MIT Media Laboratory
Vision and Modeling Group

Face Recognition Demo Page

The system diagram above shows a fully automatic system for detection, recognition and model-based coding of faces for potential applications such as video telephony, database image compression, and automatic face recognition. The system consists of a two-stage object detection and alignment stage, a contrast normalization stage, and a Karhunen-Loeve (eigenspace) based feature extraction stage whose output is used for both recognition and coding. This leads to a compact representation of the face that can be used for both recognition as well as image compression. Good-quality facial images are automatically generated using approximately 100-bytes worth of encoded data. The system has been successfully tested on a database of nearly 2000 facial photographs from the ARPA FERET database with a detection rate of 97%. Recognition rates as high as 99% have been obtained on a subset of the FERET database consisting of 2 frontal views of 155 individuals.

In September 1996, we participated in the final round of FERET tests administered by the US Army Research Laboratory which consisted of a large gallery test containing nearly 3,800 frontal images. Our system was found to be the top competitor (by a typical margin of 10% to the next best competitor). Also our system was the only fully automatic recognition system participating in the competition. The details of this competition and an analysis of the test results are available in this PostScript preprint.

Face Recognition Demos:

Photobook/Eigenfaces	Automatic Face Processor
FERET Face Database	FERET '96 Competition

• Photobook/Eigenfaces
• Automatic Face Processor
• The FERET Face Database
• The FERET '96 Face Recognition Competition

Face Recognition 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)