Thesis

Using Clustering Techniques For Exploratory Analysis of Eye-Tracking Data

If you want to read the PDF, try requesting it from the authors.

Abstract

Vision impairments in children are harmful to their learning process, cognitive development, social interaction, and scholar performance. In recent years, new technologies have been applied for vision screening tests, sharpening traditional techniques and enabling the early diagnosis of different kinds of debilitation on the visual system functionality. Eye-tracking is a widely used technique applied for different purposes, and when it comes to vision assessment and training, it is greatly suitable. This work aims to apply feature engineering and cluster analysis techniques within eye-tracking data collected from children performing structured visual tasks. Feature engineering creates meaningful attributes for the recordings in terms of performance and data quality, and the exploratory analysis covers different configurations for the clustering methods and their hyper-parameters. Cluster validation metrics evaluate the clustering results’ quality, and domain expert acknowledgment is essencial for trustful inferences regarding the children’s oculomotor system’s health. In order to streamline the exploratory analysis and facilitate the experiments, we also propose a framework for Cluster Analysis of the eye-tracking data.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
The area under the receiver operating characteristics (ROC) Curve, referred to as AUC, is a well-known performance measure in the supervised learning domain. Due to its compelling features, it has been employed in a number of studies to evaluate and compare the performance of different classifiers. In this work, we explore AUC as a performance measure in the unsupervised learning domain, more specifically, in the context of cluster analysis. In particular, we elaborate on the use of AUC as an internal/relative measure of clustering quality, which we refer to as Area Under the Curve for Clustering (AUCC). We show that the AUCC of a given candidate clustering solution has an expected value under a null model of random clustering solutions, regardless of the size of the dataset and, more importantly, regardless of the number or the (im)balance of clusters under evaluation. In addition, we elaborate on the fact that, in the context of internal/relative clustering validation as we consider, AUCC is actually a linear transformation of the Gamma criterion from Baker and Hubert (1975), for which we also formally derive a theoretical expected value for chance clusterings. We also discuss the computational complexity of these criteria and show that, while an ordinary implementation of Gamma can be computationally prohibitive and impractical for most real applications of cluster analysis, its equivalence with AUCC actually unveils a much more efficient algorithmic procedure. Our theoretical findings are supported by experimental results. These results show that, in addition to an effective and robust quantitative evaluation provided by AUCC, visual inspection of the ROC curves themselves can be useful to further assess a candidate clustering solution from a broader, qualitative perspective as well.
Article
Full-text available
Many children have undetected vision problems or insufficient visual information processing that may be a factor in lower academic outcomes. The aim of this paper is to contribute to a better understanding of the importance of vision screening for school-aged children, and to investigate the possibilities of how eye-tracking (ET) technologies can support this. While there are indications that these technologies can support vision screening, a broad understanding of how to apply them and by whom, and if it is possible to utilize them at schools, is lacking. We review interdisciplinary research on performing vision investigations, and discuss current challenges for technology support. The focus is on exploring the possibilities of ET technologies to better support screening and handling of vision disorders, especially by non-vision experts. The data orginate from a literature survey of peer-reviewed journals and conference articles complemented by secondary sources, following a rapid review methodology. We highlight current trends in supportive technologies for vision screening, and identify the involved stakeholders and the research studies that discuss how to develop more supportive ET technologies for vision screening and training by non-experts.
Article
Full-text available
Due to the close relationship between oculomotor behavior and visual processing, eye movements have been studied in many different areas of research over the last few decades. While these studies have brought interesting insights, specialization within each research area comes at the potential cost of a narrow and isolated view of the oculomotor system. In this review, we want to expand this perspective by looking at the interactions between the two most important types of voluntary eye movements: saccades and pursuit. Recent evidence indicates multiple interactions and shared signals at the behavioral and neurophysiological level for oculomotor control and for visual perception during pursuit and saccades. Oculomotor control seems to be based on shared position- and velocity-related information, which leads to multiple behavioral interactions and synergies. The distinction between position- and velocity-related information seems to be also present at the neurophysiological level. In addition, visual perception seems to be based on shared efferent signals about upcoming eye positions and velocities, which are to some degree independent of the actual oculomotor response. This review suggests an interactive perspective on the oculomotor system, based mainly on different types of sensory input, and less so on separate subsystems for saccadic or pursuit eye movements.
