Face Image Analysis by Unsupervised Learning

1. Front Matter

   Pages i-xv

   PDF

2. Summary

   • Marian Stewart Bartlett

   Pages 1-4

3. Introduction

   • Marian Stewart Bartlett

   Pages 5-38

4. Independent Component Representations for Face Recognition

   • Marian Stewart Bartlett

   Pages 39-67

5. Automated Facial Expression Analysis

   • Marian Stewart Bartlett

   Pages 69-82

6. Image Representations for Facial Expression Analysis: Comparative Study I

   • Marian Stewart Bartlett

   Pages 83-99

7. Image Representations for Facial Expression Analysis: Comparative Study II

   • Marian Stewart Bartlett

   Pages 101-128

8. Learning Viewpoint Invariant Representations of Faces in an Attractor Network

   • Marian Stewart Bartlett

   Pages 129-149

9. Conclusions and Future Directions

   • Marian Stewart Bartlett

   Pages 151-156

10. Back Matter

    Pages 157-173

    PDF

Face Image Analysis by Unsupervised Learning explores adaptive approaches to image analysis. It draws upon principles of unsupervised learning and information theory to adapt processing to the immediate task environment. In contrast to more traditional approaches to image analysis in which relevant structure is determined in advance and extracted using hand-engineered techniques, Face Image Analysis by Unsupervised Learning explores methods that have roots in biological vision and/or learn about the image structure directly from the image ensemble. Particular attention is paid to unsupervised learning techniques for encoding the statistical dependencies in the image ensemble.
The first part of this volume reviews unsupervised learning, information theory, independent component analysis, and their relation to biological vision. Next, a face image representation using independent component analysis (ICA) is developed, which is an unsupervised learning technique based on optimal information transfer between neurons. The ICA representation is compared to a number of other face representations including eigenfaces and Gabor wavelets on tasks of identity recognition and expression analysis. Finally, methods for learning features that are robust to changes in viewpoint and lighting are presented. These studies provide evidence that encoding input dependencies through unsupervised learning is an effective strategy for face recognition.
Face Image Analysis by Unsupervised Learning is suitable as a secondary text for a graduate-level course, and as a reference for researchers and practitioners in industry.

• coding
• cognition
• image analysis
• information
• information theory
• learning
• presentation
• supervised learning
• wavelet
• wavelets

`Marian Bartlett's comparison of ICA with other algorithms on the recognition of facial expressions is perhaps the most thorough analysis we have of the strengths and limits of ICA as a preprocessing stage for pattern recognition.'
T.J. Sejnowski, Salk Institute

• Institute for Neural Computation, University of California, San Diego, USA

  Marian Stewart Bartlett

Policies and ethics