Marian Stewart Bartlett

Machine Perception Lab


Marian Stewart Bartlett, Ph.D.




Institute for Neural Computation
University of California, San Diego, 0523
9500 Gilman Drive
La Jolla, CA 92093-0523

Phone: (858) 822-5241
Fax: (858) 534-2014
Email: marni@salk.edu

I am Assistant Research Professor at the Machine Perception Lab at the Institute for Neural Computation, UCSD. I received my PhD in Cognitive Science and Psychology from the University of California, San Diego in 1998. I did my Ph.D research with Terrance Sejnowski at the Computational Neurobiology Laboratory at the Salk Institute. My doctoral dissertation was on "Face image analysis by unsupervised learning and redundancy reduction." View Abstract. My Postdoc was with Javier Movellan at the Institute for Neural Computation, UCSD. My research interests include

  • Image analysis through unsupervised learning.
  • Facial identity recognition.
  • Facial expression analysis.
  • Independent component analysis for pattern recognition.

    Publications
    Recent Projects
    matlab code for face representations using ICA. REVISED 7/2003. FULL MATLAB CODE FOR ARCHITECTURES I AND II NOW AVAILABLE.
    companion code for running face recognition using ica. This code includes nearest neighbor using cosines.

    Here are photos of my son, Paul 1 2 3 and daughter, Kate 1 2.


    Face Image Analysis

    by Unsupervised Learning

    Marian Stewart Bartlett

    Kluwer International Series on Engineering and Computer Science, V. 612. Boston: Kluwer
    Academic Publishers, 2001. Ordering Information (888)-640-7378. Also available on Amazon.com.

    Foreword by Terrence J. Sejnowski

    Table of Contents

    Book Jacket

    Face Image Analysis by Unsupervised Learning explores adaptive approaches to face 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, [this book] 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 practioners in industry.

    "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, The Salk Institute







    May 7, 2001: