2.3.5 Approaches for Face Recognition across Pose and Illumination
2.4 Summary
3 Facial Representation
3.1 Introduction
3.2 Pixel-based Facial Features
3.3 Fourier-Based Facial Features
3.4 Cosine-Based Facial Features
3.5 Gabor-Based Facial Features
3.6 Haar-like Features
3.7 Local Pattern-Based Facial Features
3.7.1 Local Binary Patterns
3.7.2 Generic Local Binary Patterns
3.7.3 Local Ternary Patterns
3.7.4 Invariants of Local Binary Patterns
3.7.5 Multi-scale Local Binary Patterns
3.7.6 Multi-Scale Block Local Binary Patterns
3.8 Complex Facial Representations
3.9 My Proposed Robust Multi-Scale Block Local Binary Patterns
3.10 My Proposed Compact Histogram Representation
3.11 Summary
4 Face Detection
4.1 Description of Face Detection System
4.2 Neural Networks
4.2.1 Overview
4.2.2 Neural Network-Based Classification
4.2.3 Neural Network-Based Face Detection
4.3 AdaBoost Algorithm
4.3.1 AdaBoost-Based Face Detection
4.3.2 Face Detection Using Cascade Structure of Boosted Classifiers
4.4 My Proposed Hybrid Approach for Face Detection
4.4.1 Structure of Hybrid Face Detector
4.4.2 Applying to Face Detector
4.5 Summary
5 Distance Learning for Face Recognition
5.1 Description of Face Recognition System
5.2 Face Recognition Using Principal Component Analysis
5.3 Face Recognition Using Probabilistic PCA
5.4 Face Recognition Using Two-Dimensional PCA
5.5 Face Recognition Using LDA
5.6 Proposed Face Recognition Using Bayesian Learning
5.6.1 Bayesian Decision Theory
5.6.2 Bayesian Learning
5.6.3 Extended Bayesian Learning
5.7 My Proposed Face Recognition Using LBP
5.7.1 LBP-Based Face Recognition Framework
5.7.2 Distances to Measure Similarities of Histograms
5.7.3 Feature Transformation
5.7.4 Implementation of Computing Similarity/Dissimilarity Scores
5.8 Summary
6 Relation Learning for Face Recognition
6.1 Introduction
6.2 Face Recognition Using Support Vector Machine
6.2.1 Support Vector Machine
6.2.2 SVM-Based Face Recognition
6.3 Proposed Face Recognition Using Relation Learning
6.3.1 Theory of Relation Learning
6.3.2 Algorithm of Relation Learning
6.3.3 Relation Learning-Based Face Recognition
6.4 Summary
7 Experiments
7.1 Introduction
7.2 Databases
7.3 Performance Measures
7.3.1 Introduction to Evaluation Protocol
7.3.2 Performance Measures in Face recognition
7.3.3 Testing Protocol
7.3.4 Performance Measures in Face Detection
7.4 Experiments on Face Detection
7.4.1 AdaBoost and Neural Network-Based Face Detection System
7.4.2 Hybrid Models of AdaBoost and Neural Network
7.5 Experiments on Gender Classification
7.5.1 Database and Experiment Setup
7.5.2 Comparisons of Facial Representation Methods
7.5.3 Comparisons of Dimension Reduction Methods
7.5.4 Comparisons of Classification Methods
7.6 Experiments on Face Recognition
7.6.1 Global and Local Facial Representations
7.6.2 Gabor-Based Facial Representations
7.6.3 Local Pattern-Based Facial Representations
7.6.4 Complex Facial Representation
7.6.5 Fusion Classifiers
7.6.6 Distance Learning
7.6.7 Extended Bayesian Learning
7.6.8 Relation Learning
7.7 Summary
8 Conclusions and Suggestions for Future Work
8.1 Conclusions
8.2 Future Work
Bibliography
Nội dung
A thesis submitted for the degree of Doctor of Philosophy at The University of Canberra FACE RECOGNITION USING LOCAL PATTERNS AND RELATION LEARNING Len Bui January, 2013 Summary of Thesis The study area of this thesis is face recognition, one of the important fields in computer vision Although face recognition has recently achieved many advances, the process is still not able to meet the accuracy requirements of many applications that are affected by variations in pose and illumination The aim of this thesis is to develop a more advanced approach that can handle the challenges in pose and illumination in face recognition The thesis proposes Robust Multi-Scale Block Local Binary Pattern as a new facial representation that is sufficiently robust to accept variations in pose and illumination and yet contains rich discriminative information The thesis also investigates the metrics or scores in general used to measure similarity/dissimilarity in face recognition and contributes two novel classification methods, namely Extended Bayesian Learning and Relation Learning, to overcome difficulties such as the Small-Sample-Size problem and gain good performance for face recognition systems iii iv Certificate of Authorship of Thesis Except where clearly acknowledged in footnotes, quotations and the bibliography, I certify