People Image Analysis Consortium
 

Home -> Projects ->Face Detection Member Login  

Jump to: Publications | Releases

 Description

This is a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. We also have preliminary results for detecting faces which are rotated out of the image plane, such as profiles and semi-profiles.

The system employs multiple networks; the first is a "router" network which processes each input window to determine its orientation and then uses this information to prepare the window for one or more "detector" networks.

 Demo Videos

walking1.mpg [0.3MB]
walking2.mpg [0.3MB]
web.mpg [0.5MB]
crowd.mpg [0.6MB]

 Publications

  • Neural Network-Based Face Detection
    Henry A. Rowley, Shumeet Baluja, and Takeo kanade
    IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 20, number 1, pages 23-38, January 1998.

 Releases [ Members Only ]


PIA Consortium is a part of Robotics Institute, School of Computer Science, Carnegie Mellon University