Eye Pupil Location Using Webcam

TL;DR

This paper compares three algorithms for eye pupil detection using webcam images, evaluates their efficiency on a standard database, and implements them in a real-time application for eye movement-based control.

Contribution

It introduces a real-time eye pupil localization system using webcam images and compares multiple algorithms' efficiency in this context.

Findings

Algorithms tested on BioID database show varying efficiency.

Real-time implementation demonstrates practical usability.

System supports eye movement-based computer control.

Abstract

Three different algorithms used for eye pupil location were described and tested. Algorithm efficiency comparison was based on human faces images taken from the BioID database. Moreover all the eye localisation methods were implemented in a dedicated application supporting eye movement based computer control. In this case human face images were acquired by a webcam and processed in a real-time.