project1b

project1b - CSCI 460 Introduction to Artificial...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: CSCI 460 Introduction to Artificial Intelligence Fall 2007 Project 1(b): Artificial Neural Network Due: October 4, 2007 1 Introduction This project gives you an opportunity to apply neural network learning to the problem of face recognition. You will experiment with a neural network program to train a sunglasses recognizer and a face recognizer. This project should be done alone. Materials for the project have been provided courtesy of Dr. Tom Mitchell, a professor at Carnegie Mellon University. The face images you will use are faces of students from past Machine Learning classes (taught by Dr. Mitchell) at CMU. Interested students may wish to consult Dr. Mitchell’s textbook, Machine Learning (1997, McGraw-Hill). You will not need to do significant amounts of programming for the first part of this assignment, and you should not let the size of this document scare you. However, it will take some time for you to become familiar with the code we provide, and to train your networks. It is recommended that you read the assignment in its entirety first, and start working as soon as possible. 2 Setting Up the Project You can download the gzipped tar archive project1b.tar.gz on the course website, under the Assignments tab. You can then unzip the archive with 1 the command tar xzvf project1b.tar.gz in your download directory (under Linux and Mac OS X). Note: on Sun machines, you will need to issue the above command in two steps (because the Sun version of tar does not support the z option). That is: gunzip project1b.tar.gz tar xvf project1b.tar to unzip the archive. On Windows systems, you can unzip the archive using newer versions of WinZip. 3 Project Description 3.1 The Face Images The image data can be found in the faces directory of the archive. This directory contains 20 subdirectories, one for each person, named by userid. Each of these directories contains several different face images of the same person. You will be interested in the images with the following naming convention: <userid> <pose> <expression> <eyes> <scale>.pgm • <userid> is the user id of the person in the image, and this field has 20 values: an2i, at33, boland, bpm, ch4f, cheyer, choon, danieln, glickman, karyadi, kawamura, kk49, megak, mitchell, night, phoebe, saavik, steffi, sz24, and tammo. • <pose> is the head position of the person, and this field has 4 values: straight, left, right, up. • <expression> is the facial expression of the person, and this field has 4 values: neutral, happy, sad, angry. • <eyes> is the eye state of the person, and this field has 2 values: open, sunglasses. 2 • <scale> is the scale of the image, and this field has 3 values: 1, 2, and 4. 1 indicates a full-resolution image (128 columns × 120 rows); 2 indicates a half-resolution image (64 × 60); 4 indicates a quarter- resolution image (32 × 30). For this assignment, you will be using the quarter-resolution images for experiments, to keep training time to a manageable level....
View Full Document

{[ snackBarMessage ]}

Page1 / 16

project1b - CSCI 460 Introduction to Artificial...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online