臺灣博碩士論文加值系統

生物辨識可以藉由生物獨特的幾何特性或行為特徵來辨識物件的身份，包含人臉辨識、虹膜辨識、指紋辨識、手寫辨識、靜脈辨識、掌形辨識與步態辨識。上述的生物辨識大多需要與使用者近距離的接觸取得影像資訊與特徵或特殊擷取裝置才可以進行身份比對，但步態辨識僅需藉由攝影機從遠距離擷取出影像，即可進行身份比對。步態辨識是一個新興的生物辨識技術，可藉由每個人行走模式的不同去進行身份辨識，且可從遠距離擷取資訊，因此步態辨識漸漸成為一個熱門的生物辨識技術。在這篇論文當中，我們提出了一個新的方法來描述步態特徵，這個新方法是基於局部二元特徵延伸而出，我們改變了局部二元特徵原本的排序方式，並依照影像上漸層的方向而有不同的排序方式，我們稱為條件式排序的局部二元特徵。我們將條件式排序的局部二元特徵應用在步態能量影像上，經由條件式排序的局部二元特徵轉換後的影像即為新的特徵影像，之後使用此一新特徵來進行步態辨識，並提出選取其特徵方式。從本篇論文的研究結果中，我們所提出的特徵描述方法能夠有效的應用在步態辨識中，比其他現有的文獻還要有更高的辨識結果。

Biometric identification techniques allow the identification of a person according to some geometric or behavioral traits that are uniquely associated with him or her. Commonly used biometrics are face, iris, fingerprints, handwriting, pal, vena and gait. An important limitation of most contemporary biometric identification system is related to the fact that they require the cooperation of individual that is to be identified and some special capturing devices. Gait recognition is an emerging biometric technology which aims to identify individuals using their walking style. The apparent advantage of gait recognition in comparison to other biometrics is that it doesn’t require the attention or cooperation of the observed subject. This work proposes a new feature extraction method for gait representation and recognition. The new method is extended from the technique of Local Binary Pattern (LBP) by changing the sorting method of LBP according to the blend direction to create a new approach, Conditional-Sorting Local Binary Pattern (CS-LBP). We then apply the CS-LBP on GEI to derive different blend direction images and calculate the recognition ability for each blend direction image for feature selections. From the experimental result, we proposed a new feature description method which can be effectively applied in gait recognition, also has a higher recognition results than other existing literature.

中文摘要 ..................................................................................................... I
英文摘要 .................................................................................................... II
內文目錄 ................................................................................................... III
圖目錄 ........................................................................................................ V
表目錄 .................................................................................................... VIII
第一章 緒論 ........................................................................................... 1
1.1 研究動機 ................................................................................... 1
1.2 流程與系統架構 ....................................................................... 2
1.3 論文架構 ................................................................................... 3
第二章 相關研究 ................................................................................... 4
2.1 Model-based 步態特徵 ........................................................... 4
2.2 Appearance-based 步態特徵 .................................................. 6
第三章 相關技術 ................................................................................. 12
3.1 移動物件偵測 ......................................................................... 12
3.1.1 背景模型建立 ................................................................12
3.1.2 前景偵測 ........................................................................17
IV
3.2 週期偵測 ................................................................................. 18
3.3 步態能量影像(Gait Energy Image) ...................................... 19
3.4 局部二元特徵(Local Binary Pattern) .................................. 23
3.5 影像降維度 ............................................................................. 25
3.5.1 主成份分析(Principle Component Analysis, PCA) ...25
3.5.2 線性識別分析(Linear Discriminant Analysis, LDA) 28
第四章 步態辨識使用CS-LBP .......................................................... 33
4.1 CS-LBP ................................................................................... 33
4.2 CS-LBP 特徵選擇 .................................................................. 54
第五章 實驗結果與討論 ..................................................................... 57
5.1 資料庫介紹 ............................................................................. 57
5.2 身份辨識實驗 ......................................................................... 59
5.3 CS-LBP 特徵選取實驗 .......................................................... 60
第六章 結論 ......................................................................................... 66
參考文獻 (References) ...........................................................................67

V
圖目錄
圖2.1 人體模型 ........................................................................................ 5
圖2.2 使用橢圓形來描述人體模型[4] .................................................... 6
圖2.3 使用關節旋選角度來當作特徵 .................................................... 6
圖2.4 步態能量影像 ................................................................................ 8
圖2.5 移動剪影影像 ................................................................................ 9
圖2.6 Width Vector Mean .......................................................................... 9
圖2.7 Frieze Pattern ................................................................................. 10
圖2.8 Frieze Pattern 與Key Frame ......................................................... 10
圖2.9 SEI 影像......................................................................................... 11
圖2.10 AEI 影像 ...................................................................................... 11
圖3.1 色彩分佈模型 .............................................................................. 16
圖3.2 一個週期的步態影像 .................................................................. 19
圖3.3 步態能量示意圖 .......................................................................... 21
圖3.4 不同情況下的GEI ....................................................................... 22
圖3.5 不同步態表示法 .......................................................................... 23
圖3.6 GEI 影像使用LBP ....................................................................... 24
圖4.1 GEI 影像使用JET 能量圖表達 ................................................... 36
VI
圖4.2 區塊圖........................................................................................... 36
圖4.3 CS-LBP 排序示意圖 ..................................................................... 37
圖4.4 CS-LBP 說明 ................................................................................. 38
圖4.5 不同半徑的LBP .......................................................................... 41
圖4.6 不同半徑的CS-LBP .................................................................... 42
圖4.7 不同半徑區塊圖 .......................................................................... 42
圖4.8 半徑為2 的CS-LBP 排序方式 ................................................... 43
圖4.9 半徑為3 的CS-LBP 排序方式 ................................................... 44
圖4.10 資料庫1 號物件的GEI 影像使用半徑為1 的CS-LBP ......... 45
圖4.11 資料庫97 號物件的GEI 影像使用半徑為1 的CS-LBP ....... 46
圖4.12 資料庫85 號物件的GEI 影像使用半徑為1 的CS-LBP ....... 47
圖4.13 資料庫1 號物件的GEI 影像使用半徑為2 的CS-LBP ......... 48
圖4.14 資料庫97 號物件的GEI 影像使用半徑為2 的CS-LBP ....... 49
圖4.15 資料庫85 號物件的GEI 影像使用半徑為2 的CS-LBP ....... 50
圖4.16 資料庫1 號物件的GEI 影像使用半徑為3 的CS-LBP ......... 51
圖4.17 資料庫97 號物件的GEI 影像使用半徑為3 的CS-LBP ....... 52
圖4.18 資料庫85 號物件的GEI 影像使用半徑為3 的CS-LBP ....... 53
圖4.19 八個漸層方向的辨識能力 ........................................................ 56
圖5.1 CASIA-B 資料庫設計示意圖 ...................................................... 58
VII
圖5.2 不同狀況下的行走情形 .............................................................. 58
圖5.3 選取不同數量漸層方向的辨識結果 .......................................... 61
圖5.4 辨識率與辨識能力比較 ..............................................................64

表目錄
表5.1 在CASIA-B 資料庫的辨識率 .................................................... 59
表5.2 在CASIA-B 資料庫的平均辨識率比較 .................................... 60
表5.3 辨識率與辨識能力 ...................................................................... 64
表5.4 辨識率與辨識能力排序結果 ...................................................... 65

