Application of Eye Movement Analysis in Landscape Visual Quality Evaluation

The existing methods of landscape visual quality evaluation is mostly based on people's subjective feelings,and the objectivity and scientificity of evaluation results are insufficient.As an important means of experimental psychology,eye movement technology can show great advantages and potential in landscape visual quality evaluation.On the basis of combing and summarizing the relevant literature,based on the explanation of the technical principle of eye movement analysis,the application field,research content,technical methods and other aspects of eye movement analysis were reviewed.The application prospect of eye movement technology in landscape visual quality evaluation was explored to provide theoretical reference for the in-depth evaluation and research of landscape visual quality evaluation theory.

Adaptive navigation assistance based on eye movement features in virtual reality

Background Navigation assistance is essential for users when roaming virtual reality scenes;however,the traditional navigation method requires users to manually request a map for viewing,which leads to low immersion and poor user experience.Methods To address this issue,we first collected data on who required navigation assistance in a virtual reality environment,including various eye movement features,such as gaze fixation,pupil size,and gaze angle.Subsequently,we used the boosting-based XGBoost algorithm to train a prediction model and finally used it to predict whether users require navigation assistance in a roaming task.Results After evaluating the performance of the model,the accuracy,precision,recall,and F1-score of our model reached approximately 95%.In addition,by applying the model to a virtual reality scene,an adaptive navigation assistance system based on the real-time eye movement data of the user was implemented.Conclusions Compared with traditional navigation assistance methods,our new adaptive navigation assistance method could enable the user to be more immersive and effective while roaming in a virtual reality(VR)environment.

Eye Movement Modeling Examples as a Teaching Tool for Epidural Block

Introduction: Video examples with task demonstrations by experts, with the expert’s eye movements superimposed on the task, are known as “eye movement modeling examples” (EMME). We performed this study to evaluate if there were improvements in the performance of anesthesia novice trainees when executing the epidural technique after an EMME of epidural block procedure. Methods: We developed an eye movement modeling example (EMME) from eye tracking recordings made by experienced anesthesiologists with more than 20 years of experience. Forty-two PGY3 anesthesia trainees who had never previously performed an epidural block were randomized to receive (study group) or not receive (control group) the EMME video before their institutional training. All the trainees were evaluated every 10 epidural blocks until the end of the rotation period, by an independent, blinded observer using the Global Rating Scale for Epidural Anesthesia (GRS). Results: Trainees who received the EMME training exhibited more respect for the patient’s tissues (P Discussion: This is the first study that has used the EMME for a practical, clinical teaching purpose on real patients and that has used it as an aid in teaching epidural anesthesia. We demonstrated that inexperienced trainees who received the EMME training improved their proficiency at epidural blocks as compared to those who had no EMME training beforehand. Given this result, we welcome further studies to investigate the impact and the role of EMME on clinical teaching in the field of anesthesia.

Eye movement prediction by oculomotor plant Kalman filter with brainstem control

Our work addresses one of the core issues related to Human Computer Interaction （HCI） systems that use eye gaze as an input. This issue is the sensor, transmission and other delays that exist in any eye tracker-based system, reducing its performance. A delay effect can be compensated by an accurate prediction of the eye movement trajectories. This paper introduces a mathematical model of the human eye that uses anatomical properties of the Human Visual System to predict eye movement trajectories. The eye mathematical model is transformed into a Kalman filter form to provide continuous eye position signal prediction during all eye movement types. The model presented in this paper uses brainstem control properties employed during transitions between fast （saccade） and slow （fixations, pursuit） eye movements. Results presented in this paper indicate that the proposed eye model in a Kalman filter form improves the accuracy of eye movement prediction and is capable of a real-time performance. In addition to the HCI systems with the direct eye gaze input, the proposed eye model can be immediately applied for a bit-rate/computational reduction in real-time gaze-contingent systems

How non-rapid eye movement sleep and Alzheimer pathology are linked

Alzheimer's disease(AD)is a multifactorial neurodegenerative disorder characterized by the presence of senile plaques and neurofibrillary tangles.Research attempts to identify characteristic factors that are associated with the presence of the AD pathology on the one hand and that increase the risk of developing AD on the other.Changes in non-rapid eye movement(NREM)sleep may meet both requirements for various reasons.First,NREM-sleep is important for optimal memory function.In addition,studies report that the presence of AD pathology is associated with NREM-sleep changes.Finally,more and more results appear to suggest that sleep problems are not only a symptom of AD but can also increase the risk of AD.Several of these studies suggest that it is primarily a lack of NREM-sleep that is responsible for this increased risk.However,the majority investigated sleep only through subjective reporting,as a result of which NREMsleep could not be analyzed separately.The aim of this literature study is therefore to present the results of the studies that relate the AD pathology and NREM-sleep(registered by electroencephalography).Furthermore,we try to evaluate whether NREM-sleep analysis could be used to support the diagnosis of AD and whether NREM-sleep deficiency could be a causal factor in the development of AD.

