簡易檢索 / 詳目顯示

回結果列表
研究生： 林子皓
Lin, Tzu-Hao
論文名稱： 基於局部外觀基礎方法的人臉驗證之研究
A Study on Face Verification with Local Appearance-Based Methods
指導教授： 陳朝欽
Chen, Chaur-Chin
口試委員: 張隆紋
Chang, Long-Wen
黃仲陵
Huang, Chung-Lin
學位類別： 碩士
Master
系所名稱：
論文出版年： 2018
畢業學年度： 106
語文別： 英文
論文頁數： 30
中文關鍵詞： 人臉辨識 、人臉驗證 、局部外觀基礎方法 、梯度方向金字塔 、局部二值模式 、二分複小波轉換
外文關鍵詞： Face Recognition, Face Verification, Local Appearance-Based Method, Gradient Orientation Pyramid, Local Binary Pattern, Dual Tree-Complex Wavelet Transform
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 近年來，由於在大眾媒體中不斷出現的充滿美好幻想的應用情境逐漸地走向現實世界，人臉辨識也愈來愈受到全世界人們的關注。在兩種人臉辨識的模式中，人臉驗證(Verification)比起人臉識別(Identification)更為簡單也更適合像身分認證等實際應用上。為了更鉅細靡遺地描述人類臉部所包含的資訊，在各式各樣的人臉辨識方法中我們偏好於選擇局部外觀基礎的方法(local appearance-based methods)。
    在本論文中，我們研讀了三種局部外觀基礎的方法: 梯度方向金字塔臉(GOP-Face)、局部二值模式臉(LBP-Face)以及複數小波轉換臉(DT-CWT-Face)，並且嘗試對於這三種方法給出簡單又詳盡的概述。此外，我們採用了最近鄰居法(k nearest neighbor)並運用人臉驗證在 ORL、Yale以及FERET等資料庫上來實驗這些方法對於像是空間位移、照度變化和年齡進展等臉部變因的穩固性。結果顯示LBP-Face以及DT-CWT-Face確實在空間位移上有著較佳的穩固性，而DT-CWT-Face對於年齡進展有驚人的表現更勝於GOP-Face。然而，他們對於照度變化的效果卻不如預期。

    In recent years, due to the fantastic applications revealed in the mass media are progressively walking out to the reality, face recognition is getting more and more attention to people all over the world. Between the two modes of face recognition, verification is simpler and more suitable than identification in some practical applications such as authentication. To describe the information in human faces more elaborately, we prefer the local appearance-based methods among the various face recognition approaches.
    In this thesis, we studied three local appearance-based methods: GOP-Face (Gradient Orientation Pyramid), LBP-Face (Local Binary Pattern) and DT-CWT-Face (Dual Tree-Complex Wavelet Transform), and tried to give a clear overview of these three methods. Furthermore, we use face verification to experiment their robustness to variations like spatial shift, illumination changes and age progression on the ORL, Yale and FERET databases with k nearest neighbor classifier. The results verified that LBP-Face and DT-CWT-Face are actually more robust to the spatial shift and DT-CWT-Face is surprisingly robust to age progression, and is even better than GOP-Face. However, the performance against illumination change is not as good as expected.

    Table of Contents Chapter 1 Introduction 1 Chapter 2 Background Review 4 2.1 Preparation of GOP-Face 4 2.1.1 Image Gradient 4 2.1.2 Gaussian Pyramid 5 2.2 Preparation of LBP-Face 6 2.2.1 Original LBP 6 2.2.2 Extended LBP 6 2.2.3 Uniform Pattern and Histogram 7 2.3 Preparation of DT-CWT-Face 8 2.3.1 Dual Tree-Complex Wavelet Transform 8 2.3.2 Wavelet Bases 10 Chapter 3 Face Representation 11 3.1 GOP-Face [Ling2010] 12 3.2 LBP-Face [Ahon2006] 14 3.3 DT-CWT-Face [Liu2009] 16 Chapter 4 Experiments 18 4.1 Databases 18 4.1.1 The ORL Database 18 4.1.2 The Cropped Extended Yale Face Database B 19 4.1.3 The Color FERET Database 19 4.2 Setup and Results 20 4.2.1 Experiments on the ORL Database 21 4.2.2 Experiments on the Cropped Extended Yale Database B 23 4.2.3 Experiments on the FERET Database 25 Chapter 5 Conclusion and Future Work 27 Appendix 28 References 29

