請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/25292
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 貝蘇章 | |
dc.contributor.author | Heng-Ta Jen | en |
dc.contributor.author | 任恆達 | zh_TW |
dc.date.accessioned | 2021-06-08T06:07:59Z | - |
dc.date.copyright | 2007-07-26 | |
dc.date.issued | 2007 | |
dc.date.submitted | 2007-07-16 | |
dc.identifier.citation | Chapter 1
[1-1] B.V.K. Vijaya Kumar, M. Savvides, and C. Xie, “Correlation Pattern Recognition for Face Recognition,” in Proceedings of the IEEE, Vol. 94, No. 11, pp. 1963-1976, November 2006 Chapter 2 [2-1] A. Mahalanobis, B.V.K. Vijaya Kumar, and K. Casasent, “Minimum average correlation energy filter,” Appl. Opt. 26, 3633-3640(1986) [2-2] D. Casasent, “Unified Synthetic Discriminant Function Computational Formulation,” Appl. Opt. 23, 1620 (1984) [2-3] B.V.K Vijaya Kumar, “Minimum Variance Synthetic Discriminant Functions,” J. Opt, Soc. Am A 3, 1579 (1986) [2-4] Carnegie Mellon University Advanced Multimedia Processing Lab’s facial expression database, http://amp.ece.cmu.edu/downloads.htm [2-5] T. Sim, S. Baker, and M. Bsat, “The CMU Pose, Illumination, and Expression (PIE) Database of Human Faces,” Robotics Institute, Carnegie Mellon University, Tech. Rep. CMU-RI-TR-01-02, 2001 [2-6] M. Savvides and B.V.K. Vijaya Kumar and P.K. Khosla, “Robust, Shift-Invariant Biometric Identification from Partial Face Images”, accepted for publication in Biometric Technologies for Human Identification (OR51) 2004 [2-7] J.L. Horner and P.D. Gianino, “Phase-Only Matched Filtering,” Appl. Opt. 23, 812 (1984) Chapter 3 [3-1] A. Mahalanobis, B.V.K. Vijaya Kumar, S.R.F. Sims, and J.F. Epperson, “Unconstrained correlation filters,” Appl. Opt., Vol.33, pp. 3751-3759 (1994) [3-2] J. L. Horner and P. D. Gianino, “Phase-only matched filtering,” Appl. Opt. 23, 2324-2335 (1984) [3-3] A. Mahalanobis and D. Casasent, “Performance evaluation of minimum average correlation energy filters,” Appl. Opt. 30, 561-572 (1991) Chapter 4 [4-1] P.J. Phillips, P.J. Flynn, T. Scruggs, K.W. Bowyer, J. Chang, K. Hoffman, J. Min, and W. Worek, “Overview of the Face Recognition Grand Challenge,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2005 [4-2] Chee Kiat Ng, M. Savvides, and P.K. Khosla, “Real-Time Face Verification System on a Cell-Phone using Advanced Correlation Filters,” in IEEE AUTOID, pp.57-62, 2005 [4-3] M. Savvides, B.V.K. Vijaya Kumar and P.K. Khosla, “Efficient Boosting for Synthesizing a Minimally Compact Reduced Complexity Correlation Filter Bank for Biometric Identification,” IEEE, 587-591, 2004 [4-4] M. Savvides, K. Venkataramani and B.V.K. Vijaya Kumar, “Incremental Updating of Advanced Correlation Filter Designs,” International Conference on Multimedia and Expo, Special Session on Signal Processing and Multimodal Biometric Verification, 2003 [4-5] M. Savvides, B.V.K. Vijaya Kumar and P.K. Khosla, “Cancelable Biometric Filters for Face Recognition,” accepted for publication in ICPR 2004 [4-6] C. Xie, M. Savvides, and B.V.K. Vijaya Kumar, “Redundant Class-Dependence Feature Analysis Based on Correlation Filters Using FRGC20.Data,” Proc. of IEEE Computer Vision and Pattern Recognition (CVPR)-Workshops, Vol 3, San Diego, June 2005 [4-7] C. Xie, M. Savvides, and B.V.K. Vijaya Kumar, “Kernel Correlation Filter Based Redundant Class-Dependence Feature Analysis (KCFA) on FRGC2.0 data,” in Proc. 2nd Int. Workshop Analysis Modeling of Faces Gestures (AMFG 2005) Held in Conjunction With ICCV 2005, Beijing, 2005 [4-8] J. Heo, M. Savvides, R. Abiantun, C. Xie and B.V.K. Vijaya Kumar, “Face Recognition with Kernel Correlation Filters on a Large Scale Database,” in ICASSP, pp.181-184, 2006 [4-9] M. Savvides, J. Heo, R. Abiantun, C. Xie and B.V.K. Vijaya Kumar, “Class Dependent Kernel Discrete Cosine Transform Features for Enhanced Holistic Face Recognition in FRGC-II,” in ICASSP, pp.185-188, 2006 Chapter 5 [5-1] K.H. Jeong, P.P. Pokharel, J. Xu, S. Han, and J.C. Principe, “The Correntropy MACE Filter for Image Recognition,” in PROC. IEEE Int. Workshop on Machine Learning for signal Processing (MLSP), France, July 2006, pp. 9-14 [5-2] I. Santamaria, P.P. Pokharel, and J.C. Principe, “Generalized correlation function: Definition, properties and application to blind equalization,” IEEE Trans. Signal Processing, vol. 54, no. 6, pp. 2187-2197, June 2006 [5-3] P.P. Pokharel, J.W. Xu, D. Erdogmus, and J.C. Principe, “A Closed Form Solution for a Nonlinear Wiener Filter,” in Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), France, May 2006, vol. 3, pp. 720-723. [5-4] L. Greengard and J. Strain, “The Fast Gauss Transform,” SIAM J. Sci. Statist. Comput., vol. 12, no. 1, pp. 79-94, Jan. 1991 [5-5] K.H. Jeong, S. Han, J.C. Principe, “The Fast Correntropy MACE Filter,” in ICASSP, pp. 613-616, 2007 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/25292 | - |