Predictive Model of Live Shopping Interest Degree Based on Eye Movement Characteristics and Deep Factorization Machine

In the live broadcast process,eye movement characteristics can reflect people’s attention to the product.However,the existing interest degree predictive model research does not consider the eye movement characteristics.In order to obtain the users’interest in the product more effectively,we will consider the key eye movement indicators.We first collect eye movement characteristics based on the self-developed data processing algorithm fast discriminative model prediction for tracking(FDIMP),and then we add data dimensions to the original data set through information filling.In addition,we apply the deep factorization machine(DeepFM)architecture to simultaneously learn the combination of low-level and high-level features.In order to effectively learn important features and emphasize relatively important features,the multi-head attention mechanism is applied in the interest model.The experimental results on the public data set Criteo show that,compared with the original DeepFM algorithm,the area under curve(AUC)value was improved by up to 9.32%.

Identification of Information-Seeking Behaviors from Air Traffic Controllers′ Eye Movements

Air traffic controllers are the important parts of air traffic management system who are responsible for the safety and efficiency of the system.They make traffic management decisions based on information acquired from various sources.The understanding of their information seeking behaviors is still limited.We aim to identify controllers′ behavior through the examination of the correlations between controllers′eye movements and air traffic.Sixteen air traffic controllers were invited to participate real-time simulation experiments,during which the data of their eye ball movements and air traffic were recorded.Tweny-three air traffic complexity metrics and six eye movements metrics were calculated to examine their relationships.Two correlational methods,Pearson′s correlation and Spearman′s correlation,were tested between every eye-traffic pair of metrics.The results indicate that controllers′two kinds of information-seeking behaviors can be identified from their eye movements:Targets tracking,and confliction recognition.The study on controllers′ eye movements may contribute to the understanding of information-seeking mechanisms leading to the development of more intelligent automations in the future.

Chemogenetic activation of sublaterodorsal tegmental glutamatergic neurons alleviates rapid eye movement sleep behavior disorder symptoms in a chronic rat model of Parkinson disease

Rapid eye movement(REM)sleep behavior disorder(RBD)is a parasomnia that is featured by elevated motor behaviors and dream enactments during REM sleep.Clinical observations show that RBD bears significant relevance with several synucleinopathies such as Lewy body dementia and Parkinson disease(PD),and often develops prior to their diagnosis.Being a potential biomarker of PD,investigating the relationship of RBD symptoms and their emergence in developing PD would provide insight intoits pathogenesis.Here,in a chronic model of PD,rats with daily rotenone treatment exhibited key RBD features,including elevated sleep muscle tone,sleep fragmentation and EEG slowing at different time points.Based on detectedearly alpha synuclein aggregation and neural apoptosis in the sublaterodorsal tegmental nucleus(SLD),an area known to promote REM sleep and maintain sleep muscle atonia,the possible involvement of SLD glutamatergic neurons was interrogated.Via chemogenetic activation of SLD glutamatergic neurons,key RBD symptoms and EEG slowing in REM sleep were alleviated.These results are consistent with a progressive degeneration in REM sleep promoting pathways.Our findings provide a foundation for further studies into RBD and its relationship to neurodegenerative diseases.

Effect of Working Experience on Air Traffic Controller Eye Movement

Eye movement is an important indicator of information-seeking behavior and provides insight into cognitive strategies which are vital for decision-making.Various measures based on eye movements have been proposed to capture humans’ability to process information in a complex environment.The effectiveness of these measures has not yet been fully explored in the field of air traffic management.This paper presents a comparative study on eye-movement measures in air traffic controllers with different levels of working experience.Two commonly investigated oculomotor behaviors,fixation and saccades,together with gaze entropy,are examined.By comparing the statistical properties of the relevant metrics,it is shown that working experience has a notable effect on eye-movement patterns.Both fixation and saccades differ between qualified and novice controllers,with the former type of controller employing more efficient searching strategies.These findings are useful in enhancing the quality of controller training and contributing to an understanding of the information-seeking mechanisms humans use when executing complex tasks.

