Chou qu lian kong te zheng ji bian ren lian kong de tong ji xue fang fa

Sin Ka Yu = 抽取臉孔特徵及辨認臉孔的統計學方法 / 冼家裕.Thesis (M.Phil.)--Chinese University of Hong Kong, 2004.Includes bibliographical references (leaves 86-90).Text in English; abstracts in English and Chinese.Sin Ka Yu = Chou qu lian kong te zheng ji bian ren lian kong de tong ji xue fang fa / Xian Jiayu.Chapter Chapter 1. --- Introduction --- p.1Chapter 1.1. --- Motivation --- p.1Chapter 1.2. --- Objectives --- p.4Chapter 1.3. --- Organization of the thesis --- p.4Chapter Chapter 2. --- Facial Feature Extraction --- p.6Chapter 2.1. --- Introduction --- p.6Chapter 2.2. --- Reviews of Statistical Approach --- p.8Chapter 2.2.1. --- Eigenfaces --- p.8Chapter 2.2.1.1. --- Eigenfeatures Error! Bookmark not definedChapter 2.2.3. --- Singular Value Decomposition --- p.14Chapter 2.2.4. --- Summary --- p.15Chapter 2.3. --- Review of fiducial point localization methods --- p.16Chapter 2.3.1. --- Symmetry based Approach --- p.16Chapter 2.3.2. --- Color Based Approaches --- p.17Chapter 2.3.3. --- Integral Projection --- p.17Chapter 2.3.4. --- Deformable Template --- p.20Chapter 2.4. --- Corner-based Fiducial Point Localization --- p.22Chapter 2.4.1. --- Facial Region Extraction --- p.22Chapter 2.4.2. --- Corner Detection --- p.25Chapter 2.4.3. --- Corner Selection --- p.27Chapter 2.4.3.1. --- Mouth Corner Pairs Detection --- p.27Chapter 2.4.3.2. --- Iris Detection --- p.27Chapter 2.5. --- Experimental Results --- p.30Chapter 2.6. --- Conclusions --- p.30Chapter 2.7. --- Notes on Publications --- p.30Chapter Chapter 3. --- Fiducial Point Extraction with Shape Constraint --- p.32Chapter 3.1. --- Introduction --- p.32Chapter 3.2. --- Statistical Theory of Shape --- p.33Chapter 3.2.1. --- Shape Space --- p.33Chapter 3.2.2. --- Shape Distribution --- p.34Chapter 3.3. --- Shape Guided Fiducial Point Localization --- p.38Chapter 3.3.1. --- Shape Constraints --- p.38Chapter 3.3.2. --- Intelligent Search --- p.40Chapter 3.4. --- Experimental Results --- p.40Chapter 3.5. --- Conclusions --- p.42Chapter 3.6. --- Notes on Publications --- p.42Chapter Chapter 4. --- Statistical Pattern Recognition --- p.43Chapter 4.1. --- Introduction --- p.43Chapter 4.2. --- Bayes Decision Rule --- p.44Chapter 4.3. --- Gaussian Maximum Probability Classifier --- p.46Chapter 4.4. --- Maximum Likelihood Estimation of Mean and Covariance Matrix --- p.48Chapter 4.5. --- Small Sample Size Problem --- p.50Chapter 4.5.1. --- Dispersed Eigenvalues --- p.50Chapter 4.5.2. --- Distorted Classification Rule --- p.55Chapter 4.6. --- Review of Methods Handling the Small Sample Size Problem --- p.57Chapter 4.6.1. --- Linear Discriminant Classifier --- p.57Chapter 4.6.2. --- Regularized Discriminant Analysis --- p.59Chapter 4.6.3. --- Leave-one-out Likelihood Method --- p.63Chapter 4.6.4. --- Bayesian Leave-one-out Likelihood method --- p.65Chapter 4.7. --- Proposed Method --- p.68Chapter 4.7.1. --- A New Covariance Estimator --- p.70Chapter 4.7.2. --- Model Selection --- p.75Chapter 4.7.3. --- The Mixture Parameter --- p.76Chapter 4.8. --- Experimental results --- p.77Chapter 4.8.1. --- Implementation --- p.77Chapter 4.8.2. --- Results --- p.79Chapter 4.9. --- Conclusion --- p.81Chapter 4.10. --- Notes on Publications --- p.82Chapter Chapter 5. --- Conclusions and Future works --- p.83Chapter 5.1. --- Conclusions and Contributions --- p.83Chapter 5.2. --- Future Works --- p.8