology for Face-Recognition Algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1090-1104, Oct. 2000.