Experimental platform for moving double-camera system based on binocular vergence eye movements

A control model of binocular vergence eye movements is presented. The control model can reduce blind areas caused by the double cameras in motion platform. In order to validate the model performance, an experimental platform and its control system based on TMS320LF2407 are designed. The control system has its compacted configuration and high reliability. The simulation and experimental results show that the control system can realize binocular vergence movements. Compared with the conventional moving double cameras system, this new system can considerably reduce blind areas.

Interactive method research of dual mode information coordination integration for astronaut gesture and eye movement signals based on hybrid model

The lightweight human-robot interaction model with high real-time,high accuracy,and strong anti-interference capability can be better applied to future lunar surface exploration and construction work.Based on the feature information inputted from the monocular camera,the signal acquisition and processing fusion of the astronaut gesture and eye-movement modal interaction can be performed.Compared with the single mode,the human-robot interaction model of bimodal collaboration can achieve the issuance of complex interactive commands more efficiently.The optimization of the target detection model is executed by inserting attention into YOLOv4 and filtering image motion blur.The central coordinates of pupils are identified by the neural network to realize the human-robot interaction in the eye movement mode.The fusion between the astronaut gesture signal and eye movement signal is performed at the end of the collaborative model to achieve complex command interactions based on a lightweight model.The dataset used in the network training is enhanced and extended to simulate the realistic lunar space interaction environment.The human-robot interaction effects of complex commands in the single mode are compared with those of complex commands in the bimodal collaboration.The experimental results show that the concatenated interaction model of the astronaut gesture and eye movement signals can excavate the bimodal interaction signal better,discriminate the complex interaction commands more quickly,and has stronger signal anti-interference capability based on its stronger feature information mining ability.Compared with the command interaction realized by using the single gesture modal signal and the single eye movement modal signal,the interaction model of bimodal collaboration is shorter about 79%to 91%of the time under the single mode interaction.Regardless of the influence of any image interference item,the overall judgment accuracy of the proposed model can be maintained at about 83%to 97%.The effectiveness of the proposed method is verified.

Sex differences in eye movements and neural oscillations during mental rotation in virtual reality

Virtual reality(VR)has been a promising tool for developing visuospatial tasks.Among visuospatial tasks,mental rotation tasks are widely used in the assessment of visuospatial ability.Males have a distinct advantage in mental rotation ability compared to females,yet it is generally produced by investigations based on two-dimensional(2D)images on a computer screen.Sex differences in mental rotation tasks with three-dimensional(3D)objects in VR were not fully investigated.It is unclear whether the male's advantages in 2D mental rotation tasks are weakened in 3D tasks.The aim of this study was to provide new insights into the understanding of sex differences in mental rotation tasks presented in VR.Here,we developed a VR mental rotation task(VR-MRT)using 3D objects presented by a head-mounted display(HMD)and used VR-based eye tracking and electroencephalography(EEG)to examine eye movements and neural oscillations for males and females.Our results showed that females preferred a piecemeal strategy compared to males,suggesting a significant sex difference in visual strategy.More importantly,we found no significant sex differences in alpha-band and beta-band oscillations related to rotation processes of VR-MRT.These findings indicated that sex differences in the VR-MRT were mainly attributed to the selection of visual strategy rather than the rotation processes.The study helps to comprehensively understand the dominant factors contributing to the sex differences in the VR-MRT.

Eye movement evidence in investigative identification based on experiments

Investigative identification is a routine criminal investigative procedure,the results of which can be used as evidence in litigation.However,some suspects often deny their involvement in the case,and some witnesses may withhold information or misrepresent it,all of which may lead to a miscarriage of justice.This study created a stressful environment and conducted a simulated crime experiment to explore whether eye movement data can be an effective feature for distinguishing perpetrators,innocents,and insiders.The eye movement features—such as the total fixation duration,number of fixations,and first fixation duration—within an area of interest were collected from 83 participants sorted into informed,involved,and innocent groups.The results revealed the following:(1)compared with the object and scene stimuli,subjects with different identities were more likely to exhibit significant differences in eye movement data for the involved and irrelevant portraits.The total fixation duration and the number of fixations can provide a reference for judging whether someone is involved in a case,and the first fixation duration effect was not obvious.(2)Using machine learning algorithms to predict subjects’identities through eye movement features,it was demonstrated that the involved portrait-object-scene model had the best predictive effect.(3)Multiple algorithmic models were used to distinguish subjects’identities,and the highest accuracy of 92.7%was achieved for the informed×innocent group,88%for the innocent×suspect group(including the informed and involved groups),and 84.5%for the involved group.The eye movement analysis method can provide a reference for criminal investigators to distinguish between the perpetrator,insider,and innocent,and offer a novel approach to determining the direction of further investigation and uncovering and verifying case clues.

Effect of Rapid Eye Movement Sleep Behavior Disorder on Obstructive Sleep Apnea Severity and Cognition of Parkinson＇s Disease Patients

Background：Rapid eye movement （REM） sleep behavior disorder （RBD） and obstructive sleep apnea （OSA） are the most common sleep disorders in Parkinson’s disease （PD）. The aim of this study was to identify whether RBD could alleviate OSA severity in PD patients and its effect on cognitive impairment.Methods：From February 2014 to May 2017, we recruited 174 PD patients from the Second Affiliated Hospital of Soochow University, all of whom underwent polysomnography （PSG）. We collected clinical data, PSG results, and compared information between patients with and without RBD or OSA by analysis of covariance. We also investigated the effect of these sleep disorders on cognitive impairment using linear regression.Results：We grouped participants as follows： PD only （n = 53）, PD ＋ OSA （n = 29）, PD ＋ RBD （n = 61）, and PD ＋ RBD ＋ OSA （n = 31）. Minimum oxygen saturation （SaO2） during whole sleep and in REM sleep was higher in PD ＋ RBD ＋ OSA patients than that in PD ＋ OSA patients. PD ＋ RBD patients had worse Mini-Mental Status Examination and Montreal Cognitive Assessment （MoCA） scores than those in the PD group （P 〈 0.001）, especially in visuospatial/executive, attention, and memory functions. The PD ＋ OSA group performed worse than the PD group in the delayed recall domain. After adjusting for age, sex, body mass index, education, disease severity, and other sleep disorders, MoCA was negatively associated with OSA （β = ？0.736, P = 0.043） and RBD （β = ？2.575, P 〈 0.001）. The severity of RBD （tonic/phasic electromyography activity） and OSA （apnea-hypopnea index/oxygen desaturation index/minimum SaO2） were also associated with MoCA. The adjusted β values of RBD-related parameters were higher than that for OSA.Conclusions：We found that RBD alleviated OSA severity; however, RBD and OSA together exacerbated PD cognitive impairment. Further studies are needed to evaluate whether OSA treatment can improve cognition in PD.

Rapid Eye Movement Sleep Behavior Disorder Symptoms Correlate with Domains of Cognitive Impairment in Parkinson＆#39;s Disease

Background： Rapid eye movement （REM） sleep behavior disorder （RBD） may be a risk factor for cognitive impairment in patients with Parkinson＆#39;s disease （PD）.However, little is known regarding the relation between the severity of RBD and the different domains of cognitive impairment.The aim of this study was： （1） to investigate the domains of cognitive impairment in patients with PD and RBD, and （2） to explore risk factors for PD-mild cognitive impairment （PD-MCI） and the relationship between RBD severity and impairment in different cognitive domains in PD.Methods： The participants were grouped as follows： PD without RBD （PD-RBD;n =42）, PD with RBD （PD ＋ RBD;n =32）, idiopathic RBD （iRBD;n =15）, and healthy controls （HCs;n =36）.All participants completed a battery of neuropsychological assessment of attention and working memory, executive function, language, memory, and visuospatial function.The information of basic demographics, diseases and medication history, and motor and nonmotor manifestations was obtained and compared between PD-RBD and PD ＋ RBD groups.Particular attention was paid to the severity of RBD assessed by the RBD Questionnaire-Hong Kong （RBDQ-HK） and the RBD Screening Questionnaire （RBDSQ）, then we further examined associations between the severity of RBD symptoms and cognitive levels via correlation analysis.Results： Compared to PD-RBD subjects, PD ＋ RBD patients were more likely to have olfactory dysfunction and their Epworth Sleepiness Scale scores were higher （P 〈 0.05）.During neuropsychological testing, PD ＋ RBD patients performed worse than PD-RBD patients, including delayed memory function, especially.The MCI rates were 33%, 63%, 33%, and 8% for PD-RBD, PD ＋ RBD, iRBD, and HC groups, respectively.RBD was an important factor for the PD-MCI variance （odds ratio =5.204, P =0.018）.During correlation analysis, higher RBDSQ and RBDQ-HK scores were significantly associated with poorer performance on the Trail Making Test-B （errors） and Auditory Verbal Learning Test （delayed recall） and higher RBD-HK scores were also associated with Rey-Osterrieth complex figure （copy） results.Conclusions： When PD-RBD and PD ＋ RBD patients have equivalent motor symptoms, PD ＋ RBD patients still have more olfactory dysfunction and worse daytime somnolence.RBD is an important risk factor for MCI, including delayed memory.Deficits in executive function, verbal delayed memory, and visuospatial function were consistently associated with more severe RBD symptoms.

Clinical features of Parkinson’s disease with and without rapid eye movement sleep behavior disorder

Background:Rapid eye movement sleep behavior disorder(RBD)and Parkinson’s disease(PD)are two distinct clinical diseases but they share some common pathological and anatomical characteristics.This study aims to confirm the clinical features of RBD in Chinese PD patients.Methods:One hundred fifty PD patients were enrolled from the Parkinson`s disease and Movement Disorders Center in Department of Neurology,Shanghai General Hospital from January 2013 to August 2014.This study examined PD patients with or without RBD as determined by the REM Sleep Behavior Disorder Screening Questionnaire(RBDSQ),assessed motor subtype by Unified PD Rating Scale(UPDRS)III at“on”state,and compared the sub-scale scores representing tremor,rigidity,appendicular and axial.Investigators also assessed the Hamilton Anxiety Scale(HAMA),Hamilton Depression Scale(HAMD),Mini-Mental State Examination(MMSE),Clinical Dementia Rating(CDR),and Parkinson’s disease Sleep Scale(PDSS).Results:One hundred fourty one PD patients entered the final study.30(21.28%)PD patients had probable RBD(pRBD)diagnosed with a RBDSQ score of 6 or above.There were no significant differences for age,including age of PD onset and PD duration,gender,smoking status,alcohol or coffee use,presence of anosmia or freezing,UPDRS III,and H-Y stages between the pRBD+and pRBD−groups.pRBD+group had lower MMSE scores,higher PDSS scores,and pRBD+PD patients had more prominent proportion in anxiety,depression,constipation,hallucination and a greater prevalence of orthostatic hypotension.Conclusion:pRBD+PD patients exhibited greater changes in non-motor symptoms.However,there was no increase in motor deficits.

Eye movements characteristics of Chinese dyslexic children in picture searching

Background Reading Chinese, a kind of ideogram, relies more on visual cognition. The visuospatial cognitive deficit of Chinese dyslexia is an interesting topic that has received much attention. The purpose of current research was to explore the visuopatial cognitive characteristics of Chinese dyslexic children by studying their eye movements via a picture searching test. Methods According to the diagnostic criteria defined by ICD-10, twenty-eight dyslexic children （mean age （10.12±1.42） years） were enrolled from the Clinic of Children Behavioral Disorder in the third affiliated hospital of Sun Yat-sen University. And 28 normally reading children （mean age （10.06±1.29） years）, 1：1 matched by age, sex, grade and family condition were chosen from an elementary school in Guangzhou as a control group. Four groups of pictures （cock, accident, canyon, meditate） from Picture Vocabulary Test were chosen as eye movement experiment targets. All the subjects carried out the picture searching task and their eye movement data were recorded by an Eyelink II High-Speed Eye Tracker. The duration time, average fixation duration, average saccade amplitude, fixation counts and saccade counts were compared between the two groups of children. Results The dyslexic children had longer total fixation duration and average fixation duration （F=-7.711, P 〈0.01; F=-4.520, P 〈0.05）, more fixation counts and saccade counts （F=-7.498, P 〈0.01; F=-11.040, P 〈0.01）, and a smaller average saccade amplitude （F=-29.743, P 〈0.01） compared with controls. But their performance in the picture vocabulary test was the same as those of the control group. The eye movement indexes were affected by the difficulty of the pictures and words, all eye movement indexes, except saccade amplitude, had a significant difference within groups （P 〈0.05）. Conclusions Chinese dyslexic children have abnormal eye movements in picture searching, applying slow fixations, more fixations and small and frequent saccades. Their abnormal eye movement mode reflects the poor ability and strategy of visual information processing.