Article
Full-text available
Introduction: Vision problems affect academic performance, social and mental health. Most traditional vision screening methods rely on human expert assessments based on a set of vision tests. As technology advances, new instruments and computerised tools are available for complementing vision screening. The scoping review based on this protocol aims to investigate current technologies for vision screening, what vision tests can be complemented by technologies, and how these can support vision screening by providing measurements. Methods and analysis: The planned review will utilise the PRISMA extension for Scoping Reviews (PRISMA-ScR) tool. Electronic search will be performed in databases, including Web of Science, MEDLINE (Ovid), Scopus, Engineering Village, Cochrane and Embase. We will perform a systematic search in selected reference databases without the limitation on publications dates, or country of studies. Reference management software, like EndNote and DistillerSR, will be used to remove duplicate entries. Two authors will independently analyse the studies for inclusion eligibility. Conflicts will be resolved by discussion. We will extract the types of technologies, types of vision tests they complement and the measurements for the included studies. Overall findings will be synthesised by thematic analysis and mapping to the logic model. Ethics and dissemination: Ethical approval is not required for this review, as it will only summarise existing published data. We will publish the findings in an open access, peer-reviewed journal. We expect that the review results will be useful for vision screening experts, developers, researchers, and policymakers.
Article
Full-text available
Visual search in natural scenes is a complex task relying on peripheral vision to detect potential targets and central vision to verify them. The segregation of the visual fields has been particularly established by on-screen experiments. We conducted a gaze-contingent experiment in virtual reality in order to test how the perceived roles of central and peripheral visions translated to more natural settings. The use of everyday scenes in virtual reality allowed us to study visual attention by implementing a fairly ecological protocol that cannot be implemented in the real world. Central or peripheral vision was masked during visual search, with target objects selected according to scene semantic rules. Analyzing the resulting search behavior, we found that target objects that were not spatially constrained to a probable location within the scene impacted search measures negatively. Our results diverge from on-screen studies in that search performances were only slightly affected by central vision loss. In particular, a central mask did not impact verification times when the target was grammatically constrained to an anchor object. Our findings demonstrates that the role of central vision (up to 6 degrees of eccentricities) in identifying objects in natural scenes seems to be minor, while the role of peripheral preprocessing of targets in immersive real-world searches may have been underestimated by on-screen experiments.
Article
Full-text available
In recent decades, the use of technological resources such as the eye tracking methodology is providing cognitive researchers with important tools to better understand the learning process. However, the interpretation of the metrics requires the use of supervised and unsupervised learning techniques. The main goal of this study was to analyse the results obtained with the eye tracking methodology by applying statistical tests and supervised and unsupervised machine learning techniques, and to contrast the effectiveness of each one. The parameters of fixations, saccades, blinks and scan path, and the results in a puzzle task were found. The statistical study concluded that no significant differences were found between participants in solving the crossword puzzle task; significant differences were only detected in the parameters saccade amplitude minimum and saccade velocity minimum. On the other hand, this study, with supervised machine learning techniques, provided possible features for analysis, some of them different from those used in the statistical study. Regarding the clustering techniques, a good fit was found between the algorithms used (k-means ++, fuzzy k-means and DBSCAN). These algorithms provided the learning profile of the participants in three types (students over 50 years old; and students and teachers under 50 years of age). Therefore, the use of both types of data analysis is considered complementary.
Article
Full-text available
Several children struggle with vision difficulties caused by problematic coordination between their left and right eye muscles, i.e., oculomotor dysfunction (OMD). Many OMDs can be improved by training the eyes via physical exercises defined and supervised by vision experts. The aim of this paper is to investigate the feasibility of utilizing Serious Games (SGs) and eye-tracking technologies (ETs) for training the eyes of children having OMD. Via these activities, a trainee can, with her eye gaze, follow objects which are moving, change their directions and speed, or pop up on the screen. The results present mapping the current physical training goals to activities for SGs using input from ETs, and illustrate this correspondence for designing and developing six games. The games’ feasibility evaluation is done via semistructured interviews and evaluating user experiences. Three vision teachers (VTs) were involved in design and development, ensuring achievement of training goals, and five VT students in evaluations. The findings demonstrate the potential of using SGs and ETs to train OMD and point to future needs for improvements.