    [Abde2001] A.F. Abdelnour and I.W. Selesnick, “Nearly Symmetric Orthogonal Wavelet Bases,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), Vol. 27, No. 6, 625-637, 2001.

    [Ahon2006] T. Ahonen, A. Hadid, and M. Pietika¨inen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Trans. Pattern Anal. Machine Intell., Vol. 28, No. 12, 2037-2041, 2006.

    [Chen2000] H. Chen, P. Belhumeur, and D. Jacobs, “In Search of Illumination Invariants,” in IEEE Conf. Computer Vision and Pattern Recognition(CVPR), Vol. 1, 254-261, 2000.

    [Geor2001] A. Georghiades, P. Belhumeur, D. Kriegman, “From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, 643-660, 2001.

    [King1999] N.G. Kingsbury. “Image Processing with Complex Wavelets,” Phil. Trans. Royal Society London A, Math. Phys. Sci., Vol. 357, No. 1760, 2543–2560, 1999.

    [King2001] N.G. Kingsbury, “Complex wavelets for shift invariant analysis and filtering of signals,” Appl. Comput. Harmon. Anal., Vol. 10, No. 3, 234–253, 2001.

    [Lee2005] K. Lee, J. Ho, D. Kriegman, “Acquiring Linear Subspaces for Face Recognition under Variable Lighting,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 27, No. 5, 684-698, 2005.

    [Ling2007] H. Ling, S. Soatto, N. Ramanathan, and D.W. Jacobs, “A Study of Face Recognition as People Age,” in Proc. Int. Conf. Computer Vision(ICCV), 1-8 2007.

    [Ling2010] H. Ling, S.Soatto, N. Ramanathan, and D.W. Jacobs, “Face Verification Across Age Progression Using Discriminative Methods, ” IEEE Trans. Inf. Forensics Security, Vol. 5, No. 1, 82-91, 2010.

    [Liu2009] C.C. Liu, D.Q. Dai, “Face Recognition Using Dual-Tree Complex Wavelet Features,” IEEE Trans. Image Process., Vol.18, No. 11, 2593-2599, 2009.

    [Ojal1996] T. Ojala, M. Pietikäinen, and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Feature Distributions,” Pattern Recognition, Vol. 29, No. 1, 51-59, 1996.

    [Ojal2002] T. Ojala, M. Pietika¨inen, and T. Ma¨enpa¨a¨, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, 971-987, 2002.

    [Phil2000] P.J. Phillips, H. Moon, S.A. Rizvi, P.J. Rauss, "The FERET Evaluation Methodology for Face Recognition Algorithms," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 22, 1090-1104, 2000.

    [Sama1994] F.S. Samaria, and A.C. Harter, “Parameterisation of a Stochastic Model for Human Face Identification,” The Second IEEE Workshop on Applications of Computer Vision, 138-142, 1994.

    [Sele2005] I.W. Selesnick, R.G. Baraniuk, and N.G. Kingsburg, “The dual-tree complex wavelet transform-a coherent framework for multiscale signal and image processing,” IEEE Signal Process. Mag., Vol. 22, No. 6, 123-151, 2005.

    [Zhan2004] G. Zhang, X. Huang, S.Z. Li, Y. Wang, and X. Wu, “Boosting Local Binary Pattern (LBP)-Based Face Recognition,” Proc. Advances in Biometric Person Authentication, 179-186, 2004.

    [Web01] http://eeweb.poly.edu/iselesni/WaveletSoftware/dt1D.html, last access on May 28, 2018.

    [Web02] https://www.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-system-object.html#d119e66688, last access on May 28, 2018.

    QR CODE