Search

Abstract To investigate the associations between corneal curvature (CC) and other anterior segment biometrics in young myopic adults. In this retrospective multi-center study, 7893 young myopic adults were included. CC and other anterior segment biometrics were measured by Scheimpflug imaging (Pentacam). CC was defined as SimK at central 3 mm area, and other anterior segment biometrics included white-to-white corneal diameter (WTW), central corneal thickness (CCT), corneal volume (CV) at 3 mm, 5 mm, and 7 mm area, anterior corneal astigmatism (ACA), posterior corneal astigmatism (PCA), anterior corneal eccentricity (ACE) and asphericity (ACAP), posterior corneal eccentricity (PCE) and asphericity (PCAP), anterior chamber depth (ACD), and anterior chamber volume (ACV). Univariate regression analyses were used to assess the associations between CC and other anterior segment biometrics, and multivariate regression analyses were further performed to adjusted for age, gender and spherical equivalent. CC was higher in patients of female gender and higher myopia (all P

Abstract Purpose To evaluate the association of body stature with ocular biometrics and refraction in preschool children. Methods A cross-sectional, school-based study was conducted in Shenzhen, China. Preschool children aged 3 to 6 from 10 randomly-selected kindergartens were recruited. Ocular biometric parameters, including axial length (AL), anterior chamber depth (ACD), vitreous chamber depth (VCD), corneal radius curvature (CR), axial length to corneal radius ratio (AL-to-CR ratio) and lens thickness (LT) were measured using non-contact partial-coherence laser interferometry. Cycloplegic refractions were obtained by a desktop autorefractor. Body height and weight were measured using standard procedures. The association between body stature and ocular biometrics were analyzed with univariable and multivariable regression model. Results A total of 373 preschoolers were included. AL, ACD, VCD, CR, and AL-to-CR ratio, were positively associated with height and weight (p

Abstract The interactions between white-to-white corneal diameter (WTW) and other ocular biometrics are important for planning of refractive surgery and understanding of ocular structural changes in myopia, but such interactions are rarely investigated in young myopic adults. This is a retrospective study involving 7893 young myopic adults from five centers. WTW and other ocular biometrics were measured by Pentacam. The ocular biometrics included anterior corneal curvature (AK) and posterior corneal curvature (PK), central corneal thickness (CCT) and corneal volume (CV), anterior and corneal eccentricity and asphericity, anterior corneal astigmatism (ACA) and posterior corneal astigmatism, anterior chamber depth (ACD), and anterior chamber volume (ACV). The ocular biometrics were compared among eyes of different WTW quartiles. Multivariate linear regression was used to assess the linear associations between WTW and other ocular biometrics adjusting for age, gender and spherical equivalent. In eyes of different WTW quartiles, other ocular biometrics were also significantly different (all P

Tong Bao,1,&ast; Liru Qin,2,&ast; Guimei Hou,1 Hongmei Jiang,1 Lifeng Wang,1 Ying Wang,1 Junhui Wu,1 Jinli Wang,3 Yunlei Pang4 1Department of Ophthalmological Examination, Chifeng Chaoju Eye Hospital, Chifeng, People’s Republic of China; 2Department of Ophthalmology, Inner Mongolia Baogang Hospital, Baotou, People’s Republic of China; 3Department of Cataract, Chifeng Chaoju Eye Hospital, Chifeng, People’s Republic of China; 4Department of Ophthalmic Plastic Surgery, Chifeng Chaoju Eye Hospital, Chifeng, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Jinli Wang, Department of Cataract, Chifeng Chaoju Eye Hospital, Chifeng, People’s Republic of China, Email chaojueyewjl66@163.com Yunlei Pang, Department of Ophthalmic Plastic Surgery, Chifeng Chaoju Eye Hospital, Chifeng, People’s Republic of China, Email 29483645@qq.comObjective: To investigate the association between the peripheral refractive errors of the fundus in different regions and moderate and high myopia.Methods: In this case-control study, 320 children and adolescents aged 6 to 18 years were recruited. Peripheral refractive errors were measured using multispectral retinal refractive topography (MRT). Spherical equivalent (SE) and cylinder errors were classified into low, moderate, and high categories based on the magnitude range. Logistic regression was performed to test the factors associated with myopia.Results: There were 152 participants with low myopia and 168 participants with moderate and high myopia included in the current study. Participants with moderate and high myopia were most likely to be older, with larger axial length (AL), lower SE, less time to watch electronic devices on the weekend, a higher difference between central refractive error and paracentral refractive error from the superior side of the retina (RDV-S), but a smaller difference between the central refractive error and paracentral refractive error from the inferior side of the retina (RDV-I) than those with low myopia (all P < 0.05). After logistic analysis, female sex (odds ratio [OR] = 4.14; 95% confidence interval [CI] = 2.16– 7.97, P < 0.001), AL (OR = 6.88, 95% CI = 4.33– 10.93, P < 0.001), and RDV-I (OR = 0.52, 95% CI = 0.32– 0.86, P = 0.010) were independent factors for moderate and high myopia.Conclusion: Our study demonstrated that the retina peripheral refraction of the eyes (RDV-I) was associated with moderate and high myopia, and RDV-S was only associated with high myopia.Keywords: peripheral refractive errors, myopia, spherical equivalent, logistic analysis, ocular biometrics

