1 January 2020 in IEEE Access
Eye tracking is becoming a very important tool across many domains, including human-computer-interaction, psychology, computer vision, and medical diagnosis. Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome. Some of these methods suffer from poor image quality and variable light conditions. The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking. The availability of large-scale datasets has further improved the performance of deep learning-based methods. This paper presents a survey of the current state-of-the-art on deep learning-based gaze estimation techniques, with a focus on Convolutional Neural Networks (CNN). This paper also provides a survey on other machine learning-based gaze estimation techniques. This study aims to empower the research community with valuable and useful insights that can enhance the design and development of improved and efficient deep learning-based eye-tracking models. This study also provides information on various pre-trained models, network architectures, and open-source datasets that are useful for training deep learning models.
1 January 2019 in Heliyon
Oculomotor dysfunction may originate from physical, physiological or psychological causes and may be a marker for schizophrenia or other disorders. Observational tests for oculomotor dysfunction are easy to administer, but are subjective and transient, and it is difficult to quantify deviations. To date, video-based eye tracking systems have not provided a contextual overview of gaze data that integrates the eye video recording with the stimulus and gaze data together with quantitative feedback of metrics in relation to typical values. A system was developed with an interactive timeline to allow the analyst to scroll through a recording frame-by-frame while comparing data from three different sources. The visual and integrated nature of the analysis allows localisation and quantification of saccadic under- and overshoots as well as determination of the frequency and amplitude of catch-up and anticipatory saccades. Clinicians will be able to apply their expertise to diagnose disorders based on abnormal patterns in the gaze plots. They can use the line charts to quantify deviations from benchmark values for reaction time, saccadic accuracy and smooth pursuit gain. A clinician can refer to the eye video at any time to confirm that observed deviations originated from gaze behaviour and not from systemic errors.
23 August 2016 in Universal Access in the Information Society
6 July 2018 in African Journal of Research in Mathematics, Science and Technology Education
The Department of Basic Education in South Africa has identified factorisation as a problem area in Mathematics teaching. Learners in earlier grades are exposed to mathematical tasks, involving concepts, such as factors of integers, fractions, equivalent fractions and prime numbers, that are easier to solve when the divisibility rules are applied. An experiment was designed to investigate the effect of learners’ knowledge and their application of the divisibility rules on their gaze behaviour. Seventy-eight learners in Grades 4–7 participated in an eye-tracking study where questions on divisibility were presented on a computer screen. Learners were expected to indicate whether a five-digit dividend was divisible by a divisor and provide reasons for their answers. Gaze behaviour (expressed as the percentage of total fixation time that was spent on each digit), along with learners’ verbal responses were used to determine whether a given divisibility rule was applied correctly. The findings show that learners apply different strategies to inspect the dividend when they know the divisibility rules and apply them correctly as opposed to when they do not know the rules and/or apply them incorrectly. It is argued that, since knowledge of the divisibility rules is a reliable predictor for gaze behaviour, gaze behaviour can in turn be used to assist teachers to identify a lack of knowledge and/or the incorrect application of the divisibility rules. Teachers can then cautiously intervene with revision to assist learners whose gaze behaviour indicates that they need assistance.