Face Image Analysis by Unsupervised Learning (The Kluwer International Series in Engineering and Computer Science, Volume 612) (The Springer International Series in Engineering and Computer Science) (Hardcover)

by Marian Stewart Bartlett (Author) "How can a perceptual system learn to recognize properties of its environment without being told which features it should analyze, or whether its decisions are..." (more)
Key Phrases: independent basis images, viewpoint invariant responses, independent source images, Diff Expr, Horace Barlow, Same Expr (more...)

Editorial Reviews

Review
`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

Product Description
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.

Product Details

• Hardcover: 192 pages
• Publisher: Springer; 1 edition (May 1, 2001)
• Language: English
• ISBN-10: 0792373480
• ISBN-13: 978-0792373483
• Product Dimensions: 9 x 7.1 x 0.7 inches
• Shipping Weight: 1 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars See all reviews (1 customer review)
• Amazon.com Sales Rank: #2,885,511 in Books (See Bestsellers in Books)

  Popular in this category: (What's this?)

  #10 in

  Books > Computers & Internet > Software > Optical Character Recognition

Customer Reviews

Most Helpful Customer Reviews

5.0 out of 5 stars Important new work in image processing of faces, June 25, 2001

By A Customer

Marian Stewart Bartlett is a talented young scientist who has done some breakthrough work in the image processing of faces, particularly for the analysis of facial expressions. This book describes the details of that work, and places it in the broader context of other work in unsupervised learning and image processing. A must read for those keeping up with the latest and greatest in face image analysis!