To investigate the associations between corneal curvature (CC) and other anterior segment biometrics in young myopic adults. In this retrospective multi-center study, 7893 young myopic adults were included. CC and other anterior segment biometrics were measured by Scheimpflug imaging (Pentacam). CC was defined as SimK at central 3 mm area, and other anterior segment biometrics included white-to-white corneal diameter (WTW), central corneal thickness (CCT), corneal volume (CV) at 3 mm, 5 mm, and 7 mm area, anterior corneal astigmatism (ACA), posterior corneal astigmatism (PCA), anterior corneal eccentricity (ACE) and asphericity (ACAP), posterior corneal eccentricity (PCE) and asphericity (PCAP), anterior chamber depth (ACD), and anterior chamber volume (ACV). Univariate regression analyses were used to assess the associations between CC and other anterior segment biometrics, and multivariate regression analyses were further performed to adjusted for age, gender and spherical equivalent. CC was higher in patients of female gender and higher myopia (all P < 0.05). Eyes in higher CC quartiles had lower WTW, thinner CCT, lower CV at 3 mm and 5 mm, lower ACD, and lower ACV (all P < 0.001), but had larger ACA, larger PCA, less PCE and less PCAP (all P < 0.001), compared to eyes in lower CC quartiles. The trends of CV at 7 mm, ACE and ACAP were inconsistent in different CC quartiles. After adjusting for age, gender and spherical equivalent with multivariate linear regression, CC was positively correlated to CV at 7 mm (βs = 0.069), ACA (βs = 0.194), PCA (βs = 0.187), ACE (βs = 0.072), PCAP (βs = 0.087), and ACD (βs = 0.027) (all P < 0.05), but was negatively correlated to WTW (βs = − 0.432), CCT (βs = − 0.087), CV-3 mm (βs = − 0.066), ACAP (βs = − 0.043), PCE (βs = − 0.062), and ACV (βs = − 0.188) (all P < 0.05). CC was associated with most of the other anterior segment biometrics in young myopic adults. These associations are important for better understanding of the interactions between different anterior segment structures in young myopic patients, and are also useful for the exploration of the pathogenesis of myopia. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the association of body stature with ocular biometrics and refraction in preschool children. Methods: A cross-sectional, school-based study was conducted in Shenzhen, China. Preschool children aged 3 to 6 from 10 randomly-selected kindergartens were recruited. Ocular biometric parameters, including axial length (AL), anterior chamber depth (ACD), vitreous chamber depth (VCD), corneal radius curvature (CR), axial length to corneal radius ratio (AL-to-CR ratio) and lens thickness (LT) were measured using non-contact partial-coherence laser interferometry. Cycloplegic refractions were obtained by a desktop autorefractor. Body height and weight were measured using standard procedures. The association between body stature and ocular biometrics were analyzed with univariable and multivariable regression model. Results: A total of 373 preschoolers were included. AL, ACD, VCD, CR, and AL-to-CR ratio, were positively associated with height and weight (p < 0.05), whereas LT was negatively associated with height and weight (p < 0.01). No association was observed between stature and central cornea thickness and refraction. After adjusted for age and gender in a multivariable regression model, AL had positive associations with height (p < 0.01) and weight (p < 0.01). However, refraction had no significant association with stature parameters. Conclusion: Taller and heavier preschoolers had eyes with longer AL, deeper vitreous chamber, and flatter cornea. The significant associations between body stature and ocular biometric parameters reveal the driving influence of body development on the growth of eyeballs in preschoolers. [ABSTRACT FROM AUTHOR]

The interactions between white-to-white corneal diameter (WTW) and other ocular biometrics are important for planning of refractive surgery and understanding of ocular structural changes in myopia, but such interactions are rarely investigated in young myopic adults. This is a retrospective study involving 7893 young myopic adults from five centers. WTW and other ocular biometrics were measured by Pentacam. The ocular biometrics included anterior corneal curvature (AK) and posterior corneal curvature (PK), central corneal thickness (CCT) and corneal volume (CV), anterior and corneal eccentricity and asphericity, anterior corneal astigmatism (ACA) and posterior corneal astigmatism, anterior chamber depth (ACD), and anterior chamber volume (ACV). The ocular biometrics were compared among eyes of different WTW quartiles. Multivariate linear regression was used to assess the linear associations between WTW and other ocular biometrics adjusting for age, gender and spherical equivalent. In eyes of different WTW quartiles, other ocular biometrics were also significantly different (all P < 0.05). After adjusting for age, gender and spherical equivalent, WTW was positively correlated to AK (β = 0.26 to 0.29), ACA (β = 0.13), anterior corneal asphericity (β = 0.05), PK (β = 0.33 to 0.34), posterior corneal asphericity (β = 0.13), ACD (β = 0.29), and ACV (β = 40.69), and was negatively correlated to CCT (β = − 6.83), CV (β = − 0.06 to − 0.78), anterior corneal eccentricity (β = − 0.035), and posterior corneal eccentricity (β = − 0.14) (all P < 0.001). In conclusion, we found that in young myopic adults, larger WTW was associated with thinner corneal thickness, flatter corneal curvature, more anterior corneal toricity, less corneal eccentricity and asphericity, and broader anterior chamber. Our findings may fill in the gap of literature, and help us better understand how the anterior segment structures interact with the WTW in myopia. [ABSTRACT FROM AUTHOR]

The sclera has recently been gaining attention as a biometric modality due to its various desirable characteristics. A key step in any type of ocular biometric recognition, including sclera recognition, is the segmentation of the relevant part(s) of the eye. However, the high computational complexity of the (deep) segmentation models used in this task can limit their applicability on resource-constrained devices such as smartphones or head-mounted displays. As these devices are a common desired target for such biometric systems, lightweight solutions for ocular segmentation are critically needed. To address this issue, this paper introduces IPAD (Iterative Pruning with Activation Deviation), a novel method for developing lightweight convolutional networks, that is based on model pruning. IPAD uses a novel filter-activation-based criterion (ADC) to determine low-importance filters and employs an iterative model pruning procedure to derive the final lightweight model. To evaluate the proposed pruning procedure, we conduct extensive experiments with two diverse segmentation models, over four publicly available datasets (SBVPI, SLD, SMD and MOBIUS), in four distinct problem configurations and in comparison to state-of-the-art methods from the literature. The results of the experiments show that the proposed filter-importance criterion outperforms the standard L1 and L2 approaches from the literature. Furthermore, the results also suggest that: (i) the pruned models are able to retain (or even improve on) the performance of the unpruned originals, as long as they are not over-pruned, with RITnet and U-Net at 50% of their original FLOPs reaching up to 4% and 7% higher IoU values than their unpruned versions, respectively, (ii) smaller models require more careful pruning, as the pruning process can hurt the model’s generalization capabilities, and (iii) the novel criterion most convincingly outperforms the classic approaches when sufficient training data is available, implying that the abundance of data leads to more robust activation-based importance computation.

