性別辨識在電腦視覺的領域中逐漸受到重視，而且可以廣泛地應用在安全監 控、商業分析或人機互動識別等領域。由於步態性別辨識系統具有非侵犯性、遠 距獲取、影像畫質要求不高、與不易偽裝等特性，不僅是學術界的熱門研究主題，
也可為生活增加許多便利性。
步態是由許多不同且複雜的紋理組合而成，使得不同人所展現出的步態變化 細微與差異程度相當地複雜。本論文採用將影像先經過 GEI 處理後，結合 TPLZP 擷取步態影像的特徵，並以區塊式特徵擷取方法計算出子區塊內各個像素點的特 徵值後將其統計成特徵直方圖，並將各區塊所對應的特徵直方圖加以串聯後，以 此作為該張影像之特徵資訊。實驗結果顯示，相較於其他人提出的方法，我們的 方法擁有較好的性別辨識率。
針對本論文提出的方法，主要的結論有：
1. 在步態性別辨識系統中，擷取步態影像的特徵是影響步態性別辨識系統
其效能最重要的一環。本論文提出先將步態影像經過 GEI 處理後再使 用區塊式 TPLZP 擷取影像的特徵，實驗結果證實我們所提方法可以獲 得良好的效果。
2. 為了證實我們所提方法之可行性，我們亦分別使用 CASIA dataset B 步 態資料庫中不同配件與不同角度的影像進行實驗，亦獲得不錯的辨識結 果。
因為性別辨識領域的蓬勃發展，有許多學者投入研究在特徵擷取之方法之改 良，未來可以嘗試將我們的方法在特徵維度上進行改良，降低運算與縮短訓練時 間；或是在第一階段的處理，將步態能量影像替換成其他步態影像描述技術；或 是在第二階段使用不同的圖樣來描述，以提升性別辨識系統之效能。
本篇論文皆是使用整張步態影像進行辨識，並沒有將局部的特徵，例如：步 伐大小、胸部或臀部等部位分別擷取出再進行測試，若局部辨識的辨識結果具有
45
良好的辨識率，則以此進行分析將會對性別辨識有更深的了解，或許可以降低特 徵擷取的時間。
在現實生活中，多數所拍攝的影像必定不會是 90 度或是無配件的行人，所 以我們未來可以多著重於其它幾度或是有佩戴配件的影響的分析與效能。
在實際應用層面，隨著科技的進步，無論在哪皆可廣泛地看到攝影裝置的設 立，例如：一般店家的攝影機、車上的行車紀錄器或 3C 產品上的相機等，若能 使步態性別辨識系統可以因此廣泛的被使用，將可大幅提高商業與科技發展，生 活亦趨便利。
46
參考文獻
[1] CASIA Gait Database, http://www.cbsr.ia.ac.cn/english/Gait%20Databases.asp.
[2] A. F. Bobick and J. W. Davis, “The recognition of human movement using temporal templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 257-267, 2001.
[3] X. Zhou and B. Bhanu, “Integrating face and gait for human recognition,” in Proc. Conference on Computer Vision and Pattern Recognition Workshop, 2006, p. 55.
[4] J. Han and B. Bhanu, “Individual recognition using gait energy image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 2, pp.
316-322, 2006.
[5] K. Balci and V. Atalay, “PCA for gender estimation: which eigenvectors contribute?” in Proc. IEEE International Conference on Pattern Recognition, vol.
3, 2002, pp. 363-366.
[6] J. Wu, “A novel approach for discrimination of human gait using kernel learning algorithm,” in Proc. IEEE 6th International Conference on Natural Computation, 2010, vol. 6, pp. 3253-3256.
[7] S. Yu, D. Tan, and T. Tan, “A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition,” in Proc. IEEE 18th International Conference on Pattern Recognition, 2006, vol. 4, pp. 441-444.
[8] D. Zhang, Y. Wang, and B. Bhanu, “Ethnicity classification based on gait using multi-view fusion,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2010, pp. 108-115.
[9] D. Zhang and Y. Wang, “Using multiple views for gait-based gender classification,” in Proc. IEEE Control and Decision Conference, 2014, pp.
2194-2197.
[10] Y. Wang, Y. Chen, H. Huang, and K. Fan, “Local block-difference pattern for use in gait-based gender classification,” Journal of Information Science and Engineering, vol. 31, no. 6, pp. 1993-2008, 2015.
[11] L. Zhang, R. Chu, S. Xiang, and S. Z. Li, “Face detection based on multi-block LBP representation,” in Proc. International Conference on Biometrics, 2007, pp.
11-18.
[12] L.-C. Fan, View-insensitive Gender Recognition Using Local Binary Patterns, Master thesis, Dept. Computer Science and Information Engineering, National Central Univ., Taoyuan, Taiwan, 2009.
[13] H.-C. Lian and B.-L. Lu, “Multi-view gender classification using local binary patterns and support vector machine,” in J. Wang et al. (Eds): ISNN 2006, LNCS
47
3972, pp. 202-209, 2006.
[14] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp.
971-987, 2002.
[15] H. H. Manap, N. M. Tahir, and A. I. M. Yassion, “Statistical analysis of parkinson disease gait classification using artificial neural network,” in Proc.
2011 IEEE International Symposium on Signal Processing and Information Technology, 2011, pp. 60-65.
[16] C. Shan, S. Gong, and P. W. McOwan, “Fusing gait and face cues for human gender recognition,” Neurocomputing, vol. 71, no. 10-12, pp. 1931-1938, 2008.
[17] C. Shan, S. Gong, and P. W. McOwan, “Learning gender from gaits and faces,”
in Proc. IEEE Conference on Advanced Video and Signal Based Surveillance, 2007, pp. 505-510.
[18] L. Lee and W. E. L. Grimson, “Gait analysis for recognition and classification,”
in Proc. 5th IEEE International Conference on Automatic Face and Gesture Recognition, 2002, pp. 148-155.
[19] A. Kale, A. K. Roychowdhury, and R. Chellappa, “Fusion of gait and face for human identification,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, 2004, p. V-901-4.
[20] A. J. O’Toole, T. Vetter, N. F. Troje, and H. H. Bulthoff, “Sex classification is better with three-dimensional head structure than with image intensity information,” Perception, vol. 26, no. 1, pp. 75-84, 1997.
[21] Q. Ma, S. Wang, D. Nie, and J. Qiu, “Recognizing humans based on gait moment image,” in Proc. IEEE 8th International Association for Computer and Information Science Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, 2007, vol. 2, pp. 606-610.
[22] S.-S. Lai, Human Identification Using Gait Features via Forward Difference History Image, Master thesis, Dept. Computer Science and Information Engineering, National Central Univ., Taoyuan, Taiwan, 2011.
[23] Weka-KNN: https://sourceforge.net/projects/weka-knn/.
[24] J. Lu, G. Wang, and T. S. Huang, “Gait-based gender classification in unconstrained environments,” in Proc. 21st International Conference on Pattern Recognition, 2012, pp. 3284-3287.
[25] S. Sarkar, P. Phillips, Z. Liu, I. Vega, P. Grother, and K. Bowyer, “The humanid gait challenge problem: data sets, performance, and analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 2, pp.
162-177, 2005.
48
[26] J. MacQueen, “Berkeley symposium on mathematical statics and probability,” in Proc. 5th Berkeley Symposium on Mathematical. Statistics and Probability, 1967, vol. 1, pp. 281-297.
[27] A. Sabir, N. Al-Jawad, S. Jassim, and A. Al-Talabani, “Human gait gender classification based on fusing spatio-temporal and wavelet statistical features,” in Proc. 5th Computer Science and Electronic Engineering Conference, 2013, pp.
140-145.
[28] D. Migliore, M. Mattucci, and M. Nacca, “A revaluation of frame difference in fast and robust motion detection,” in Proc. 4th ACM International Workshop on Video Surveillance and Sensor Networks, 2006, pp. 215-218.