Article
Full-text available
A number of virtual reality head-mounted displays (HMDs) with integrated eye trackers have recently become commercially available. If their eye tracking latency is low and reliable enough for gaze-contingent rendering, this may open up many interesting opportunities for researchers. We measured eye tracking latencies for the Fove-0, the Varjo VR-1, and the High Tech Computer Corporation (HTC) Vive Pro Eye using simultaneous electrooculography measurements. We determined the time from the occurrence of an eye position change to its availability as a data sample from the eye tracker (delay) and the time from an eye position change to the earliest possible change of the display content (latency). For each test and each device, participants performed 60 saccades between two targets 20° of visual angle apart. The targets were continuously visible in the HMD, and the saccades were instructed by an auditory cue. Data collection and eye tracking calibration were done using the recommended scripts for each device in Unity3D. The Vive Pro Eye was recorded twice, once using the SteamVR SDK and once using the Tobii XR SDK. Our results show clear differences between the HMDs. Delays ranged from 15 ms to 52 ms, and the latencies ranged from 45 ms to 81 ms. The Fove-0 appears to be the fastest device and best suited for gaze-contingent rendering.
Chapter
Full-text available
This chapter adopts an integrative literature review to describe and analyze theories and empirical research on visual development, impairment, screening, and intervention. The purpose is to inform teachers on how to influence students’ education and social growth through understanding vision. Vision is especially essential for reading, accessing classroom materials, and learning. Yet, in many countries, vision problems in children are not assessed and thus not treated. The negative consequences for individuals and society are often significant. Though there is an abundance of eye health specialists in developed countries, not all visual problems that influence learning and reading are screened or treated effectively. This is worse in developing countries where eye health infrastructure often is lacking. Even screening and treatment given through the eye healthcare system is not always sustainable, since regular follow-up is lacking. The literature review shows that vision is a developing sense important for learning and that teachers can screen children’s vision and support visual development. It can be concluded that every child in the twenty-first century school should have teachers with knowledge in vision. An example of a higher education initiative is presented to illustrate possible further education for teachers in the area of vision.
Article
Full-text available
A new graphical display is proposed for partitioning techniques. Each cluster is represented by a so-called silhouette, which is based on the comparison of its tightness and separation. This silhouette shows which objects lie well within their cluster, and which ones are merely somewhere in between clusters. The entire clustering is displayed by combining the silhouettes into a single plot, allowing an appreciation of the relative quality of the clusters and an overview of the data configuration. The average silhouette width provides an evaluation of clustering validity, and might be used to select an ‘appropriate’ number of clusters.
Article
Full-text available
Background: Academic performance at different educational levels has become a very important subject of study in local, national and international institutions. A visual system working properly is critical to improving academic performance. It is important to check children's vision during the different stages of elementary school. Methods: A visual screening was carried out in elementary school children, aged between 6 and 12, across Spain. The screening included: the collection of demographic data, surveys of children and families about their vision habits and a basic optometric screening to detect visual problems. Results: Children with bad academic performance had worse visual health than those with good academic performance. Conclusions: It would be highly recommendable to introduce policies that ensure the early detection of visual disorders in schools and primary care in order to improve the academic performance of elementary students.
Article
Full-text available
Eye tracking has become increasingly important in many sectors because of its ability to facilitate day to day activities, especially for users with special needs, where tasks as simple as turning on a light require effort. To tackle similar issues, we propose a model that utilizes Video Oculography approach through Tobii technology with added voice interfaces using Azure cloud to help control home appliances. This model traces the user via reflected infrared light patterns and calculates the gaze position automatically. This method uses no wearable technology through Video Oculography with multiple cameras which deliver several advantages; it provides accurate gaze estimates, portability of the video recording system, and fully remote recordings. Eye tracking facilitates interactions to control home appliances when the user cannot or does not wish to use their hands by means of the IoT and cloud Technologies. Eye tracking has great impact in countless fields such as neurology, cognition, communication and security of different categories. Focus groups and usability tests show that many users were satisfied with the straightforward use of the model, flexibility and reliability in interacting with the system, and accuracy in the movement of the pointer, make this model a reliable solution to simplifying some daily tasks.
Article
Full-text available
Objective The purpose of this study was to examine the reliability of oculomotor metrics in healthy individuals, to determine the normative values through cluster analysis, and to compare oculomotor metrics by age groups in a suite of digitized eye tracking tests. Design Experimental cross sectional Participants A large sample of 2993 participants completed RightEye tests. Results These tests demonstrated acceptable or higher reliability on 85% of the eye movement metrics and the clustering analysis distinguished 5 distinct age groups. Furthermore, group differences were found between age clusters. Conclusions Overall, the findings represent the reliability of a computerized oculomotor measure and the importance to consider individual and group characteristics for clinical applications as well as applied settings.