With the unprecedented mobile technology revolution, mobile devices have transcended from being the primary means of communication to an all-in-one platform. Consequently, an increasing number of individuals are accessing online services for e-commerce and banking via smartphones instead of traditional desktop computers. However, smartphones can be easily misplaced, lost, or stolen more often than other computing devices, thereby demanding effective user authentication mechanisms for device unlocking and secured transactions. Ocular biometrics has obtained significant attention from academia and industry because of its accuracy, security, and ease of use in mobile devices. Several studies have demonstrated the efficacy of deep learning models for ocular-based user authentication on smartphones. However, these high-performing models require enormous space and computational complexity due to the millions of parameters and computations involved. These requirements make their deployment on resource-constrained smartphones challenging. To this end, a handful of studies have been proposed for compact-size ocular-based deep-learning models to facilitate on-device deployment. In this paper, we conduct a thorough analysis of the existing neural network compression techniques applied as a standalone and in combination for ocular-based user authentication. Extensive experimental validation is performed on the two latest large-scale ocular biometric datasets collected using smartphones, namely, UFPR and VISOB 2.0 datasets. This study benchmarks the results of advanced compression techniques for further research and development in lightweight models for ocular-based user authentication on smartphones.

This study aimed to investigate changes in non-cycloplegic ocular biometrics during the initial six months of treatment with a 0.1% atropine loading dose and 0.01% atropine compared with a placebo and analyze their contribution to the treatment effect on cycloplegic spherical equivalent (SE) progression. The study was based on a randomized, double-masked, placebo-controlled, multicenter trial evaluating a 0.1% atropine six-month loading dose and 0.01% atropine in reducing myopic progression in Danish children. The treatment phase was 24 months, and the washout phase was 12 months. Parameters measured included changes in axial length (AL), anterior chamber depth (ACD), lens thickness (LT), vitreous chamber depth (VCD), and choroidal thickness (ChT), while cycloplegic SE and lens power were calculated. Longitudinal changes and contributions to treatment effects were analyzed using constrained linear mixed models and mediation analyses, respectively. After six months, AL was 0.13 mm shorter (95% confidence interval [CI], −0.18 to −0.07 [adjusted p < 0.001]) and 0.06 mm shorter (95% CI, −0.11 to −0.01 [adjusted p = 0.060]) with a 0.1% atropine loading dose and 0.01% atropine, respectively, compared to the placebo group. Similar concentration-dependent changes were found with ACD, LT, VCD, ChT, and cycloplegic SE. Although the treatment effects trended toward concentration-dependent responses, only the treatment effect mediated by AL at three months differed significantly between 0.01% atropine and a 0.1% atropine loading dose (adjusted p = 0.023). Several ocular biometrics, including AL, ACD, and LT, changed dose-dependently during low-dose atropine treatment. Moreover, the treatment effect of atropine on SE progression was mediated by a subset of ocular biometrics, mainly AL, with trends toward concentration dependency and distributional shifts over time. [ABSTRACT FROM AUTHOR]

Abstract Corneal volume (CV) is a useful index for detecting forme fruste keratoconus from normal corneas. It can be used to evaluate the whole cornea, since it can measure corneal areas up to 10 mm in diameter. Thus, CV has become the clinicians' interest as a diagnostic tool of corneal ectatic disease and a measure of corneal integrity to determine suitability for refractive surgery. We conducted a cross‐sectional study including 7893 myopic patients from five ophthalmic centers to investigate the distribution pattern of CV. Our study showed that distribution of CV‐3, CV‐5, and CV‐7 mm were slightly positively skewed and the 2.5th to 97.5th percentiles were 3.6–4.4, 10.4–12.8, 22.5–27.5 mm3, respectively. Central corneal thickness (CCT) was significantly correlated with CV in all measurement regions. The correlation between CV and CCT showed an inconsistent trend with the increase of age. The correlation coefficient between CV and CCT did not change significantly with the increase of myopia degree in low to moderate myopia, but fluctuated significantly in high myopia (less than −6.0 diopters). According to our results, corneal volume follows a slightly positively skewed distribution pattern in myopic Chinese patients. The information is useful for screening refractive surgery candidates and assessing the risk of corneal refractive surgery.

Abstract Purpose To investigate the prevalence of myopia in Chinese primary school students and their ocular biometrics including axial length (AL), corneal radius of curvature (CRC) and spherical equivalent refraction (SER). To analyze their association with potential myopia risk factors, such as body mass index (BMI), cram school, time of outdoor activity and electronic screen use. Methods In this cross-sectional study of 4500 primary school students from 5 schools, participants underwent refraction using non-cycloplegic autorefractor and visual acuity testing. A follow-up study in the same schools was conducted in 2022. Myopia was defined as SER ≤ -0.50 diopter (D) and uncorrected visual acuity (UCVA)

Purpose: To investigate the characteristics of eyes with large variations in predicted refraction using four traditional intraocular lens (IOL) formulas and evaluate the accuracy of new-generation intraocular lens power calculation formulas. Methods: Eyes that had variation in predicted refraction (≥ 0.75 D) using four traditional formulas (SRK/T, Holladay 1, Hoffer Q, and Haigis formulas) were included. Axial length (AL), anterior chamber depth (ACD), average keratometry (AK), and the ratio of axial length to corneal radius (AL/CR) were measured. New-generation formulas (Barrett Universal II, Emmetropia Verifying Optical 2.0, Kane, and Pearl-DGS formulas) and traditional formulas were compared. The median absolute error (MedAE) was the main parameter to evaluate the accuracy of formulas. Results: A total of 79 participants (79 eyes) who had variation in predicted refraction of (≥ 0.75 D) using four traditional formulas out of 510 eyes (510 patients) underwent uncomplicated cataract surgeries. The Barrett Universal II (0.29 D), EVO 2.0 (0.31 D), Kane (0.30 D), and Pearl-DGS (0.33 D) formulas produced significantly lower median absolute errors (MedAEs) than the Hoffer Q (0.61 D) and Holladay 1 (0.59 D) formulas (P < 0.01). The Wang-Koch (WK) adjustment significantly improved the accuracy of the Holladay 1 formula in long eyes (P < 0.001). Conclusions: Abnormal AL, ACD, and AK are more likely to lead to prediction errors using traditional formulas. New-generation formulas and traditional formulas with WK adjustment showed satisfactory prediction accuracy. [ABSTRACT FROM AUTHOR]