Eye-movement Patterns of Chinese Children with Developmental Dyslexia during the Stroop Test

Objective To compare the eye-movement patterns of Chinese children with developmental dyslexia（DD children） with those of non-dyslexic children as they perform the Stroop Color and Word Test（SCWT）, and to explore the relationship between their eye-movement patterns and interference effect. Methods An EyeLink II was used to record the eye-movement parameters of 32 DD children and 37 non-dyslexic children as they performed the SCWT. The independent samples t-test and repeated measures were used to analyze behavioral and eye-movement parameters. Results Compared to the control group, Chinese DD children presented lower accuracy（F = 8.488）, slower response time（F = 25.306）, and larger interference effect（t = 2.29）; Chinese DD children also exhibited lower frequency of fixations（F = 6.069）, greater numbers of saccades（F = 7.914） and fixations（F = 5.272）, and shorter mean saccade distance（F = 4.03）. All behavioral and eye-movement parameters differed significantly among the three tasks in the SCWT. There was significant interaction between groups and tasks in accuracy（F = 5.844）, and marginally significant interaction in response time（F = 3.040）. Chinese DD children tended to have lower accuracy and longer response time than the control group in the ＇color-word naming＇ task. Conclusion Compared to non-dyslexic children, Chinese DD children are subject to a stronger interference effect. When performing the SCWT, Chinese DD children exhibit abnormal eye-movement patterns, namely shorter mean saccade distance, lower frequency of fixations, and more fixations and saccades. These abnormal eye movements may be relatively stable oculomotor patterns of DD children performing visual processing, and not influenced by impaired interference effect.

Comparison Study of Polysomnographic Features in Multiple System Atrophy-cerebellar Types Combined with and without Rapid Eye Movement Sleep Behavior Disorder

Background： The brain stem is found to be impaired in multiple system atrophy-ccrcbellar types （MSA-C）. Rapid eye movement （REM） sleep behavior disorder （RBD） is reported as a marker of progressive brain stem dysfunction. Few systematic studies about the sleep disturbances in MSA-C patients combined with or without RBD were reported. This study aimed to explore the polysomnographic （PSG） features of sleep disturbances between MSA-C patients with and without RBD. Methods： Totally, 46 MSA-C patients （23 with RBD, and 23 without RBD） were enrolled in this study. All patients underwent a structured interview for their demographic data, history of sleep pattern, and movement disorders; and then, overnight video-PSG was performed in each patient. All the records were evaluated by specialists at the Sleep Medicine Clinic for RBD and the Movement Disorder Clinic for MSA-C. The Student＇s t-test, Mann-Whitney U-test for continuous variables, and the Chi-square test for categorical variables were used in this study. Results： MSA-C patients with RBD had younger visiting age （52.6 ± 7.4 vs. 56.7 ± 6.0 years, P = 0.046） and shorter duration of the disease （12.0 [12.0, 24.0] vs. 24.0 [14.0, 36.0] months, P 0.009） than MSA-C patients without RBD. MSA-C with RBD had shorter REM sleep latency （111.7 ± 48.2 vs. 157.0 ± 68.8 rain, P = 0.042）, higher percentage of REM sleep （14.9% ±4.0% vs. 10.0% ± 3.2%, P = 0.019）, and lower Stage 1 （9.5% ±7.2% vs. 15.9% ±8.0%, P= 0.027） than MSA-C without RBD. Moreover, MSA-C patients with RBD had more decreased sleep efficiency （52.4% ±12.6% vs. 65.8% ±15.9%, P = 0.029） than that without RBD. Conclusions： In addition to the RBD, MSA-C patients with RBD had other more severe sleep disturbances than those without RBD. The sleep disorders of MSA patients might be associated with the progress of the disease.

Identification of Eye Movements from Non-frontal Face Images for Eye-controlled Systems

The novel eye-based human-computer interaction(HCI) system aims to provide people, especially, disabled persons,a new way of communication with surroundings. It adopts a series of continual eye movements as input to perform simple control activities. Identification of eye movements is the crucial technology in these eye-based HCI systems. At present, researches on eye movement identification mainly focus on frontal face images. In fact, acquisition of non-frontal face images is more reasonable in real applications. In this paper, we discuss the identification process of eye movements from non-frontal face images. Firstly, the original head-shoulder images of 0?–±60?azimuths are sampled without any auxiliary light source. Secondly, the non-frontal face region is detected by using the Adaboost cascade classifiers. After that, we roughly extract eye windows by the integral projection function.Then, we propose a new method to calculate the x- y coordinates of the pupil center point by searching the minimal intensity value in the eye windows. According to the trajectory of the pupil center points, different eye movements(eye moving left, right, up or down)are successfully identified. A set of experiments is presented.