Article
Full-text available
Significance: The results of this study suggest that clinicians providing vergence/accommodative therapy for the treatment of childhood convergence insufficiency should not suggest that such treatment, on average, will lead to improvements on standardized assessments of reading performance after 16 weeks of treatment. Purpose: The purpose of this study was to determine the effect of office-based vergence/accommodative therapy on reading performance in 9- to 14-year-old children with symptomatic convergence insufficiency. Methods: In a multicenter clinical trial, 310 children 9 to 14 years old with symptomatic convergence insufficiency were randomized in a 2:1 ratio to 16 weeks of office-based vergence/accommodative therapy or office-based placebo therapy, respectively. The primary outcome was change in reading comprehension as measured by the reading comprehension subtest of the Wechsler Individual Achievement Test, Third Edition (WIAT-III) at the 16-week outcome. Secondary reading outcomes of word identification, reading fluency, listening comprehension, comprehension of extended text, and reading comprehension were also evaluated. Results: The adjusted mean improvement in WIAT-III reading comprehension was 3.7 (95% confidence interval [CI], 2.6 to 4.7) standard score points in the vergence/accommodative therapy group and 3.8 (95% CI, 2.4 to 5.2) points in the placebo therapy group, with an adjusted mean group difference of -0.12 (95% CI, -1.89 to 1.66) points that was not statistically significant. No statistically significant treatment group differences were found for any of the secondary reading outcome measures. Conclusions: For children aged 9 to 14 years with symptomatic convergence insufficiency, office-based vergence/accommodative therapy was no more effective than office-based placebo therapy for improving reading performance on standardized reading tests after 16 weeks of treatment.
Article
Full-text available
Eye tracking is a popular research tool in developmental cognitive neuroscience for studying the development of perceptual and cognitive processes. However, eye tracking in the context of development is also challenging. In this paper, we ask how knowledge on eye-tracking data quality can be used to improve eye-tracking recordings and analyses in longitudinal research so that valid conclusions about child development may be drawn. We answer this question by adopting the data-quality perspective and surveying the eye-tracking setup, training protocols, and data analysis of the YOUth study (investigating neurocognitive development of 6000 children). We first show how our eye-tracking setup has been optimized for recording high-quality eye-tracking data. Second, we show that eye-tracking data quality can be operator-dependent even after a thorough training protocol. Finally, we report distributions of eye-tracking data quality measures for four age groups (5 months, 10 months, 3 years, and 9 years), based on 1531 recordings. We end with advice for (prospective) developmental eye-tracking researchers and generalizations to other methodologies.
Thesis
Full-text available
Eyes are the window to the world, and most of the input from the surrounding environment is captured through the eyes. In Human-Computer Interaction too, gaze based interactions are gaining prominence, where the user’s gaze acts as an input to the system. Of late portable and inexpensive eye-tracking devices have made inroads in the market, opening up wider possibilities for interacting with a gaze. However, research on feedback to the gaze-based events is limited. This thesis proposes to study vibrotactile feedback to gaze-based interactions. This thesis presents a study conducted to evaluate different types of vibrotactile feedback and their role in response to a gaze-based event. For this study, an experimental setup was designed wherein when the user fixated the gaze on a functional object, vibrotactile feedback was provided either on the wrist or on the glasses. The study seeks to answer questions such as the helpfulness of vibrotactile feedback in identifying functional objects, user preference for the type of vibrotactile feedback, and user preference of the location of the feedback. The results of this study indicate that vibrotactile feedback was an important factor in identifying the functional object. The preference for the type of vibrotactile feedback was somewhat inconclusive as there were wide variations among the users over the type of vibrotactile feedback. The personal preference largely influenced the choice of location for receiving the feedback.
Article
Full-text available
Childhood visual impairment (VI) have a significant impact on the educational achievement, career choices and social life of affected individual, and in children, is mainly due to either preventable or treatable causes. Reliable data on the prevalence and causes of VI in children will guide the development of a systematic vision screening program for its early detection and successful treatment of possible causes. The purpose of this literature review is to summarize the available data on prevalence and causes of VI in school-age children from various regions globally. A discussion on the major findings highlighting the definition criteria, classifications and limitations for further studies is also presented. •
Article
Full-text available
Objective: Major depression disorder (MDD) is one of the most prevalent mental disorders worldwide. Diagnosing depression in the early stage is crucial to treatment process. However, due to depression's comorbid nature and the subjectivity in diagnosis, an early diagnosis could be challenging. Recently, machine learning approaches have been used to process Electroencephalography (EEG) and neuroimaging data to facilitate the diagnosis. In the present study, we used a multimodal machine learning approach involving EEG, eye tracking and galvanic skin response data as input to classify depression patients and healthy controls. Methods: One hundred and forty-four MDD depression patients and 204 matched healthy controls were recruited. They were required to watch a series of affective and neutral stimuli while EEG, eye tracking information and galvanic skin response were recorded via a set of low-cost, portable devices. Three machine learning algorithms including Random Forests, Logistic Regression and Support Vector Machine (SVM) were trained to build dichotomous classification model. Results: The results showed that the highest classification f1 score was obtained by Logistic Regression algorithms, with accuracy = 79.63%, precision = 76.67%, recall = 85.19% and f1 score = 80.70% Limitations: No hospitalized patients were available; only outpatients were included in the present study. The sample consisted mostly of young adult, and no elder patients were included. Conclusions: The machine learning approach can be a useful tool for classifying MDD patients and healthy controls and may help for diagnostic processes.