that I am the sole author of the thesis submitted today entitled Face Recognition Using Local Patterns and Relation Learning I further certify that to the best of my knowledge the thesis contains no material previously published or written by another person except where due reference is made in the text of the thesis The material in the thesis has not been the basis of an award of any other degree or diploma except where due reference is made in the text of the thesis The thesis complies with University requirements for a thesis as set out in Higher Degree by Research Examination Policy, Schedule Two (S2) Refer to http://www.canberra.edu.au/research/hdr-policy-and-procedures ———————————————————————————————Signature of Candidate ———————————————————————————————Signature of chair of the supervisory panel ——————————————— Date v vi Acknowledgements First and foremost, I would like to thank my primary supervisor, Associate Professor Dat Tran, for his enormous support during my study at University of Canberra, in a variety of ways, both academic and personal I would also like to thank my co-supervisors, Professor Xu Huang and Associate Professor Girija Chetty, for their consistent encouragement and support on my research My four-and-half-year research at the Faculty of Information Sciences and Engineering has been priceless The facilities and environment for studying are excellent A special thanks to the Faculty and my friends for their support and discussions I would like to thank Vietnam Ministry of Education and Training for granting me the scholarship to study at University of Canberra My study could have not taken without the endless love, support of my family, father, sisters, brothers and nephews This thesis is dedicated to my beloved mother vii viii Contents Contents Summary of Thesis iii Certificate of Authorship of Thesis v Acknowledgements vii List of Figures xiii List of Tables xix List of Abbreviations xxi List of Publications xxiii Introduction 1.1 Face Recognition 1.2 Challenges to Face Recognition 1.3 Current Approaches to Face Recognition 1.4 Motivation 1.5 Problem Statement 1.6 Thesis Contribution 1.7 Thesis Organization 12 Literature Review 2.1 15 Literatures on Facial Feature Representation 17 2.1.1 Data Independent Feature Extraction 17 2.1.2 Data Dependent Feature Extraction 20 2.1.3 Mixed Feature Extraction 23 2.2 Literatures on Face Detection 24 2.3 Literatures on Face Recognition 27 ix Contents 2.4 2.3.1 General Face Recognition System 27 2.3.2 Unsupervised Distance Learning-Based Approaches 27 2.3.3 Supervised Distance Learning-Based Approaches 29 2.3.4 Support Vector Machines-Based Approaches 30 2.3.5 Approaches for Face Recognition across Pose and Illumination 30 Summary 33 Facial Representation 35 3.1 Introduction 36 3.2 Pixel-based Facial Features 36 3.3 Fourier-Based Facial Features 37 3.4 Cosine-Based Facial Features 38 3.5 Gabor-Based Facial Features 40 3.6 Haar-like Features 43 3.7 Local Pattern-Based Facial Features 46 3.7.1 Local Binary Patterns 46 3.7.2 Generic Local Binary Patterns 49 3.7.3 Local Ternary Patterns 3.7.4 Invariants of Local Binary Patterns 51 3.7.5 Multi-scale Local Binary Patterns 52 3.7.6 Multi-Scale Block Local Binary Patterns 52 50 3.8 Complex Facial Representations 53 3.9 My Proposed Robust Multi-Scale Block Local Binary Patterns 54 3.10 My Proposed Compact Histogram Representation 55 3.11 Summary 56 Face Detection 57 4.1 Description of Face Detection System 58 4.2 Neural Networks 59 4.3 4.2.1 Overview 59 4.2.2 Neural Network-Based Classification 60 4.2.3 Neural Network-Based Face Detection 61 AdaBoost Algorithm 64 4.3.1 AdaBoost-Based Face Detection 65 x Chapter Conclusions and Suggestions for Future Work Chapter Conclusions and Suggestions for Future Work 155 Chapter Conclusions and Suggestions for Future Work 8.1 Conclusions In brief, face recognition is one of the major biometric techniques Although knowledge of face recognition has recently achieved many advances, it is still not sufficient to meet the accuracy requirements of many applications operating under significant variations of illumination and pose As a result of this study, I would draw the following conclusions Facial representations The difficulties in face recognition that are caused by many factors continue to be a challenge for any face recognition algorithm The difficulties faced include a large variability in facial appearance of the same person, the high dimensionality of data and small sample size, and high complex and nonlinear manifolds Local patterns including Local Binary Pattern and its variants provide the current best facial representations for face recognition systems because they are invariant against monotonic gray level change Second, its computation is rather simple, making image analysis possible in challenging real-time conditions Gabor-based facial representations and their combination with local patterns provide strongly fused representations better for each individual representation They are complimentary in the sense that LBP captures small appearance details while Gabor features encode facial shape over a broader range of scales Face detection Most current face detection algorithms satisfy the requirements of practical applications A set of Haar-like and extended Haar-like features are the best feature representations for face detection Boosting-based face detection algorithms are the most effective for real-time face detectors and are comparable to Neural Network-based algorithms Especially, AdaBoost learning can efficiently choose the best subset from a huge set of features and build a strong nonlinear detector The cascade structure significantly improves the performance of the face detector in the detection speed, with only a little decrease in detection rate 156 Chapter Conclusions and Suggestions for Future Work A hybrid model based on the combination of AdaBoost and Neural Network can improve both detection speed and detection rate Face recognition Most current face recognition algorithms can satisfy the requirements of practical applications under controlled conditions Because the nature of face recognition is a problem of a large number of classes, almost all face recognition uses distances between images to measure their similarity In other words, face recognition, in practice, is a classification problem in that the number of classes is very large while the number of samples available for each class is very limited Therefore, most face recognition systems use a Nearest Neighbor rule to make the decision or, distance-based classification Relation learning derived from a Support Vector Machine framework can efficiently handle the problem of small sample size in face recognition 8.2 Future Work One of major issues for facial representation based on the local binary patterns is that a small change in an input image could cause a large change in the output or pattern, so that the method may work improperly for images with noise or flat areas In the future, we need to combine with other methods to limit the limitation Although relation learning can handle small sample size problems in face recognition, its performance in recognition rate needs to improve by combining with other classification methods that include a data reduction method The proposed relation learning could be applied to other biometric applications such as fingerprinting, and iris and speech recognition The proposed relation learning approach is to deal with the insufficient data problem It defines a relation between two objects and applies this definition to determine all possible relations in the training data set The relation between two objects is used to measure the similarity between them Instead of considering objects in their data space as other methods do, a relation space is used The proposed hybrid model based on AdaBoost and Neural Network and the proposed Baysian learning technique could be applied to learning problems for other 157 Chapter Conclusions and Suggestions for Future Work biometric applications We can also combine the proposed hybrid model with other classification methods that have the ability to reject false negative patterns correctly and efficiently in order to improve the performance The proposed hybrid model will be able to achieve minimum computation time in biometric applications 158 Bibliography Bibliography Ahonen, T., Hadid, A., and Pietikainen, M (2006) Face description with local binary patterns: Application to face recognition Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(12):2037–2041 7, 50, 91 Ahonen, T., Hadid, A., and Pietikäinen, M (2004) Face recognition with local binary patterns Computer Vision-ECCV 2004, pages 469–481 7, 22, 32, 48, 54, 91, 133, 134 Ahonen, T and Pietikäinen, M (2009) Pixelwise local binary pattern models of faces using kernel density estimation Advances in Biometrics, pages 52–61 Arca, S., Campadelli, P., and Lanzarotti, R (2006) A face recognition system based on automatically determined facial fiducial points Pattern Recognition, 39(3):432–443 Bartlett, M S (2001) Independent component representations for face recognition Face Image Analysis by Unsupervised Learning, pages 39–67 6, 18 Bartlett, M S., Movellan, J R., and Sejnowski, T J (2002) Face recognition by independent component analysis Neural Networks, IEEE Transactions on, 13(6):1450–1464 18, 28 Basri, R and Jacobs, D (2003) Lambertian reflectance and linear subspaces Pattern Analysis and Machine Intelligence, IEEE Transactions on, 25(2):218–233 31 Belhumeur, P N., Hespanha, J P., and Kriegman, D J (1997) Eigenfaces vs fisherfaces: Recognition using class specific linear projection Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(7):711–720 6, 18, 29, 81 Belkin, M and Niyogi, P (2003) Laplacian eigenmaps for dimensionality reduction and data representation Neural computation, 15(6):1373–1396 19 159 Bibliography Beveridge, J., Bolme, D., Draper, B., and Teixeira, M (2005) The csu face identification evaluation system Machine vision and applications, 16(2):128–138 88 Beveridge, J., She, K., Draper, B., and Givens, G (2001) A nonparametric statistical comparison of principal component and linear discriminant subspaces for face recognition In Computer Vision and Pattern Recognition, 2001 CVPR 2001 Proceedings of the 2001 IEEE Computer Society Conference on, volume 1, pages I–535–I–542 vol IEEE 121 Bishop, C (1995) Neural networks for pattern recognition Oxford University Press, USA 59, 98 Bishop, C M (2006) Pattern recognition and machine learning Springer New York 17, 59, 86, 98, 99 Blanz, V., Romdhani, S., and Vetter, T (2002) Face identification across different poses and illuminations with a 3d morphable model In Automatic Face and Gesture Recognition, 2002 Proceedings Fifth IEEE International Conference on, pages 192–197 IEEE 31 Bui, L and Le, T (2008) A hybrid approach of adaboost and artificial neural network for detecting human faces In Proceedings of the IEEE International Conference on Research, Innovation and Vision for the Future (RIVF), pages 79–85 IEEE 10, 12, 67 Bui, L., Tran, D., Huang, X., and Chetty, G (2010) Face gender recognition based on 2d principal component analysis and support vector machine In Proceedings of the 4th International Conference on Network and System Security (NSS), pages 579–582 IEEE 127 Bui, L., Tran, D., Huang, X., and Chetty, G (2011a) Classification of gender and face based on gradient faces In Proceedings of the 3rd European Workshop on Visual Information Processing (EUVIP), pages 269–272 IEEE 140 Bui, L., Tran, D., Huang, X., and Chetty, G (2011b) Face recognition based on gabor features In Proceedings of the 3rd European Workshop on Visual Information Processing (EUVIP), pages 264–268 IEEE 140 160 Bibliography Bui, L., Tran, D., Huang, X., and Chetty, G (2011c) A new approach to bayesian method for face recognition In practice, 1:3 10, 88 Bui, L., Tran, D., Huang, X., and Chetty, G (2011d) Novel metrics for face recognition using local binary patterns Knowledge-Based and Intelligent Information and Engineering Systems (KES), pages 436–445 11, 92, 94 Bui, L., Tran, D., Huang, X., and Chetty, G (2011e) Relation learning-a new approach to face recognition Proceedings of Advances Concepts for Intelligent Vision Systems (ACIVS), Belgium, LNCS 6915, pages 566–575 11 Bui, L., Tran, D., Huang, X., and Chetty, G (2012) Face gender classification based on active appearance model and fuzzy k-nearest neighbors In The 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV’12), USA IEEE 127 Chan, C., Kittler, J., and Messer, K (2007) Multi-scale local binary pattern histograms for face recognition Advances in Biometrics, pages 809–818 52 Comon, P (1994) Independent component analysis, a new concept? Signal processing, 36(3):287–314 18 Coppersmith, D and Winograd, S (1990) Matrix multiplication via arithmetic progressions Journal of symbolic computation, 9(3):251–280 137 Daubechies, I (1990) The wavelet transform, time-frequency localization and signal analysis Information Theory, IEEE Transactions on, 36(5):961–1005 21 DeMers, D and Cottrell, G (1993) Non-linear dimensionality reduction Advances in Neural Information Processing Systems, pages 580–580 20 Duda, R O., Hart, P E., and Stork, D G (2001) Pattern classification Wiley New York 59, 98, 99 Feraud, R., Bernier, O., Viallet, J E., and Collobert, M (2000) A fast and accurate