BackgroundSeveral studies have shown that various concentrations of low-concentration atropine can reduce myopia progression and control axial elongation safely and efficiently in children. The aim of this study was to evaluate the effects of 0.02% and 0.01% atropine on ocular biometrics.MethodsCohort study. 138 and 142 children were randomized to use either 0.02% or 0.01% atropine eye drops, respectively. They wore single-vision (SV) spectacles, with one drop of atropine applied to both eyes nightly. Controls (N = 120) wore only SV spectacles. Ocular and corneal astigmatism were calculated using Thibos vector analysis and split into J0 and J45.ResultsThe changes in cycloplegic spherical equivalent refraction (SER) and axial length (AL) were −0.81 ± 0.52D, −0.94 ± 0.59D, and −1.33 ± 0.72D; and 0.62 ± 0.29 mm, 0.72 ± 0.31 mm, and 0.89 ± 0.35 mm in the 0.02% and 0.01% atropine and control groups, respectively (all P 0.05). Intraocular pressure (IOP), corneal curvature, ocular astigmatism J45, and corneal astigmatism (including J0 and J45) remained stable over time in the three groups (all P > 0.05). The contributions to SER progression from the changes in AL, lens and corneal power of the three groups were similar (P > 0.05). The contribution of AL change alone to the change in SER was 56.3%, 63.4% and 78.2% in the above corresponding three groups.ConclusionsAfter 2 years, 0.02% and 0.01% atropine had no clinical effects on corneal and lens power, ocular and corneal astigmatism, ACD or IOP compared to the control group. 0.02% and 0.01% atropine helped to control myopia progression mainly by reducing AL elongation.

Purpose: To identify 24-h changes in ocular biometric parameters in subjects with ocular hypertension (OHT), and to determine if an intraocular pressure (IOP)-lowering drug alters these parameters. Methods: Thirty volunteers with OHT (58.6 ± 9.2 years of age) were enrolled in this randomized, double-masked, placebo-controlled, crossover study. Participants self-administered 0.2% brimonidine or placebo 3 times daily for 6 weeks. Measurements of seated and supine IOP, central cornea thickness (CCT), anterior chamber depth (ACD), axial length (AXL), and lens thickness were made at 8 am, 3 pm, 8 pm, and 3 am. Statistical tests were Student's 2-tailed paired t-tests or 2-way analysis of variance (ANOVA) followed by one-way ANOVA and post hoc testing. Results: Time of day had a significant effect on IOP, CCT, ACD, and AXL. In placebo-treated eyes, CCT was greater at 3 am than at any other time (P < 0.01), ACD and AXL were greater at 3 am and 8 pm than at 3 pm (P < 0.01). Daytime IOPs were higher than nighttime (seated, P = 0.007; supine, P = 0.018), and supine IOP at night was higher than seated IOP during the day (P < 0.001). Brimonidine did not lower IOP at night nor did it alter the 24-h patterns of CCT, ACD, and AXL. Conclusions: Ocular biometric parameters exhibit characteristic 24-h fluctuations in patients with OHT. At night compared with day, the supine IOP increases, the cornea thickens, the anterior chamber deepens, and the AXL increases. Brimonidine does not alter these parameters at times when it lowers IOP (day) nor when it does not (night). Clinical Trial Registration number: NCT0132419. [ABSTRACT FROM AUTHOR]

The massive availability of cameras and personal devices results in a wide variability between imaging conditions, producing large intra-class variations and a significant performance drop if images from heterogeneous environments are compared for person recognition purposes. However, as biometric solutions are extensively deployed, it will be common to replace acquisition hardware as it is damaged or newer designs appear or to exchange information between agencies or applications operating in different environments. Furthermore, variations in imaging spectral bands can also occur. For example, face images are typically acquired in the visible (VIS) spectrum, while iris images are usually captured in the near-infrared (NIR) spectrum. However, cross-spectrum comparison may be needed if, for example, a face image obtained from a surveillance camera needs to be compared against a legacy database of iris imagery. Here, we propose a multialgorithmic approach to cope with periocular images captured with different sensors. With face masks in the front line to fight against the COVID-19 pandemic, periocular recognition is regaining popularity since it is the only region of the face that remains visible. As a solution to the mentioned cross-sensor issues, we integrate different biometric comparators using a score fusion scheme based on linear logistic regression This approach is trained to improve the discriminating ability and, at the same time, to encourage that fused scores are represented by log-likelihood ratios. This allows easy interpretation of output scores and the use of Bayes thresholds for optimal decision-making since scores from different comparators are in the same probabilistic range. We evaluate our approach in the context of the 1st Cross-Spectral Iris/Periocular Competition, whose aim was to compare person recognition approaches when periocular data from visible and near-infrared images is matched. The proposed fusion approach achieves reductions in the error rates of up to 30%–40% in cross-spectral NIR–VIS comparisons with respect to the best individual system, leading to an EER of 0.2% and a FRR of just 0.47% at FAR = 0.01%. It also represents the best overall approach of the mentioned competition. Experiments are also reported with a database of VIS images from two different smartphones as well, achieving even bigger relative improvements and similar performance numbers. We also discuss the proposed approach from the point of view of template size and computation times, with the most computationally heavy comparator playing an important role in the results. Lastly, the proposed method is shown to outperform other popular fusion approaches in multibiometrics, such as the average of scores, Support Vector Machines, or Random Forest. • Multialgorithmic approach for periocular recognition using images from different sensors. • Integration of systems at the score level using linear logistic regression fusion. • Evaluation in both visible-to-visible and visible-to-near-infrared comparisons. • Comparison with popular fusion approaches employed in multibiometrics. • Best overall approach evaluated in cross-eyed periocular competitions. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the prevalence of myopia in Chinese primary school students and their ocular biometrics including axial length (AL), corneal radius of curvature (CRC) and spherical equivalent refraction (SER). To analyze their association with potential myopia risk factors, such as body mass index (BMI), cram school, time of outdoor activity and electronic screen use.Methods: In this cross-sectional study of 4500 primary school students from 5 schools, participants underwent refraction using non-cycloplegic autorefractor and visual acuity testing. A follow-up study in the same schools was conducted in 2022. Myopia was defined as SER ≤ -0.50 diopter (D) and uncorrected visual acuity (UCVA) < 0.00 logMAR (6/6). Logistic regression models were used to determine factors associated with myopia.Results: After excluding 389 participants, the overall prevalence of myopia was 33.6%. The prevalence of high myopia was 0.6%. The prevalence of myopia in girls was significantly higher than that in boys (37.6% vs. 30.0%, p < 0.001). The height, weight and BMI were significantly associated with AL (r = 0.471, r = 0.440, r = 0.276, p < 0.001, respectively). AL/CRC ratio was more highly correlated with SER than AL alone. Regression analysis showed that AL/CRC and hyperopia reserve were associated with myopia onset in the subsequent year (F = 201.557, p < 0.001; F = 68.934, p < 0.001). The cut point of hyperopia reserve for myopia in the subsequent year for grade 1 students was + 0.31D. Age (p < 0.001), parental myopia (p = 0.001) and lack of outdoor activity between classes (p = 0.049) were independently associated with higher prevalence rates of myopia.Conclusion: The prevalence of myopia among Chinese schoolchildren is alarming high. Consistent with previous cross-sectional data, AL/CRC and hyperopia reserve could function as myopia detection indicators. The hyperopia reserve among children aged between 6 ~ 7 years was low. Healthcare providers need to raise parents' awareness of the importance of regular eye examination and proper optical correction. [ABSTRACT FROM AUTHOR]

Periocular recognition has grown in popularity in biometrics applications over the years, and it is now being used in several large-scale national initiatives. Even though periocular patterns are unique, extrinsic factors like illumination, disease in the eye, camera-eye angle, and sensor interoperability can influence them. The use of contact lenses, particularly color cosmetic lenses, can complicate ocular biometrics by obscuring feature patterns and altering inter-class and intra-class distributions. This paper presents an in-depth analysis of changes in the eye (iris and sclera) color on periocular recognition performance. For this purpose, the proposed method generates an augmented dataset by masking out the ocular region (sclera and iris area) from a subject's periocular images and replacing it with other subjects' ocular regions. We simulate the uses of colored contact lenses by performing three experiments, and for each experiment, three cases are considered (recognition using the left eye, right eye, and both eyes). Statistical parameters are measured and compared to evaluate the performance, reliability, flexibility, robustness, and usability of periocular biometrics under different scenarios. [ABSTRACT FROM AUTHOR]

To assess baseline ocular biometric risk factors for progression from primary angle closure suspect (PACS) to primary angle closure (PAC) or acute angle closure (AAC). Prospective, observational study. Six hundred forty-three mainland Chinese with untreated PACS. Participants underwent baseline clinical examinations, including gonioscopy, anterior segment OCT (AS-OCT) imaging, and A-scan ultrasound biometry as part of the Zhongshan Angle Closure Prevention (ZAP) Trial. Primary angle closure suspect was defined as an inability to visualize pigmented trabecular meshwork in 2 or more quadrants based on static gonioscopy. Primary angle closure was defined as development of intraocular pressure above 24 mmHg or peripheral anterior synechiae. Progression was defined as development of PAC or an AAC attack. Multivariable logistic regression models were developed to assess biometric risk factors for progression. Six-year progression from PACS to PAC or AAC. Six hundred forty-three untreated eyes (609 nonprogressors, 34 progressors) of 643 participants were analyzed. In a multivariable model with continuous parameters, narrower horizontal angle opening distance of 500 μm from the scleral spur (AOD 500 ; odds ratio [OR], 1.10 per 0.01-mm decrease; P = 0.03), flatter horizontal iris curvature (IC; OR, 1.96 per 0.1-mm decrease; P = 0.01), and older age (OR, 1.11 per 1-year increase; P = 0.01) at baseline were associated significantly with progression (area under the receiver operating characteristic curve [AUC], 0.73). Smaller cumulative gonioscopy score was not associated with progression (OR, 1.03 per 1-modified Shaffer grade decrease; P = 0.85) when replacing horizontal AOD 500 in the multivariable model. In a separate multivariable model with categorical parameters, participants in the lowest quartile of horizontal AOD 500 (OR, 3.10; P = 0.002) and IC (OR, 2.48; P = 0.014) measurements and 59 years of age or older (OR, 2.68; P = 0.01) at baseline showed higher odds of progression (AUC, 0.72). Ocular biometric measurements can help to risk-stratify patients with early angle closure for more severe disease. Anterior segment OCT measurements of biometric parameters describing the angle and iris are predictive of progression from PACS to PAC or AAC, whereas gonioscopy grades are not. [ABSTRACT FROM AUTHOR]

The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufficient to extract iris information. In addition to providing information about an individual's identity, features extracted from these traits can also be explored to obtain other information such as the individual's gender, the influence of drug use, the use of contact lenses, spoofing, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specific problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics. [ABSTRACT FROM AUTHOR]

With the advances in cataract phacoemulsification and intraocular lens implantation, more and more attention has been paid to the postoperative effects by both clinicians and patients. Meanwhile, the instruments for the preoperative measurements are also evolving. Various types of ocular biometers have emerged, which have evolved the principles from ultrasound to swept-source optical coherence tomography(SS-OCT). The OA-2000, a new type of SS-OCT based ocular biometer with fully automatic three-dimensional scanning, has the advantages of simple and safe operation, high resolution, excellent repeatability, fast measurement and good tissue penetration. It can obtain multiple ocular biological parameters in one measurement, which enables a wide application prospect. Here, we review the measurement principle and clinical application of OA-2000.

ObjectiveTo observe the associations between regional peripheral refraction and myopia development in young Chinese people.MethodsTwo hundred and forty-one young adult subjects (21 emmetropes, 88 low myopes, 94 moderate myopes, and 38 high myopes) aged 18–28 years were included, and only the right eyes were tested. Eye biometrics were measured before pupil dilation using the Lenstar. Relative peripheral refractive errors (RPRE) were measured after pupil dilation using multispectral refractive topography (MRT), at nine retinal eccentricities: 0–5, 5–10, 10–15, 15–20, 20–25, 25–30, 30–35, 35–40, and 40–45 degrees.ResultsIn this study, RPRE increased with eccentricity, and it shows a growing trend with the increase of the degree of myopia among emmetropia, low myopia and moderate myopia groups, and RPRE varied with myopia severity at eccentricities between 20 and 35 degrees only. In addition, axial length (AL) and RPRE were positively correlated between 20 and 45 degrees, and AL was an independent risk factor for RPRE between 20 and 35 degrees.ConclusionThese findings indicate that the eccentricities between 20 and 35 degrees RPRE may be closely related to refractive development and eye growth in young Chinese people.

The area of ocular biometrics is among the most popular branches of biometric recognition technology. This area has long been dominated by iris recognition research, while other ocular modalities such as the periocular region or the vasculature of the sclera have received significantly less attention in the literature. Consequently, ocular modalities beyond the iris are not well studied and their characteristics are today still not as well understood. While recent needs for more secure authentication schemes have considerably increased the interest in competing ocular modalities, progress in these areas is still held back by the lack of publicly available datasets that would allow for more targeted research into specific ocular characteristics next to the iris. In this paper, we aim to bridge this gap for the case of sclera biometrics and introduce a novel dataset designed for research into ocular biometrics and most importantly for research into the vasculature of the sclera. Our dataset, called Sclera Blood Vessels, Periocular and Iris (SBVPI), is, to the best of our knowledge, the first publicly available dataset designed specifically with research in sclera biometrics in mind. The dataset contains high-quality RGB ocular images, captured in the visible spectrum, belonging to 55 subjects. Unlike competing datasets, it comes with manual markups of various eye regions, such as the iris, pupil, canthus or eyelashes and a detailed pixel-wise annotation of the complete sclera vasculature for a subset of the images. Additionally, the datasets ship with gender and age labels. The unique characteristics of the dataset allow us to study aspects of sclera biometrics technology that have not been studied before in the literature (e.g. vasculature segmentation techniques) as well as issues that are of key importance for practical recognition systems. Thus, next to the SBVPI dataset we also present in this paper a comprehensive investigation into sclera biometrics and the main covariates that affect the performance of sclera segmentation and recognition techniques, such as gender, age, gaze direction or image resolution. Our experiments not only demonstrate the usefulness of the newly introduced dataset, but also contribute to a better understanding of sclera biometrics in general. [ABSTRACT FROM AUTHOR]

Copyright of Uporabna Informatika is the property of Slovensko Drustvo Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Purpose: To assess associations between different types of electronic devices, myopic refraction and ocular biometric parameters in children aged 6–14 years in urban areas of Tianjin, China. Methods: A school‐based, cross‐sectional study was performed on 566 children (302 boys and 264 girls). The children underwent a comprehensive eye examination, including cycloplegic autorefraction and ocular biometry. The children's parents completed a detailed questionnaire that included each child's demographics, the use of electronic devices and other related risk factors. Results: Myopia was not associated with time spent using various electronic devices. However, the mean spherical equivalent refraction (SER) decreased by 0.28 D (p = 0.042) and 0.33 D (p = 0.018) for each 1‐h increase in the time spent using smart phones and computers, respectively. In the multiple linear regression analyses of factors associated with the SER, the standardised coefficient B for time spent reading and writing was approximately four to five times larger than the standardised coefficient for time spent using smart phones or computers. Time spent using tablets and watching television was not significantly associated with the SER. A longer axial length (AL) was associated with more time spent using smart phones (B = 0.23, p = 0.006) and computers (B = 0.26, p = 0.002) but not using tablets (p = 0.45) and watching television (p = 0.45). No significant association was found between other ocular biometric parameters and time spent using various electronic devices. Conclusions: On average, a more myopic SER and longer AL were both associated with more time spent using smart phones and computers, but not with time spent using tablets and watching television. The magnitude of the association between SER and time spent reading and writing was a substantially larger than that for smart phone or computer use. Different types of electronic devices had differing levels of association with myopic refraction. [ABSTRACT FROM AUTHOR]

The sclera has recently been gaining attention as a biometric modality due to its various desirable characteristics. A key step in any type of ocular biometric recognition, including sclera recognition, is the segmentation of the relevant part(s) of the eye. However, the high computational complexity of the (deep) segmentation models used in this task can limit their applicability on resource-constrained devices such as smartphones or head-mounted displays. As these devices are a common desired target for such biometric systems, lightweight solutions for ocular segmentation are critically needed. To address this issue, this paper introduces IPAD (Iterative Pruning with Activation Deviation), a novel method for developing lightweight convolutional networks, that is based on model pruning. IPAD uses a novel filter-activation-based criterion (ADC) to determine low-importance filters and employs an iterative model pruning procedure to derive the final lightweight model. To evaluate the proposed pruning procedure, we conduct extensive experiments with two diverse segmentation models, over four publicly available datasets (SBVPI, SLD, SMD and MOBIUS), in four distinct problem configurations and in comparison to state-of-the-art methods from the literature. The results of the experiments show that the proposed filter-importance criterion outperforms the standard L 1 and L 2 approaches from the literature. Furthermore, the results also suggest that: (i) the pruned models are able to retain (or even improve on) the performance of the unpruned originals, as long as they are not over-pruned, with RITnet and U-Net at 50% of their original FLOPs reaching up to 4 % and 7 % higher IoU values than their unpruned versions, respectively, (ii) smaller models require more careful pruning, as the pruning process can hurt the model's generalization capabilities, and (iii) the novel criterion most convincingly outperforms the classic approaches when sufficient training data is available, implying that the abundance of data leads to more robust activation-based importance computation. [ABSTRACT FROM AUTHOR]

Ocular biometrics in the visible spectrum has emerged as an area of significant research activity. In this paper, we propose a hybrid convolution-based model, for verifying a pair of periocular images containing the iris. We compose the hybrid model as a combination of an unsupervised and a supervised convolution neural network, and augment the combination with the well-known geometry-based Root SIFT model. We also compare the performance of both convolution-based models against each other, as well as, with the baseline Root SIFT. In the first (unsupervised w.r.t target dataset) convolution based deep learning approach, we use a stacked convolutional architecture, using external models learned a-priori on external facial and periocular data, on top of the baseline Root SIFT model applied on the provided data, and apply different score fusion models. In the second (supervised w.r.t target dataset) approach, we again use a stacked convolution architecture; but here, we learn the feature vector in a supervised manner. On the MICHE-II dataset, we obtain an AUROC of 0.946 and 0.981, and EER of 0.092 and 0.066, for the two models respectively. The hybrid model we propose, which combines these two convolutional neural networks, outperforms the constituents, in case both images arise from the same device type, but not necessarily so otherwise, obtaining a AUROC of 0.986 and EER of 0.053. We also benchmark our performance on the standard VISOB database, where we outperform the state of the art methods, achieving a TPR of 99.5% at a FPR of 0.001%. Given the robustness and significant performance of our methodology, our system can be used in practical applications with minimal error. [ABSTRACT FROM AUTHOR]

Ocular biometrics encompasses the imaging and use of characteristic features extracted from the eyes for personal recognition. Ocular biometric modalities in visible light have mainly focused on iris, blood vessel structures over the white of the eye (mostly due to conjunctival and episcleral layers), and periocular region around eye. Most of the existing studies on iris recognition use the near infrared spectrum. However, conjunctival vasculature and periocular regions are imaged in the visible spectrum. Iris recognition in the visible spectrum is possible for light color irides or by utilizing special illumination. Ocular recognition in the visible spectrum is an important research area due to factors such as recognition at a distance, suitability for recognition with regular RGB cameras, and adaptability to mobile devices. Further these ocular modalities can be obtained from a single RGB eye image, and then fused together for enhanced performance of the system. Despite these advantages, the state-of-the-art related to ocular biometrics in visible spectrum is not well known. This paper surveys this topic in terms of computational image enhancement, feature extraction, classification schemes and designed hardware-based acquisition set-ups. Future research directions are also enumerated to identify the path forward. [ABSTRACT FROM AUTHOR]

Biometrics, an integral component of Identity Science , is widely used in several large-scale-county-wide projects to provide a meaningful way of recognizing individuals. Among existing modalities, ocular biometric traits such as iris, periocular, retina, and eye movement have received significant attention in the recent past. Iris recognition is used in Unique Identification Authority of India’s Aadhaar Program and the United Arab Emirate’s border security programs, whereas the periocular recognition is used to augment the performance of face or iris when only ocular region is present in the image. This paper reviews the research progression in these modalities. The paper discusses existing algorithms and the limitations of each of the biometric traits and information fusion approaches which combine ocular modalities with other modalities. We also propose a path forward to advance the research on ocular recognition by (i) improving the sensing technology, (ii) heterogeneous recognition for addressing interoperability, (iii) utilizing advanced machine learning algorithms for better representation and classification, (iv) developing algorithms for ocular recognition at a distance, (v) using multimodal ocular biometrics for recognition, and (vi) encouraging benchmarking standards and open-source software development. [ABSTRACT FROM AUTHOR]

Anisometropia represents a unique example of ocular development, where the two eyes of an individual, with an identical genetic background and seemingly subject to identical environmental influences, can grow asymmetrically to produce significantly different refractive errors. This review provides an overview of the research examining myopic anisometropia, the ocular characteristics underlying the condition and the potential aetiological factors involved. Various mechanical factors are discussed, including corneal structure, intraocular pressure and forces generated during near work that may contribute to development of anisomyopia. Potential visually guided mechanisms of unequal ocular growth are also explored, including the influence of astigmatism, accommodation, higher-order aberrations and the choroidal response to altered visual experience. The association between binocular vision, ocular dominance and asymmetric refraction is also considered, along with a review of the genetic contribution to the aetiology of myopic anisometropia. Despite a significant amount of research into the biomechanical, structural and optical characteristics of anisometropic eyes, there is still no unifying theory, which adequately explains how two eyes within the same visual system grow to different endpoints. [ABSTRACT FROM AUTHOR]

Abstract: Biometrics is the science of recognizing people based on their physical or behavioral traits such as face, fingerprints, iris, and voice. Among these characteristics, ocular biometrics has gained popularity due to the significant progress made in iris recognition. However, iris recognition is unfavorably influenced by the non-frontal gaze direction of the eye with respect to the acquisition device. In such scenarios, additional parts of the eye, such as the sclera (the white of the eye) may be of significance. In this article, we investigate the use of the sclera texture and vasculature patterns evident in the sclera as a potential biometric. Iris patterns are better discerned in the near infrared spectrum (NIR) while vasculature patterns are better discerned in the visible spectrum (RGB). Therefore, multispectral images of the eye, consisting of both NIR and RGB channels, are used in this work in order to ensure that both the iris and the vasculature patterns are imaged. The contributions of this work include: (a) the assembling of a multispectral eye database to initiate research on this topic; (b) the design of a novel algorithm for sclera segmentation based on a normalized sclera index measure; and (c) the evaluation of three different feature extraction and matching schemes on the assembled database in order to examine the potential of utilizing the sclera and the accompanying vasculature pattern as biometric cues. Experimental results convey the potential of this biometric in an ocular-based recognition system. [Copyright &y& Elsevier]

Abstract: Most current ocular biometric systems are based on recognition and classification of unique iridial patterns typically captured in near infrared spectrum (NIR). However, eye images in the visible spectrum (e.g. RGB images) also reveal some iridial patterns in addition to the vascularity of the white of the eyes (mostly due to conjunctival and episcleral layers). These vascular patterns have rich and uniquely identifiable information. The combination of the aforementioned modalities provides an opportunity for bi-modal ocular biometrics using only visible spectrum captures. Multimodality improves the performance of biometric systems compared to single mode biometrics. In this work, a bi-modal ocular biometric system is described, where match scores from vasculature of the white of the eye and iris modalities are fused. We report the performance of this enhanced complementary biometric identification using UBIRIS v1 database. The proposed method, for a quality-vetted subset of UBIRIS v1 RGB ocular images, produces an area under receiver operating characteristic curve (AUC) of 0.9954 and an equal error rate (EER) of 0.0452. In comparison, individual modalities yield an AUC of 0.9822 and EER of 0.0759 for iris and an AUC of 0.9623 and an EER of 0.1022 for conjunctival vasculature. The proposed new algorithms may overcome constraints of using NIR imaging for iris and provide a better overall performance using only RGB eye images. We conclude that bi-modal iris–conjunctival fusion can improve the otherwise challenging RGB iris recognition. [Copyright &y& Elsevier]

Periocular biometrics is the recognition of individuals based on the appearance of the region around the eye. Periocular recognition may be useful in applications where it is difficult to obtain a clear picture of an iris for iris biometrics, or a complete picture of a face for face biometrics. Previous periocular research has used either visible-light (VL) or near-infrared (NIR) light images, but no prior research has directly compared the two illuminations using images with similar resolution. We conducted an experiment in which volunteers were asked to compare pairs of periocular images. Some pairs showed images taken in VL, and some showed images taken in NIR light. Participants labeled each pair as belonging to the same person or to different people. Untrained participants with limited viewing times correctly classified VL image pairs with 88% accuracy, and NIR image pairs with 79% accuracy. For comparison, we presented pairs of iris images from the same subjects. In addition, we investigated differences between performance on light and dark eyes and relative helpfulness of various features in the periocular region under different illuminations. We calculated performance of three computer algorithms on the periocular images. Performance for humans and computers was similar. [ABSTRACT FROM PUBLISHER]

Abstract: As the standard iris biometric algorithm “sees” them, the left and right irises of the same person are as different as irises of unrelated people. Similarly, in terms of iris biometric matching, the eyes of identical twins are as different as irises of unrelated people. The left and right eyes of an individual or the eyes of identical twins are examples of genetically identical irises. In experiments with human observers viewing pairs of iris images acquired using an iris biometric system, we have found that there is recognizable similarity in the left and right irises of an individual and in the irises of identical twins. This result suggests that iris texture analysis different from that performed in the standard iris biometric algorithm may be able to answer questions that iris biometrics cannot answer. [Copyright &y& Elsevier]

Abstract: The periocular region is the part of the face immediately surrounding the eye, and researchers have recently begun to investigate how to use the periocular region for recognition. Understanding how humans recognize faces helped computer vision researchers develop algorithms for face recognition. Likewise, understanding how humans analyze periocular images could benefit researchers developing algorithms for periocular recognition. We conducted two experiments to determine how humans analyze periocular images. In these experiments, we presented pairs of images and asked volunteers to determine whether the two images showed eyes from the same subject or from different subjects. In the first experiment, subjects were paired randomly to create different-subject queries. Our volunteers correctly determined the relationship between the two images in 92% of the queries. In the second experiment, we considered multiple factors in forming different-subject pairs; queries were formed from pairs of subjects with the same gender and race, and with similar eye color, makeup, eyelash length, and eye occlusion. In addition, we limited the amount of time volunteers could view a query pair. On this harder experiment, the correct verification rate was 79%. We asked volunteers to describe what features in the images were helpful to them in making their decisions. In both experiments, eyelashes were reported to be the most helpful feature. [Copyright &y& Elsevier]

Purpose: To investigate the influence of a short period of elevated IOP (induced through the wearing of standard swimming goggles) upon axial length. Methods: Forty young adult subjects (20 myopes and 20 emmetropes, mean age 22 ± 2 years) had their IOP and axial length measured before, during and after a 3 min period of swimming goggle wear. IOP was measured using a non-contact tonometer, and axial length with an optical biometer based upon the principle of partial coherence interferometry. Results: A 3-min period of swimming goggle wear was found to be associated with a significant increase in IOP (mean change 3.7 ± 2.6 mmHg, p < 0.0001) and a significant axial elongation of the eye (mean change in axial length of 18 ± 12 μm, p < 0.0001). Both IOP and axial length were found to return to baseline levels upon removal of the swimming goggles. A significant positive association was found between the changes in IOP and axial length (r² = 0.37, p < 0.0001). There were no significant differences between the emmetropic and myopic subjects in terms of their magnitude of change in axial length and IOP during swimming goggle wear. Conclusions: A small magnitude of elevation in IOP, induced through mechanical means and imposed for a short period of time was associated with a small but statistically significant axial elongation of the eye. [ABSTRACT FROM AUTHOR]

To examine the familial correlations, heritability ( h 2) and common environmental components ( c 2) of myopia and ocular biometric traits (all treated as continuous outcomes) in families collected through the Genes in Myopia (GEM) family study in Australia. A total of 132 pedigrees (723 participants) were recruited for this study. All individuals completed a risk factor questionnaire and underwent a detailed eye examination including spherical equivalent (SphE) and ocular biometric measurements of axial length (AL), anterior chamber depth (ACD) and corneal curvature (CC). Familial correlations were calculated and h 2 and c2 were estimated using a variance component model that assumes a multivariate t distribution within each pedigree. Two definitions of common environments ( c 2) were considered: nuclear family (current) shared environment (Model 1) and sib-ship (childhood) shared environment (Model 2). Population ascertainment adjustment was performed using the Blue Mountains eye study dataset. The trends observed for familial correlations suggested that SphE is influenced by both environmental and genetic factors whereas AL, ACD and CC are predominantly genetically determined. This was largely confirmed by variance components modelling. Heritability estimates (adjusted for age, sex and years of education) from the best fitting ACE model (Model 2, childhood shared environment) were 0.50 ± 0.05 for SphE, 0.73 ± 0.04 for AL, 0.78 ± 0.04 for ACD and 0.16 ± 0.06 for CC. Childhood environmental effects were significant with c 2 estimated to be 0.33 ± 0.04 for SphE, 0.06 ± 0.03 for AL, 0.22 ± 0.04 for ACD and 0.10 ± 0.05 for CC. Age was associated with SphE, total years of education was associated with AL and sex was associated with all traits studied. We used a novel and conservative approach to account for and estimate common environmental effects by specifying either nuclear family or sib-ship environment when estimating heritability estimates and showed that all traits examined (SphE, AL, ACD and CC) are heritable, thus reflecting a genetic component. These traits therefore all represent candidates for quantitative trait linkage analyses. [ABSTRACT FROM AUTHOR]

As a practical pursuit of quantified uniqueness, biometrics explores the parameters that make us who we are and provides the tools we need to secure the integrity of that identity. In our culture of constant connectivity, an increasing reliance on biometrically secured mobile devices is transforming them into a target for bad actors. While no system will ever prevent all forms of intrusion, even state of the art biometric methods remain vulnerable to spoof attacks. As these attacks become more sophisticated, liveness based attack detection methods provide a potential deterrent. We present a novel optokinetc nystagmus (OKN) based liveness assessment system for mobile applications which leverages phase-locked temporal features of a unique reflexive behavioral response. In this paper we provide proof of concept for eliciting, collecting and extracting the OKN response motion signature on a mobile device. Results of our most successful experimental machine learning classifier are reported for a multi-layer LSTM based model demonstrating a 98.4% single stimulus detection performance for simulated video based attacks. • Mobile device displays provide a suitable platform for inducing Optokinetic Nystagmus • Ocular motion dynamics extracted with existing ocular feature localization methods • Motion based eye behavioral classification reliable biometric liveness assessment • Eye movements in selfie videos provide security against sophisticated spoof attacks [ABSTRACT FROM AUTHOR]