Article
Full-text available
Existing event detection algorithms for eye-movement data almost exclusively rely on thresholding one or more hand-crafted signal features, each computed from the stream of raw gaze data. Moreover, this thresholding is largely left for the end user. Here we present and develop gazeNet, a new framework for creating event detectors that do not require hand-crafted signal features or signal thresholding. It employs an end-to-end deep learning approach, which takes raw eye-tracking data as input and classifies it into fixations, saccades and post-saccadic oscillations. Our method thereby challenges an established tacit assumption that hand-crafted features are necessary in the design of event detection algorithms. The downside of the deep learning approach is that a large amount of training data is required. We therefore first develop a method to augment hand-coded data, so that we can strongly enlarge the data set used for training, minimizing the time spent on manual coding. Using this extended hand-coded data, we train a neural network that produces eye-movement event classification from raw eye-movement data without requiring any predefined feature extraction or post-processing steps. The resulting classification performance is at the level of expert human coders. Moreover, an evaluation of gazeNet on two other datasets showed that gazeNet generalized to data from different eye trackers and consistently outperformed several other event detection algorithms that we tested.
Article
Full-text available
Health monitoring technology in everyday situations is expected to improve quality of life and support aging populations. Mental fatigue among health indicators of individuals has become important due to its association with cognitive performance and health outcomes, especially in older adults. Previous models using eye-tracking measures allow inference of fatigue during cognitive tasks, such as driving, but they require us to engage in specific cognitive tasks. In addition, previous models were mainly tested by user groups that did not include older adults, although age-related changes in eye-tracking measures have been reported especially in older adults. Here, we propose a model to detect mental fatigue of younger and older adults in natural viewing situations. Our model includes two unique aspects: (i) novel feature sets to better capture fatigue in natural-viewing situations and (ii) an automated feature selection method to select a feature subset enabling the model to be robust to the target's age. To test our model, we collected eye-tracking data from younger and older adults as they watched video clips before and after performing cognitive tasks. Our model improved detection accuracy by up to 13.9% compared with a model based on the previous studies, achieving 91.0% accuracy (chance 50%).
Article
Full-text available
Disorders of the vestibular system possibly decrease vision, causing abnormal nystagmus and dizziness. To diagnose abnormal nystagmus, various studies have been reported including the use of rotating chair tests and videonystagmography. However, these tests are unsuitable for home use due to their high costs. Thus, a low-cost video-oculography system is necessary to obtain clinical features at home. In this paper, we present a goggle-type low-cost video-oculography system using an infrared camera and Raspberry Pi board for tracking the pupils and evaluating a vestibular system. Horizontal eye movement is derived from video data obtained from an infrared camera and infrared light-emitting diodes, and the velocity of head rotation is obtained from a gyroscope sensor. Each pupil was extracted using a morphology operation and a contour detection method. Rotatory chair tests were conducted with our developed device. To evaluate our system, gain, symmetry, and phase were measured and compared System 2000.
Article
Full-text available
Strabismus is one of the most common vision diseases that would cause amblyopia and even permanent vision loss. Timely diagnosis is crucial for well treating strabismus. In contrast to manual diagnosis, automatic recognition can significantly reduce labor cost and increase diagnosis efficiency. In this paper, we propose to recognize strabismus using eye-tracking data and convolutional neural networks. In particular, an eye tracker is first exploited to record a subject’s eye movements. A gaze deviation (GaDe) image is then proposed to characterize the subject’s eye-tracking data according to the accuracies of gaze points. The GaDe image is fed to a convolutional neural network (CNN) that has been trained on a large image database called ImageNet. The outputs of the full connection layers of the CNN are used as the GaDe image’s features for strabismus recognition. A dataset containing eye-tracking data of both strabismic subjects and normal subjects is established for experiments. Experimental results demonstrate that the natural image features can be well transferred to represent eye-tracking data, and strabismus can be effectively recognized by our proposed method.
Chapter
Full-text available
The behavior of time-varying and static electric and magnetic fields are governed by Maxwell's equations formulated by James Clerk Maxwell (1865; 1873). These equations simply summarize the mathematical consequences of the classical experiments of Faraday, Ampere, Coulomb, Maxwell, and others. Maxwell's equations can be found in general texts on electromagnetic theory. However, they are essentially applicable to electromagnetic fields in free space (i.e., radiation fields). Where conducting and/or magnetic media are involved, then, although the equations continue to be valid, current sources can arise in other ways than specified under free space conditions. These modifications must be introduced through a consideration of the particular nature of current sources appropriate for the problem at hand. Our goal here, after introducing Maxwell's equations in the form valid for free space conditions, is to specialize them so that they correctly describe conditions that arise in bioelectromagnetism. Following this, our goal is to simplify the equations where possible, based on practical electrophysiological considerations.
Thesis
Full-text available
Eye and gaze movements play an essential role in identifying individuals' emotional states, cognitive activities, interests, and attention among other behavioral traits. Besides, they are natural, fast, and implicitly reflect the targets of interest, which makes them a highly valuable input modality in human-computer interfaces. Therefore, tracking gaze movements, in other words, eye tracking is of great interest to a large number of disciplines, including human behaviour research, neuroscience, medicine, and human-computer interaction. Tracking gaze movements accurately is a challenging task, especially under unconstrained conditions. Over the last two decades, significant advances have been made in improving the gaze estimation accuracy. However, these improvements have been achieved mostly under controlled settings. Meanwhile, several concerns have arisen, such as the complexity, inflexibility and cost of the setups, increased user effort, and high sensitivity to varying real-world conditions. Despite various attempts and promising enhancements, existing eye tracking systems are still inadequate to overcome most of these concerns, which prevent them from being widely used. In this thesis, we revisit these concerns and introduce a novel multi-camera eye tracking framework. The proposed framework achieves a high estimation accuracy while requiring a minimal user effort and a non-intrusive flexible setup. In addition, it provides improved robustness to large head movements, illumination changes, use of eye wear, and eye type variations across users. We develop a novel real-time gaze estimation framework based on adaptive fusion of multiple single-camera systems, in which the gaze estimation relies on projective geometry. Besides, to ease the user calibration procedure, we investigate several methods to model the subject-specific estimation bias, and consequently, propose a novel approach based on weighted regularized least squares regression. The proposed method provides a better calibration modeling than state-of-the-art methods, particularly when using low-resolution and limited calibration data. Being able to operate with low-resolution data also enables to utilize a large field-of-view setup, so that large head movements are allowed. To address aforementioned robustness concerns, we propose to leverage multiple eye appearances simultaneously acquired from various views. In comparison with conventional single view approach, the main benefit of our approach is to more reliably detect gaze features under challenging conditions, especially when they are obstructed due to large head pose or movements, or eye glasses effects. We further propose an adaptive fusion mechanism to effectively combine the gaze outputs obtained from multi-view appearances. To this effect, our mechanism firstly determines the estimation reliability of each gaze output and then performs a reliability-based weighted fusion to compute the overall point of regard. In addition, to address illumination and eye type robustness, the setup is built upon active illumination and robust feature detection methods are developed. The proposed framework and methods are validated through extensive simulations and user experiments featuring 20 subjects. The results demonstrate that our framework provides not only a significant improvement in gaze estimation accuracy but also a notable robustness to real-world conditions, making it suitable for a large spectrum of applications.
Article
Full-text available
Human eye movements are stereotyped and repeatable, but how specific to a normal individual are the quantitative properties of his or her eye movements? We recorded saccades, anti-saccades and smooth-pursuit eye movements in a sample of over 1000 healthy young adults. A randomly selected subsample (10%) of participants were re-tested on a second occasion after a median interval of 18.8 days, allowing us to estimate reliabilities. Each of several derived measures, including latencies, accuracies, velocities, and left-right asymmetries, proved to be very reliable. We give normative means and distributions for each measure and describe the pattern of correlations amongst them. We identify several measures that exhibit significant sex differences. The profile of our oculomotor measures for an individual constitutes a personal oculomotor signature that distinguishes that individual from most other members of the sample of 1000.
Conference Paper
Full-text available
Eye gaze patterns or scanpaths of subjects looking at art while answering questions related to the art have been used to decode those tasks with the use of certain classifiers and machine learning techniques. Some of these techniques require the artwork to be divided into several Areas or Regions of Interest. In this paper, two ways of clustering the static visual stimuli - k-means and the density based clustering algorithm called OPTICS - were used for this purpose. These algorithms were used to cluster the gaze points before classification. The classification success rates were then compared. While it was observed that both k-means and OPTICS gave better success rates than manual clustering, which is itself higher than chance level, OPTICS consistently gave higher success rates than k-means given the right parameter settings. OPTICS also formed clusters that look more intuitive and consistent with the heat map readings than k-means, which formed clusters that look unintuitive and less consistent with the heat map.
Conference Paper
Full-text available
This paper presents a comparison of 10 machine learning algorithms in eyemovement event detection task. The goal was to build a universal algorithm, which could work with any type of the eye-tracking data. Results show that even if tested on noisy data, sampled at a broad range of sampling rates, 5 out of 10 machine learning based universal models perform better than state-of-the-art algorithms. Even more, 7 machine learning based specialist classifiers, trained to work with high quality data, outperform expert coders as reported by Larsson et al. (2015).
Conference Paper
Full-text available
Eye tracking is a technology of growing importance for mobile and wearable systems, particularly for newly emerging virtual and augmented reality applications (VR and AR). Current eye tracking solutions for wearable AR and VR headsets rely on optical tracking and achieve a typical accuracy of 0.5° to 1°. We investigate a high temporal and spatial resolution eye tracking system based on magnetic tracking using scleral search coils. This technique has historically relied on large generator coils several meters in diameter or requires a restraint for the user's head. We propose a wearable scleral search coil tracking system that allows the user to walk around, and eliminates the need for a head restraint or room-sized coils. Our technique involves a unique placement of generator coils as well as a new calibration approach that accounts for the less uniform magnetic field created by the smaller coils. Using this technique, we can estimate the orientation of the eye with a mean calibrated accuracy of 0.094°.
Article
Eye tracking is the process of measuring where one is looking (point of gaze) or the motion of an eye relative to the head. Researchers have developed different algorithms and techniques to automatically track the gaze position and direction, which are helpful in different applications. Research on eye tracking is increasing owing to its ability to facilitate many different tasks, particularly for the elderly or users with special needs. This study aims to explore and review eye tracking concepts, methods, and techniques by further elaborating on efficient and effective modern approaches such as machine learning (ML), Internet of Things (IoT), and cloud computing. These approaches have been in use for more than two decades and are heavily used in the development of recent eye tracking applications. The results of this study indicate that ML and IoT are important aspects in evolving eye tracking applications owing to their ability to learn from existing data, make better decisions, be flexible, and eliminate the need to manually re-calibrate the tracker during the eye tracking process. In addition, they show that eye tracking techniques have more accurate detection results compared with traditional event-detection methods. In addition, various motives and factors in the use of a specific eye tracking technique or application are explored and recommended. Finally, some future directions related to the use of eye tracking in several developed applications are described.
Conference Paper
The aim of this paper is to contribute to a better understanding of children's vision care from the identification to treatment, with, in particular, a better understanding of the use of eye tracking (ET) technologies. While there are indications that these technologies can support vision care, a comprehensive understanding of the possibilities is lacking. Here, we review cross-disciplinary research on performing vision care, and identify current challenges for using and further developing ET technologies. To this end, we describe (1) the involved stakeholders, (2) screening possibilities at schools, and (3) how technology-supported vision screening is used today. Data come from a literature survey of peer-reviewed journal and conference articles, complemented by secondary sources from related projects and products. The focus is on literature after 2000, and in particular, on screening oculomotor dysfunctions (OMD), for school children. The results show that the contributions to state of the art from various research areas are fragmented, in particular regarding the communication between the necessary stakeholders influencing vision care, the handling of general and functional vision care, and between screening and treatment. Further development of ET technologies will likely depend on overcoming these fragmentations. A first step in this direction consists of providing a thorough description of stakeholders, their roles, and requirements enabling communication on children with vision problems.
Chapter
This research used eye movement tracking to study the ways adolescents decode and comprehend multimodal texts. The focus is on eye movement regression between text and picture to investigate how participants use the two-stage information-processing model when attempting to comprehend visual texts. Ten adolescents ranging in age from 14 to 19 were asked to read a series of different types of visually based texts. Specifically, they read six short excerpts from graphic novels that varied widely in the complexity of both textual and visual features. The narratives included graphic novels, graphic retellings of canonical texts, and wordless visual texts.