face detector for indexation of face images pages 77–82 27 Fisher, R A (1936) The use of multiple measurements in taxonomic problems Annals of Human Genetics, 7(2):179–188 18 161 Bibliography Freund, Y and Schapire, R (1995) A desicion-theoretic generalization of on-line learning and an application to boosting In Computational learning theory, pages 23–37 Springer 64 Friedman, J., Hastie, T., and Tibshirani, R (2001) The elements of statistical learning, volume Springer Series in Statistics 99 Fukunaga, K (1990) Introduction to statistical pattern recognition Academic Pr 98 Georghiades, A., Belhumeur, P., and Kriegman, D (2001) From few to many: Illumination cone models for face recognition under variable lighting and pose Pattern Analysis and Machine Intelligence, IEEE Transactions on, 23(6):643–660 31 Gross, R., Matthews, I., and Baker, S (2002) Eigen light-fields and face recognition across pose In Automatic Face and Gesture Recognition, 2002 Proceedings Fifth IEEE International Conference on, pages 1–7 IEEE 31 Guo, G., Li, S., and Chan, K (2000) Face recognition by support vector machines In Automatic Face and Gesture Recognition, 2000 Proceedings Fourth IEEE International Conference on, pages 196–201 IEEE 30, 103 Hafed, Z M and Levine, M D (2001) Face recognition using the discrete cosine transform International Journal of Computer Vision, 43(3):167–188 21 Heisele, B., Ho, P., and Poggio, T (2001) Face recognition with support vector machines: Global versus component-based approach In Computer Vision, 2001 ICCV 2001 Proceedings Eighth IEEE International Conference on, volume 2, pages 688–694 IEEE 30, 104 Hotelling, H (1933) Analysis of a complex of statistical variables into principal components Journal of educational psychology, 24(6):417 27, 76 Huang, C., Ai, H., Li, Y., and Lao, S (2007) High-performance rotation invariant multiview face detection Pattern Analysis and Machine Intelligence, IEEE Transactions on, 29(4):671–686 26, 27 162 Bibliography Huang, F., Zhou, Z., Zhang, H., and Chen, T (2000) Pose invariant face recognition In Automatic Face and Gesture Recognition, 2000 Proceedings Fourth IEEE International Conference on, pages 245–250 IEEE 30 Huang, J., Shao, X., and Wechsler, H (1998) Face pose discrimination using support vector machines (svm) volume 1, pages 154–156 27 Hussain, S and Triggs, B (2012) Visual recognition using local quantized patterns 10, 55 Jiang, D., Hu, Y., Yan, S., Zhang, L., Zhang, H., and Gao, W (2005) Efficient 3d reconstruction for face recognition Pattern Recognition, 38(6):787–798 32 Jin, H., Liu, Q., Lu, H., and Tong, X (2004) Face detection using improved lbp under bayesian framework In Image and Graphics, 2004 Proceedings Third International Conference on, pages 306–309 IEEE 51 Jutten, C and Herault, J (1991) Blind separation of sources, part i: An adaptive algorithm based on neuromimetic architecture Signal processing, 24(1):1–10 18 Kanade, T (1973) Picture processing system by computer complex and recognition of human faces Department of Science, Kyoto University 16 Kelly, M (1970) Visual identification of people by computer Technical report, DTIC Document 16 Kirby, M and Sirovich, L (1990) Application of the karhunen-loeve procedure for the characterization of human faces Pattern Analysis and Machine Intelligence, IEEE Transactions on, 12(1):103–108 16, 27, 75 Kramer, M A (1991) Nonlinear principal component analysis using autoassociative neural networks AIChE journal, 37(2):233–243 20 Kruskal, J (1964) Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis Psychometrika, 29(1):1–27 19 Kuncheva, L (2004) Combining pattern classifiers: methods and algorithms WileyInterscience 98 Lai, J H., Yuen, P C., and Feng, G C (2001) Face recognition using holistic fourier invariant features Pattern Recognition, 34(1):95–109 21 163 Bibliography Li, S Z and Jain, A K (2005) Handbook of face recognition Springer 28, 98 Li, S Z and Jain, A K (2011) Handbook of face recognition Springer-Verlag New York Inc 4, 28, 77, 98, 130, 132 Liao, S., Law, M W K., and Chung, A C S (2009) Dominant local binary patterns for texture classification Image Processing, IEEE Transactions on, 18(5):1107–1118 22 Liao, S., Zhu, X., Lei, Z., Zhang, L., and Li, S (2007) Learning multi-scale block local binary patterns for face recognition Advances in Biometrics, pages 828–837 52 Lienhart, R., Kuranov, A., and Pisarevsky, V (2003) Empirical analysis of detection cascades of boosted classifiers for rapid object detection Pattern Recognition, pages 297–304 26 Lienhart, R and Maydt, J (2002) An extended set of haar-like features for rapid object detection In Image Processing 2002 Proceedings 2002 International Conference on, volume 1, pages I–900–I–903 vol IEEE 44 Liu, C (2004) Gabor-based kernel pca with fractional power polynomial models for face recognition Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(5):572–581 32 Liu, C and Shum, H Y (2003) Kullback-leibler boosting volume 1, pages I–587–I–587 131 Liu, C and Wechsler, H (2002) Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition Image Processing, IEEE Transactions on, 11(4):467–476 140 Ming-Hsuan, Y (2002a) Face recognition using extended isomap In Image Processing 2002 Proceedings 2002 International Conference on, volume 2, pages II–117–II–120 vol.2 19 Ming-Hsuan, Y (2002b) Kernel eigenfaces vs kernel fisherfaces: Face recognition using kernel methods pages 215–220 IEEE 20 164 Bibliography Moghaddam, B., Jebara, T., and Pentland, A (2000) Bayesian face recognition Pattern Recognition, 33(11):1771–1782 6, 29, 86 Moghaddam, B and Pentland, A (1997) Probabilistic visual learning for object representation Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(7):696–710 24, 28, 79, 80 Moon, H and Phillips, P (2001) Computational and performance aspects of pcabased face-recognition algorithms PERCEPTION-LONDON-, 30(3):303–322 28, 77 Moses, Y., Adini, Y., and Ullman, S (1994) Face recognition: The problem of compensating for changes in illumination direction Computer Vision—ECCV’94, pages 286–296 Movellan, J (2002) Tutorial on gabor filters Open Source Document 40 Nixon, M and Aguado, A (2012) Feature Extraction & Image Processing for Computer Vision Academic Press 37, 38 Nocedal, J and Wright, S J (1999) Numerical optimization Springer verlag 90 Ojala, T., Pietikainen, M., and Maenpaa, T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24(7):971–987 Ojala, T., Pietikäinen, M., and Harwood, D (1996) A comparative study of texture measures with classification based on featured distributions Pattern Recognition, 29(1):51–59 9, 22, 46, 49, 91 Osuna, E., Freund, R., and Girosit, F (1997) Training support vector machines: an application to face detection pages 130–136 24 Papageorgiou, C., Oren, M., and Poggio, T (1998) A general framework for object detection In Computer Vision, 1998 Sixth International Conference on, pages 555–562 IEEE 43 Pearson, K (1901) Liii on lines and planes of closest fit to systems of points in space The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 2(11):559–572 18, 76 165 Bibliography Pentland, A., Moghaddam, B., and Starner, T (1994) View-based and modular eigenspaces for face recognition pages 84–91 7, 16, 30, 129 Pham, M T and Cham, T J (2007) Fast training and selection of haar features using statistics in boosting-based face detection pages 1–7 26 Pham, M T., Hoang, V D., and Cham, T J (2008) Detection with multi-exit asymmetric boosting pages 1–8 44 Phillips, P (1998) Support vector machines applied to face recognition US Department of Commerce, Technology Administration, National Institute of Standards and Technology 30, 103 Phillips, P., Moon, H., Rizvi, S., and Rauss, P (2002) The feret evaluation methodology for face-recognition algorithms Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(10):1090–1104 27, 98 Phillips, P J., Moon, H., Rizvi, S A., and Rauss, P J (2000) The feret evaluation methodology for face-recognition algorithms Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(10):1090–1104 121 Phillips, P J., Scruggs, W T., O’Toole, A J., Flynn, P J., Bowyer, K W., Schott, C L., and Sharpe, M (2007) Frvt 2006 and ice 2006 large-scale results National Institute of Standards and Technology, NISTIR, 7408 98 Pietikäinen, M., Hadid, A., Zhao, G., and Ahonen, T (2011) Computer vision using local binary patterns, volume 40 Springer 22 Raja, Y., Gong, S., and Mary, Q (2006) Sparse multiscale local binary patterns 22 Ricker, N (1953) Wavelet contraction, wavelet expansion, and the control of seismic resolution Geophysics, 18(4):769–792 21 Riklin-Raviv, T and Shashua, A (1999) The quotient image: class based recognition and synthesis under varying illumination conditions In Computer Vision and Pattern Recognition, 1999 IEEE Computer Society Conference on., volume IEEE 30 166 Bibliography Romdhani, S and Vetter, T (2003) Efficient, robust and accurate fitting of a 3d morphable model In Computer Vision, 2003 Proceedings Ninth IEEE International Conference on, pages 59–66 IEEE 31 Roweis, S and Saul, L (2000) Nonlinear dimensionality reduction by locally linear embedding Science, 290(5500):2323–2326 19 Rowley, H A., Baluja, S., and Kanade, T (1998) Neural network-based face detection Pattern Analysis and Machine Intelligence, IEEE Transactions on, 20(1):23–38 xiv, 24, 61, 62, 63 Schneiderman, H and Kanade, T (2000) A statistical method for 3d object detection applied to faces and cars volume 1, pages 746–751 25, 27 Shan, S., Yang, P., Chen, X., and Gao, W (2005) Adaboost gabor fisher classifier for face recognition Analysis and Modelling of Faces and Gestures, pages 279–292 140 Shan, S., Zhang, W., Su, Y., Chen, X., and Gao, W (2006) Ensemble of piecewise fda based on spatial histograms of local (gabor) binary patterns for face recognition volume 4, pages 606–609 23, 32 Shawe-Taylor, J and Cristianini, N (2004) Kernel methods for pattern analysis Cambridge university press 20 Smola, A and Schölkopf, B (1998) Learning with kernels Citeseer 20 Stoer, J and Bulirsch, R (2002) Introduction to numerical analysis, volume 12 Springer 86 Sun, N., Zheng, W., Sun, C., Zou, C., and Zhao, L (2006) Gender classification based on boosting local binary pattern Advances in Neural Networks-ISNN 2006, pages 194–201 Sung, K K and Poggio, T (1998) Example-based learning for view-based human face detection Pattern Analysis and Machine Intelligence, IEEE Transactions on, 20(1):39–51 24 Tan, X and Triggs, B (2007a) Enhanced local texture feature sets for face recognition under difficult lighting conditions pages 168–182 22, 50, 71, 72 167 Bibliography Tan, X and Triggs, B (2007b) Fusing gabor and lbp feature sets for kernel-based face recognition Analysis and Modeling of Faces and Gestures, pages 235–249 23, 32 Taylor, S (2003) Intel Integrated Performance Primitives: How to Optimize Software Applications Using Intel IPP Intel Press 44 Tenenbaum, J., De Silva, V., and Langford, J (2000) A global geometric framework for nonlinear dimensionality reduction Science, 290(5500):2319–2323 19 Turk, M and Pentland, A (1991a) Eigenfaces for recognition Journal of cognitive neuroscience, 3(1):71–86 16, 18, 27, 75 Turk, M A and Pentland, A P (1991b) Face recognition using eigenfaces pages 586–591 6, 24 Vasilescu, M A O and Terzopoulos, D (2003) Multilinear subspace analysis of image ensembles volume 2, pages II–93–II–93 29 Viola, P and Jones, M (2001) Fast and robust classification using asymmetric adaboost and a detector cascade Proc of NIPS01 25, 26, 43, 44, 65, 66 Viola, P and Jones, M J (2004) Robust real-time face detection International journal of computer vision, 57(2):137–154 12, 21, 25 Vladimir, V and Vapnik, V (1995) The nature of statistical learning theory 20, 99 Wang, H., Li, S., and Wang, Y (2004) Face recognition under varying lighting conditions using self quotient image In Automatic Face and Gesture Recognition, 2004 Proceedings Sixth IEEE International Conference on, pages 819–824 IEEE 31 Wang, X and Tang, X (2003) Unified subspace analysis for face recognition pages 679–686 29 Webb, A (1999) Statistical pattern recognition A Hodder Arnold Publication 98 Weinberger, K., Blitzer, J., and Saul, L (2006) Distance metric learning for large margin nearest neighbor classification In In NIPS Citeseer 29 168 Bibliography Wiskott, L., Fellous, J M., Kuiger, N., and von der Malsburg, C (1997) Face recognition by elastic bunch graph matching Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(7):775–779 22, 27, 32 Wu, J., Brubaker, S C., Mullin, M D., and Rehg, J M (2008) Fast asymmetric learning for cascade face detection Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(3):369–382 26 Yang, J., Zhang, D., and Frangi, A (2004) Two-dimensional pca: a new approach to appearance-based face representation and recognition Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(1):131–137 19, 80 Yang, M H., Roth, D., and Ahuja, N (2000) A snow-based face detector 25 Zhang, B., Gao, Y., Zhao, S., and Liu, J (2010) Local derivative pattern versus local binary pattern: face recognition with high-order local pattern descriptor Image Processing, IEEE Transactions on, 19(2):533–544 23, 51 Zhang, G., Huang, X., Li, S., Wang, Y., and Wu, X (2005a) Boosting local binary pattern (lbp)-based face recognition Advances in biometric person authentication, pages 179–186 xiv, 23, 54, 139 Zhang, L., Chu, R., Xiang, S., Liao, S., and Li, S (2007) Face detection