dc.description.abstract | 最小平均相關能量濾波器很常應用於影像辨識系統。當用來訓練濾波器的影像經過適當的選擇,我們可以得到滿意的辨識率。然而我們知道最小平均相關能量濾波器的效能對於失真非常敏感,因此我們利用滿足某些特定的條件來最佳化濾波器的效能、而不使用嚴格的限制。為了避免多於不必要的影像來訓練濾波器,而浪費記憶體和運算量,在這篇論文我們提供一個演算法可以自動從資料庫裡找尋最適合拿來訓練濾波器的影像。另外基於安全和隱私因素,我們必須把加密功能加入我們的濾波器設計中,避免資料被盜用的可能,然後我們會證明使用的加密功能並不會影響到辨識能力。最後為了處理資料量龐大的情形跟人臉的非線性變形,我們使用種類相關的特徵分析跟使用更高維的資料訊息來做相關性。整合這些技術,我們將濾波器改良的更可以克服現實生活當中可能產生的問題。 | zh_TW |
dc.description.abstract | The minimum average correlation energy (MACE) filter is a well known correlation filter for pattern recognition. The recognition rates will be attractive while choosing the training images properly. But the MACE filter is sensitive to the distortion, thus we optimize the filter by removing the hard constraint and satisfying certain criterion, which is so-called unconstrained correlation filter. In order to avoid redundant training images, here we provide an algorithm to automatically choose the proper training images from a dataset. For security issue, we also use encryption method in the filter design and we will show that the encryption process do not affect the recognition performance. Finally for the large scale database and the nonlinear distortion in human face, we improve the recognition performance by using class-dependent feature analysis and correntropy function, where correntropy is a positive definite function that generalizes the concept of correlation by utilizing higher order moment information of signal structure. Using these technologies, we can make the filter more practical in real application. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T06:07:59Z (GMT). No. of bitstreams: 1 ntu-96-R94942101-1.pdf: 1313393 bytes, checksum: c7188bf03c02bf8a61e08f19c1654ec4 (MD5) Previous issue date: 2007 | en |
dc.description.tableofcontents | Chapter 1 Introduction 1
Chapter 2 Minimum Average Correlation Energy Filter 5 2.1 Introduction 5 2.2 Notation 5 2.3 Problem Definition 6 2.4 Solution 8 2.5 Properties of MACE Filter 10 2.6 The Fitness Metric of MACE Filter 13 2.7 Experiments 13 2.8 Conclusion 20 Chapter 3 Unconstrained Correlation Filter 21 3.1 Introduction 21 3.2 Notation 21 3.3 Derivation of the Filter Equation 22 3.3.1 Unconstrained Minimum Average Correlation Energy (MACE) Filter 23 3.3.2 Maximum Average Correlation Height (MACH) Filter 24 3.3.3 Generalized MACH (GMACH) Filter 30 3.4 Relation Between Maximum Average Correlation Height, minimum-Squared-Error Synthetic Discriminant Function, and Minimum Average Correlation Energy Filter 31 3.5 Optimal Trade-Off Design of Minimum-Average Correlation Height Filter 33 3.6 Amplitude-Normalized Filter Design 34 3.7 Experiments 36 3.8 Conclusion 38 Chapter 4 Face recognition on a large scale database with cancelable correlation filter 39 4.1 Introduction 39 4.2 Background Knowledge of Correlation Filter 39 4.3 How to Choose the Proper Training Set 40 4.3.1 Algorithm 41 4.3.2 Simulation Result 42 4.4 Cancelable Correlation Filter 44 4.4.1 Structure of the Cancelable Correlation Filter 44 4.4.2 PSR invariance to arbitrary convolution kernels 47 4.4.3 Experiment and Simulation 49 4.5 Redundant Class-dependence Feature Analysis 49 4.6 Kernel Correlation Filters 55 4.7 Conclusion 57 Chapter 5 The Correntropy MACE Filter 59 5.1 Introduction 59 5.2 Notation 60 5.3 Derivation of the Correntropy MACE Filter 60 5.4 CFA using Correntropy MACE Filter 63 5.5 Conclusion 64 Chapter 6 Conclusions and Future Work 65 Reference 67 | |
dc.language.iso | en | |
dc.title | 相關濾波器適用於人臉辨識之設計與應用 | zh_TW |
dc.title | Face Recognition Using Correlation Filters | en |
dc.type | Thesis | |
dc.date.schoolyear | 95-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林康平,黃文良,丁建均 | |
dc.subject.keyword | 相關濾波器,人臉辨識,種類相關特徵分析,非線性失真,相關墒, | zh_TW |
dc.subject.keyword | correlation filter,face recognition,class-dependent feature analysis (CFA),kernel trick,nonlinear distortion,correntropy, | en |
dc.relation.page | 71 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2007-07-18 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-96-1.pdf 目前未授權公開取用 | 1.28 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。