A Neural Network Face Recognition Assignment

This assignment, given in the fall semester of 1994 for the Machine Learning class at Carnegie Mellon, involves face recognition using neural networks. 32 images of each of 20 students in the class were taken with a variety of head positions and facial expressions. These images were then used to train and test neural networks to recognize individual people, and to recognize different face poses.

The assignment document describes the assignment in detail.

The code directory contains the source code for the neural network algorithm (Backpropagation) and image access code used in this assignment.

The trainset directory contains the training set specification files given for use with the neural network program.

The face images directory contains the face image data in PGM format. See the assignment document above for a description of the face images.

js@cs.cmu.edu (Last updated 16-Dec-94)