Baback Moghaddam


Ph.D. in Electrical Engineering and Computer Science

Massachusettes Institute of Technology, 1997

Research interests
Visual Recognition, Cognitive Neuroscience

Advisor: Alex Pentland

Education
BS, Electrical & Computer Engineering, 1989 (Magna Cum Laude)
MS, Electrical & Computer Engineering, 1992 (Honors)
George Mason University

Experience
Research Instructor
Center of Excellence in Command, Control, Communications & Intelligence (C3I)
George Mason University, 1992


Research Description

Research involves probabilistic visual learning for view-based object recognition, robust feature detection and the construction of attention maps for visual search. Current work is on automated face recognition (see my face recognition demo page for further details). Also interested in the inverse problem of mapping 2D views of a face to a 3D model and the analysis of facial and whole-body articulation.

Also involved in computational modeling of human judgements of facial attractiveness and our perception of "beauty". Ongoing "pet-project": Statistical Modeling of the "Beauty Subspace" Spanned by Christy Turlington's 2D-XYI Facial Manifold Morphology (see figure above). Alas, this line of research wouldn't fly as a real dissertation!

Publications

Beyond Eigenfaces: Probabilistic Matching for Face Recognition
Moghaddam B., Wahid W. and Pentland A.
International Conference on Automatic Face & Gesture Recognition, Nara, Japan, April 1998. (TR #443)

Probabilistic Visual Learning for Object Representation
Moghaddam B. and Pentland A.
Pattern Analysis and Machine Intelligence, PAMI-19 (7), pp. 696-710, July 1997

A Bayesian Similarity Measure for Direct Image Matching
Moghaddam B., Nastar C. and Pentland A.
International Conference on Pattern Recognition, Vienna, Austria, August 1996. (TR #393)

Bayesian Face Recognition Using Deformable Intensity Surfaces
Moghaddam B., Nastar C. and Pentland A.
IEEE Conf. on Computer Vision & Pattern Recognition, San Francisco, CA, June 1996. (TR #371)

Active Face Tracking and Pose Estimation in an Interactive Room
Darrell T., Moghaddam B. and Pentland A.
IEEE Conf. on Computer Vision & Pattern Recognition, San Francisco, CA, June 1996. (TR #356)

Generalized Image Matching: Statistical Learning of Physically-Based Deformations
Nastar C., Moghaddam B. and Pentland A.
Fourth European Conference on Computer Vision, Cambridge, UK, April 1996. (TR #368)

Probabilistic Visual Learning for Object Detection
Moghaddam, B. and Pentland A.
International Conference on Computer Vision, Cambridge, MA, June 1995. (TR #326)

A Subspace Method for Maximum Likelihood Target Detection
Moghaddam, B. and Pentland A.
International Conference on Image Processing, Washington DC, October 1995. (TR #335)

An Automatic System for Model-Based Coding of Faces
Moghaddam, B. and Pentland A.
IEEE Data Compression Conference, Snowbird, Utah, March 1995. (TR #317)

View-Based and Modular Eigenspaces for Face Recognition
Pentland A., Moghaddam B., Starner T.
IEEE Conf. on Computer Vision & Pattern Recognition, Seattle, WA, July 1994. (TR #245)

Fractional Brownian Motion Models for Synthetic Aperture Radar Imagery Scene Segmentation
Stewart C., Moghaddam B., Hintz K., Novak L.
Proceedings of the IEEE, Vol. 81, No. 10, October 1993.

A Comparison of Local Fractal Dimension Estimation Methods
Moghaddam B., Hintz K., Stewart C.
Pattern Recognition & Image Analysis, Vol. 12, No. 1, 1992.


Interests
Music, Art and Cinema

Birthplace
Tehran, Iran

A favorite book
"Ulysses", by James Joyce

Most wishes to have dinner with
William Burroughs, Allen Ginsberg & Jack Kerouac (at the same table)


Personal Web Page


Vismod Home Page