Intensity based methodologies for facial expression recognition.

by Hok Chun Lo.Thesis (M.Phil.)--Chinese University of Hong Kong, 2001.Includes bibliographical references (leaves 136-143).Abstracts in English and Chinese.LIST OF FIGURES --- p.viiiLIST OF TABLES --- p.xChapter 1. --- INTRODUCTION --- p.1Chapter 2. --- PREVIOUS WORK ON FACIAL EXPRESSION RECOGNITION --- p.9Chapter 2.1. --- Active Deformable Contour --- p.9Chapter 2.2. --- Facial Feature Points and B-spline Curve --- p.10Chapter 2.3. --- Optical Flow Approach --- p.11Chapter 2.4. --- Facial Action Coding System --- p.12Chapter 2.5. --- Neural Network --- p.13Chapter 3. --- EIGEN-ANALYSIS BASED METHOD FOR FACIAL EXPRESSION RECOGNITION --- p.15Chapter 3.1. --- Related Topics on Eigen-Analysis Based Method --- p.15Chapter 3.1.1. --- Terminologies --- p.15Chapter 3.1.2. --- Principal Component Analysis --- p.17Chapter 3.1.3. --- Significance of Principal Component Analysis --- p.18Chapter 3.1.4. --- Graphical Presentation of the Idea of Principal Component Analysis --- p.20Chapter 3.2. --- EigenFace Method for Face Recognition --- p.21Chapter 3.3. --- Eigen-Analysis Based Method for Facial Expression Recognition --- p.23Chapter 3.3.1. --- Person-Dependent Database --- p.23Chapter 3.3.2. --- Direct Adoption of EigenFace Method --- p.24Chapter 3.3.3. --- Multiple Subspaces Method --- p.27Chapter 3.4. --- Detail Description on Our Approaches --- p.29Chapter 3.4.1. --- Database Formation --- p.29Chapter a. --- Conversion of Image to Column Vector --- p.29Chapter b. --- "Preprocess: Scale Regulation, Orientation Regulation and Cropping." --- p.30Chapter c. --- Scale Regulation --- p.31Chapter d. --- Orientation Regulation --- p.32Chapter e. --- Cropping of images --- p.33Chapter f. --- Calculation of Expression Subspace for Direct Adoption Method --- p.35Chapter g. --- Calculation of Expression Subspace for Multiple Subspaces Method. --- p.38Chapter 3.4.2. --- Recognition Process for Direct Adoption Method --- p.38Chapter 3.4.3. --- Recognition Process for Multiple Subspaces Method --- p.39Chapter a. --- Intensity Normalization Algorithm --- p.39Chapter b. --- Matching --- p.44Chapter 3.5. --- Experimental Result and Analysis --- p.45Chapter 4. --- DEFORMABLE TEMPLATE MATCHING SCHEME FOR FACIAL EXPRESSION RECOGNITION --- p.53Chapter 4.1. --- Background Knowledge --- p.53Chapter 4.1.1. --- Camera Model --- p.53Chapter a. --- Pinhole Camera Model and Perspective Projection --- p.54Chapter b. --- Orthographic Camera Model --- p.56Chapter c. --- Affine Camera Model --- p.57Chapter 4.1.2. --- View Synthesis --- p.58Chapter a. --- Technique Issue of View Synthesis --- p.59Chapter 4.2. --- View Synthesis Technique for Facial Expression Recognition --- p.68Chapter 4.2.1. --- From View Synthesis Technique to Template Deformation --- p.69Chapter 4.3. --- Database Formation --- p.71Chapter 4.3.1. --- Person-Dependent Database --- p.72Chapter 4.3.2. --- Model Images Acquisition --- p.72Chapter 4.3.3. --- Templates' Structure and Formation Process --- p.73Chapter 4.3.4. --- Selection of Warping Points and Template Anchor Points --- p.77Chapter a. --- Selection of Warping Points --- p.78Chapter b. --- Selection of Template Anchor Points --- p.80Chapter 4.4. --- Recognition Process --- p.81Chapter 4.4.1. --- Solving Warping Equation --- p.83Chapter 4.4.2. --- Template Deformation --- p.83Chapter 4.4.3. --- Template from Input Images --- p.86Chapter 4.4.4. --- Matching --- p.87Chapter 4.5. --- Implementation of Automation System --- p.88Chapter 4.5.1. --- Kalman Filter --- p.89Chapter 4.5.2. --- Using Kalman Filter for Trakcing in Our System --- p.89Chapter 4.5.3. --- Limitation --- p.92Chapter 4.6. --- Experimental Result and Analysis --- p.93Chapter 5. --- CONCLUSION AND FUTURE WORK --- p.97APPENDIX --- p.100Chapter I. --- Image Sample 1 --- p.100Chapter II. --- Image Sample 2 --- p.109Chapter III. --- Image Sample 3 --- p.119Chapter IV. --- Image Sample 4 --- p.135BIBLIOGRAPHY --- p.13