HALL OF EYES

An Investigation of Image Feature Detection

Chiouguey J. Chen, Timothy D. Dorney, and Robert H. Sparr

Abstract

A review of the literature reveals that approaches to feature extraction vary widely and many methods are quite specific to a particular application. Some extraction problems involve the detection of a desired target despite noise in the image. Other problems involve the identification of a member of a class defined by a class subset despite natural variation.

Our project involves the detection of members of a class. Specifically, we attempt to develop a method of locating the eyes in an image of a human face. Such a system would be useful in security applications and in the automatic selection of control points for digital image warping.

In this project, we compare two basic approaches: matched filters and artificial neural networks. We develop several techniques to improve upon the results obtained with a basic matched filter and we develop a suitable artificial neural network and training set for our application.

This project was completed as a portion of Richard Baraniuk's 1997 class on Image Processing at Rice University.

Contact the authors:
jchen@micro.ti.com
tdorney@ti.com
sparr@owlnet.rice.edu