[1]URL: http://www.darpa.mil/
[2]Liang Wang, Huazhong Ning, Tieniu Tan, and Wwiming Hu, “Fusion of Static and Dynamic Body Biometrics for Gait Recognition,” IEEE Transaction on Circuits and Systems for Video Technology, vol. 14, no. 2, pp. 149-158, Feb. 2004.
[3]Imed Bouchrika and Mark S. Nixon, “Model-Based Feature Extraction for Gait Analysis and Recognition,” Proceedings of Mirage: Computer Vision / Computer Graphics Collaboration Techniques, pp. 150-160, May 2007.
[4]L. Lee and W. E. L. Grimson, “Gait Analysis for Recognition and Classification,” IEEE International Conference on Automatic Face and Gesture Recognition, pp.148-155, May 2002.
[5]David Cunado, Mark S. Nixon, and John N. Carter, “Automatic Extraction and Description of Human Gait Models for Recognition purposes,” Computer Vision and Image Understanding, vol. 90, no. 1, pp. 1–41, Mar. 2003.
[6]Liang Wang, Tieniu Tan, Huazhong Ning, and Weiming Hu, “Silhouette Analysis-based Gait Recognition for Human Identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 12, pp. 1505- 1518, Dec. 2003.
[7]Dong Xu, Shuicheng Yan, Dacheng Tao, Lei Zhang, Xuelong Li, and Hong-Jiang Zhang, “Human Gait Recognition with Matrix Representation,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 16, no. 7, pp. 896-903, Jul. 2006.
[8]Ju Han and Bir Bhanu, “Individual Recognition using Gait Energy Image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 2, pp. 316-322, Feb. 2006.
[9]Toby H. W. Lam and Raymond S.T. Lee, “A New Representation for Human Gait Recognition: Motion Silhouettes Image (MSI),” International Conference on Biometrics, pp. 612–618, 2006.
[10]Sungjun Hong, Heesung Lee, and Euntai Kim, “Automatic Gait Recognition using Width Vector Mean,” IEEE Conference on Industrial Electronics and Applications, pp. 647-650, May 2009.
[11]Yanxi Liu, Robert Collins, and Yanghai Tsin, “Gait Sequence Analysis using Frieze Patterns,” European Conference on Computer Vision, pp. 733-736, May 2002.
[12]Bing Sun, Junchi Yan, and Yuncai Liu, “Human Gait Recognition by Integrating Motion Feature and Shape Feature,” International Conference on Multimedia Technology, pp. 1-4, Oct. 2010.
[13]Xiaxi Huang and Nikolaos V. Boulgouris, “Gait Recognition with Shifted Energy Image and Structural Feature Extraction,” IEEE Transactions on Image Processing, vol. 21, no.4, pp. 2256-2268, Apr. 2012.
[14]Erhu Zhang, Yongwei Zhao, and Wei Xiong, “Active Energy Image Plus 2DLPP for Gait Recognition,” Signal Processing, vol. 90, no. 7, pp. 2295-2302, July 2010.
[15]Kyungnam Kim, Thanarat H. Chalidabhongse, David Harwood, and Larry Davis, “Real-time Foreground-background Segmentation using Codebook model,” Real-Time Imaging, vol. 11, no. 3, pp. 172-185, Jun. 2005.
[16]Sudeep Sarkar, P. Jonathon Phillips, Zongyi Liu, Isidro Robledo Vega, Patrick Grother, and Kevin W. 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, Feb. 2005.
[17]Aaron F. Bobick and James W. Davis, “The Recognition of Human Movement using Temporal Templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, Mar. 2001.
[18]Timo Ojala, Matti Pietikainen, and Topi 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, Jul. 2002.
[19]Timo Ahonen, Abdenour Hadid, and Matti Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, Dec. 2006.
[20]Di Huang, Caifeng Shan, Mohsen Ardabilian, Yunhong Wang, and Liming Chen, “Local Binary Patterns and Its Application to Facial Image Analysis: A Survey,” IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 41, no. 6, pp. 765-781, Nov. 2011
[21]Zhenhua Guo, Lei Zhang, and David Zhang, “A Completed Modeling of Local Binary Pattern Operator for Texture Classification,” IEEE Transactions on Image Processing, vol. 19, no. 6, pp. 1657-1663, Jun. 2010.
[22]Peter N. Belhumeur, Joao P. Hespanha, and David J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, Jul. 1997.
[23]Matthew A. Turk and Alex P. Pentland, “Face Recognition using Eigenfaces,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586-591, Jun. 1991.
[24]Shiqi Yu, Daoliang Tan, and Tieniu Tan, “A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition,” Conference on Pattern Recognition, vol. 4, pp.441-444, Aug. 2006
[25]Yasushi Makihara, Ryusuke Sagawa, Yasuhiro Mukaigawa, Tomio Echigo, and Yasushi Yagi, “Which Reference View is Effective for Gait Identification Using a View Transformation Model?,” Conference on Computer Vision and Pattern Recognition Workshop, pp. 45, Jun. 2006.
[26]Khalid Bashir, Tao Xiang, and Shaogang Gong, “Gait Recognition without Subject Cooperation,” Pattern Recognition Letters, vol. 31, no. 13, pp. 2052-2060, Jun. 2010.