[29] A. Sabir, N. Al-Jawad, and S. Jassim, “Gait recognition using spatio-temporal silhouette-based features,” in Proc. Mobile Multimedia/Image Processing, Security, and Applications, 2013, vol. 8755, pp. 1-10.
[30] Y.-J. Li, C.-C. Lai, C.-H. Wu, S.-T. Pan, and S.-J. Lee, “Gender classification from face images with local texture pattern,” International Journal of Industrial Electronics and Electrical Engineering, vol. 3, no. 11, pp. 15-17, 2015.
[31] L. Wolf, T. Hassner, and Y. Taigman, “Descriptor based methods in the wild,” in Proc. Faces in Real-Life Images Workshop at The European Conference on Computer Vision, 2008, pp. 1-14.
[32] L. Wolf, T. Hassner, and Y. Taigman, “Effective unconstrained face recognition by combining multiple descriptors and learned background statistics,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 10, pp.
1978-1990, 2011.
[33] G. Mahalingam and K. Ricanek Jr., “LBP-based periocular recognition on challenging face datasets,” EURASIP Journal on Image and Video Processing, vol. 2013, no. 36, pp. 1-13, 2013.
[34] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 1999, pp. 246-252.
[35] R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti, “Detecting moving objects, ghosts, and shadows in video streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1337-1342, 2003.
[36] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in Proc. The 5th Annual Workshop on Computational Learning Theory, 1992, pp.144-152.
[37] C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A practical guide to support vector classification,” Technical report, Dept. of Computer Science, National Taiwan Univ., Taipei, Taiwan, 2003.
49
[38] B. Luo, Y. Zhang, and Y.-H. Pan, “Face recognition based on wavelet transform and SVM,” in Proc. IEEE Conference on Information Acquisition, 2005, pp.
373-377.
[39] G. Guo, S. Z. Li, and K. Chan, “Face recognition by support vector machines,”
in Proc. 4th IEEE International Conference on Automatic Face and Gesture Recognition, 2000, pp. 196-201.
[40] http://mklab.iti.gr/project/GPU-LIBSVM [41] https://www.python.org/downloads/
[42] http://www.gnuplot.info/
[43] C.-C. Chang and C.-J. Lin, LIBSVM: a library for support vector machines.
Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001.
[44] R. Martin-Felez, R. A. Mollineda, and J. S. Sanchez, “A gender recognition experiment on the CASIA gait database dealing with its imbalanced nature,” in Proc. International Conference on Computer Vision Theory and Applications, 2010, vol. 2, pp. 439-444.
[45] C.-Y. Chang and T.-H. Wu, “Using gait information for gender recognition,” in Proc. 10th International Conference on Intelligent Systems Design and Applications, 2010, pp. 1388-1393.
[46] J. Lu and Y. P. Tan, “Uncorrelated discriminant simplex analysis for view-invariant gait signal computing,” Pattern Recognition Letters, vol. 31, no. 5, pp. 382-393, 2010.
[47] K. Arai and R. A. Asmara, “Human gait gender classification using 2D discrete wavelet transforms energy,” International Journal of Computer Science and Network Security, vol. 11, no. 12, pp. 62-68, 2011.
[48] R. Matin-Felez, R. A. Mollineda, and J. S. Sanchez, “Towards a more realistic appearance-based gait representation for gender recognition,” in Proc. 20th International Conference on Pattern Recognition, 2010, pp. 3810-3813.
[49] S. Yu, T. Tan, K. Huang, K. Jia, and X. Wu, “A study on gait-based gender classification,” IEEE Transactions on Image Processing, vol. 18, no. 8, pp.
1905-1910, 2009.
[50] A. Sabir, N. Al-Jawad, S. Jassin, and A. Al-Talabani, “Human gait gender classification based on fusing spatio-temporal and wavelet statistical features,” in Proc. 5th Computer Science and Electronic Engineering Conference, 2013, pp.
140-145.