based on multi-block lbp representation Advances in Biometrics, pages 11–18 Zhang, L and Samaras, D (2006) Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(3):351–363 32 Zhang, W., Shan, S., Gao, W., Chen, X., and Zhang, H (2005b) Local gabor binary pattern histogram sequence (lgbphs): A novel non-statistical model for face representation and recognition volume 1, pages 786–791 xiv, 32, 53, 54 Zhao, W., Chellappa, R., Phillips, P J., and Rosenfeld, A (2003) Face recognition: A literature survey Acm Computing Surveys (CSUR), 35(4):399–458 16 Zhou, S and Chellappa, R (2005) Image-based face recognition under illumination and pose variations JOSA A, 22(2):217–229 31 169 [...]... 98 6.2 Face Recognition Using Support Vector Machine 99 6.3 6.4 6.2.1 Support Vector Machine 99 6.2.2 SVM-Based Face Recognition 103 Proposed Face Recognition Using Relation Learning 104 6.3.1 Theory of Relation Learning 104 6.3.2 Algorithm of Relation Learning 108 6.3.3 Relation Learning- Based Face Recognition. .. current face recognition systems use both local features and the whole face region for classification It is argued that these methods potentially offer the best model Typical examples are Modular Eigenface (Pentland et al., 1994) using Eigenface and Eigenfeature such as Eigeneye, Eigennose, Eigenmouth, and Component-based method using face region and components Recently, hybrid methods using Local Patterns. .. Huang, X., and Chetty, G (2011c) A new approach to bayesian method for face recognition In practice, 1:3 Bui, L., Tran, D., Huang, X., and Chetty, G (2011d) Novel metrics for face recognition using local binary patterns Knowledge-Based and Intelligent Information and Engineering Systems (KES), pages 436–445 Bui, L., Tran, D., Huang, X., and Chetty, G (2011e) Relation learning- a new approach to face recognition. .. 5.3 Face Recognition Using Probabilistic PCA 78 5.4 Face Recognition Using Two-Dimensional PCA 80 5.5 Face Recognition Using LDA 81 5.6 Proposed Face Recognition Using Bayesian Learning 82 5.7 5.8 70 5.6.1 Bayesian Decision Theory 82 5.6.2 Bayesian Learning 85 5.6.3 Extended Bayesian Learning. .. the input to a face recognition system Typical examples are Eigenface (Turk and Pentland, 1991b) using Principal Component Analysis, Probabilistic Eigenface (Moghaddam et al., 2000) using Bayesian learning, Fisherface (Belhumeur et al., 1997) using Fisher Linear Discriminant Analysis and Bartlett (2001) using Independent Component Analysis Although their systems are not as complicated and often have... estimate of the location and scale of a face It also includes face land marking to localize facial landmarks e.g eyes, nose, mouth and facial outline 3 Chapter 1 Introduction A face normalization module will normalize the resulting face geometrically and photometrically Such is definitely necessary because most the current face recognition systems, in reality, are expected to deal with face images in varying... 4.4 4.5 Face Detection Using Cascade Structure of Boosted Classifiers 66 My Proposed Hybrid Approach for Face Detection 67 4.4.1 Structure of Hybrid Face Detector 67 4.4.2 Applying to Face Detector 68 Summary 68 5 Distance Learning for Face Recognition 69 5.1 Description of Face Recognition System 5.2 Face Recognition Using. .. A typical face recognition system (shown in Figure 1.2) consists of four modules: face localization, face normalization, feature extraction and feature matching Figure 1.2: A typical face recognition system A face localization module aims to extract facial regions from the image background In the case of video clips, the detected faces may need to be tracked across multiple frames using a face- tracking... seconds)139 7.25 Results of face recognition for three facial representations on FERET 140 7.26 Results of face recognition of fusion classifiers on ORL 141 7.27 Results of face recognition of fusion classifiers on FERET 141 7.28 Results of face recognition of fusion classifiers on ORL 142 7.29 Results of face recognition using fusion classifiers on Extended Yale Face Database ... as Local Binary Pattern (Ahonen et al., 2004, 2006; Ahonen and Pietikäinen, 2009) have been widely used in face recognition and detection due to their good performance and relatively simple and efficient computation tasks 1.4 Motivation Face recognition is the major biometric technique in use It is more natural and non-intrusive than the other biometric techniques such as fingerprinting, and iris and