Article
We study involuntary micro-movements of the eye for biometric identification. While prior studies extract lower-frequency macro-movements from the output of video-based eye-tracking systems and engineer explicit features of these macro-movements, we develop a deep convolutional architecture that processes the raw eye-tracking signal. Compared to prior work, the network attains a lower error rate by one order of magnitude and is faster by two orders of magnitude: it identifies users accurately within seconds.
Article
Recent research have shown that the eye movement data measured by an eye tracker does not necessarily reflect the exact rotations of the eyeball. For example, post-saccadic eye movements may be more reflecting the relative movements between the pupil and the iris rather than the eyeball oscillations. Since, accurate measurement of eye movements is important in many studies, it is crucial to identify different factors that influence the dynamics of the eye movements measured by an eye tracker. Previous studies have shown that deformation of the internal structure of the iris and size of the pupil directly affect the amplitude of the post-saccadic oscillations that are measured by video-based eye trackers that are pupil-based. In this paper, we look at the effect of aging on post-saccadic oscillations. We recorded eye movements from a group of 43 young and 22 older participants during an abstract and a more natural viewing task. The recording was conducted with a video-based eye tracker using the pupil center and corneal reflection. We anticipated that changes in the muscle strength as an effect of aging might affect, directly or indirectly, the post-saccadic oscillations. Results showed that the size of the post-saccadic oscillations were significantly larger for our older group. The results suggests that aging has to be considered as an important factor when studying the post-saccadic eye movements.
Article
Common computational methods for automated eye movement detection - i.e. the task of detecting different types of eye movement in a continuous stream of gaze data - are limited in that they either involve thresholding on hand-crafted signal features, require individual detectors each only detecting a single movement, or require pre-segmented data. We propose a novel approach for eye movement detection that only involves learning a single detector end-to-end, i.e. directly from the continuous gaze data stream and simultaneously for different eye movements without any manual feature crafting or segmentation. Our method is based on convolutional neural networks (CNN) that recently demonstrated superior performance in a variety of tasks in computer vision, signal processing, and machine learning. We further introduce a novel multi-participant dataset that contains scripted and free-viewing sequences of ground-truth annotated saccades, fixations, and smooth pursuits. We show that our CNN-based method outperforms state-of-the-art baselines by a large margin on this challenging dataset, thereby underlining the significant potential of this approach for holistic, robust, and accurate eye movement protocol analysis.
Chapter
This chapter reviews the characteristics of the normal reader's eye movements during reading, abnormal eye movements and the relationship of different types of dyslexia to eye movement patterns. Developmental dyslexia is referred to as a specific reading disability in which the child has normal intelligence and is at least two years behind expected grade level in reading, has normal sensory acuity, and is without neurological damage and emotional problems. The chapter further discusses the types of eye movement disorders that result from lesions of the central nervous system and illustrates how these abnormalities affect reading. The chapter additionally presents eye movement data from two patients with eye movement disorders. It is shown that disordered efferent oculomotor control causes severe and insuperable problems. During reading, the eyes make a series of saccadic eye movements, generally in a left-to-right direction. The term “saccade” is used to distinguish this rapid, jerky type of eye movement, separated by fixational pauses, from pursuit or smooth tracking movements in which the eyes move slowly, maintaining fixation on a moving target or on a stationary point while the head moves. There are three types of saccadic eye movement disorders that are known to influence reading behavior: paralytic or slow saccades that result from lesions involving the basal ganglia, brain stem, and cerebral cortex; impaired saccadic initiation that results from acquired and congenital apraxias involving the left and right parietal lobe; and dysmetric saccades, which result from lesions involving the cerebellum and cerebellar pathways.
Conference Paper
Worldwide, around 10% of the population has dyslexia, a specific learning disorder. Most of previous eye tracking experiments with people with and without dyslexia have found differences between populations suggesting that eye movements reflect the difficulties of individuals with dyslexia. In this paper, we present the first statistical model to predict readers with and without dyslexia using eye tracking measures. The model is trained and evaluated in a 10-fold cross experiment with a dataset composed of 1,135 readings of people with and without dyslexia that were recorded with an eye tracker. Our model, based on a Support Vector Machine binary classifier, reaches 80.18% accuracy using the most informative features. To the best of our knowledge, this is the first time that eye tracking measures are used to predict automatically readers with dyslexia using machine learning.