Please use this identifier to cite or link to this item:
Title: Eye gaze based reading detection
Keywords: Reading detection, gaze tracking, user interest tracking, finite state machines, attentive systems, blink detection
Issue Date: 19-Feb-2004
Source: FOO TUN KEAT (2004-02-19). Eye gaze based reading detection. ScholarBank@NUS Repository.
Abstract: In this thesis, we examine the possibility of determining whether a computer user is engaged in reading material on the computer monitor, or not, using image sequences from an ordinary camera. The challenges in determining whether reading is taking place is in differentiating this from the different activities that the user can perform at the computer, and being tolerant to user differences, different types of text and how they are displayed. We have proposed an algorithm based on estimating gaze directions, achieving an average accuracy of 84.1% on 10 people. Changes in the gaze directions over a specified interval during reading are modelled using a set of Finite State Machines (FSMs). Gaze directions estimated over a finite time interval (window) are checked with respect to these FSMs to determine whether the interval represents reading. An aggregate of these determinations over successive time windows is finally used to infer whether reading is taking place.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
meng_thesis.pdf4.43 MBAdobe PDF



Page view(s)

checked on Dec 11, 2017


checked on Dec 11, 2017

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.