Skip to main content
Presentation
A Fast Neural-Based Eye Detection System
Faculty of Informatics - Papers (Archive)
  • Fok Hing Chi Tivive, University of Wollongong
  • Abdesselam Bouzerdoum, University of Wollongong
RIS ID
13027
Publication Date
13-12-2005
Publication Details
This article was originally published as: Tivive, FHC & Bouzerdoum, A, A Fast Neural-Based Eye Detection System, Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2005), 13-16 December 2005, 641-644. Copyright IEEE 2005.
Abstract

This paper presents a fast eye detection system which is based on an artificial neural network known as the shunting inhibitory convolutional neural network, or SICoNNet for short. With its two-dimensional network architecture and the use of convolution operators, the eye detection system processes an entire input image and generates the location map of the detected eyes at the output. The network consists of 479 trainable parameters which are adapted by a modified Levenberg-Marquardt training algorithm in conjunction with a bootstrap procedure. Tested on 180 real images, with 186 faces, the accuracy of the eye detector reaches 96.8% with only 38 false detections.

Citation Information
Fok Hing Chi Tivive and Abdesselam Bouzerdoum. "A Fast Neural-Based Eye Detection System" (2005)
Available at: http://works.bepress.com/sbouzerdoum/31/