Two- and Three-Dimensional Patterns of the Face

by Peter W. Hallinan, Gaile Gordon, A. L. Yuille, Peter Giblin, David Mumford

Overview

The human face is perhaps the most familiar and easily recognized object in the world, yet both its three-dimensional shape and its two-dimensional images are complex and hard to characterize. This book develops the vocabulary of ridges and parabolic curves, of illumination eigenfaces and elastic warpings for describing the perceptually salient features of a face and its images. The book also explores the underlying mathematics and applies these mathematical techniques to the computer vision problem of face recognition, using both optical and range images.

Product Details

ISBN-13:	9781568810874
Publisher:	Taylor & Francis
Publication date:	06/15/1999
Edition description:	New Edition
Pages:	272
Product dimensions:	6.00(w) x 9.00(h) x (d)

About the Author

Hallinan, Peter W.; Gordon, Gaile; Yuille, A. L.; Giblin, Peter; Mumford, David

Table of Contents

1. Faces from a Pattern-Theoretic Perspective 2. Overview of Approaches to Face Recognition 3. Modeling Variations in Illumination 4. Modeling Variations in Geometry 5. Recognition from Image Data 6. Parabolic Curves and Ridges on Surfaces 7. Sculpting a Surface 8. Finding Facial Features from Range Data 9. Recognition from Range Data 10. What's Next?

Editorial Reviews

Develops the vocabulary of ridges, parabolic curves, illumination eigenfaces, and elastic warpings for describing the perceptually salient features of a face and its images. The team of five computer scientists and mathematicians explore the underlying mathematics, and apply these mathematical techniques to the computer vision problem of face recognition, using both optical and range images. The book grew out of work at the Harvard Robotics Laboratory in the early 1990s. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews