The method for quantified analysis and pattern visualization for eye blinking using high-frame-rate video

Objective The increasing rate of depression among university students is a cause of great concern worldwide. With the recent growth in computer vision technology, eye movement features are proving beneficial in the assessment of depression owing to their non-invasiveness. Our objective was to determine the presence of depression through emotional elicitation by studying blink patterns in a student population. Method The blink data of 50 university students (26 males, 24 females) from different regions of the country within the age group of 21–26 years were collected using an experimental setup. Results Statistical tests on blink data revealed that blink rate changes with changes in emotion from joy to sadness or vice versa, irrespective of one’s depression status. Another explanation is that the blink rates of the healthy and depressed groups differed significantly during sad emotional states. The tests also indicated a half-closed eye state as a possible symptom of depression. Conclusions These findings suggest that the prevalence of mental health problems can be detected at an early stage by designing simple non-invasive procedures, such as blink pattern analysis driven by technology and expert advice, which will help prevent the further development of such illnesses.

In a typical transmission control protocol and Internet protocol (TCP/IP) suite, there are several ways, such as using photograph, three-dimensional (3D) model, and video clip of a valid user to mock the facial recognition. Studies show that there has been significant improvement in detecting photograph and 3D model spoofing. However, there is no such improvement in detecting video spoofing. Recent studies suggest that liveness monitoring using the facial features has potential to improve security, especially in biometric systems. In this paper, a liveness monitoring technique is introduced to assist facial recognition. In the proposed system, an eye blinking pattern is used through a real-time generic web-camera. An eye blinking password system using ultrasonic range sensing module is developed for liveness detection of the users. The system is tested by conducting experiments using 15 valid users and 100 different user appearances. According to the experimental results, the proposed system achieves 99% face recognition accuracy and 99% liveliness detection performance.

A method for a real-time vision system that automatically detects a user's eye blinks and accurately measures their durations is introduced. The system is intended to provide an alternate input modality to allow people with severe disabilities to access a computer. Voluntary long blinks trigger mouse clicks, while involuntary short blinks are ignored. The system enables communication using blink patterns: sequences of long and short blinks which are interpreted as semiotic messages. The location of the eyes is determined automatically through the motion of the user's initial blinks. Subsequently, the eye is tracked by correlation across time, and appearance changes are automatically analyzed in order to classify the eye as either open or closed at each frame. No manual initialization, special lighting, or prior face detection is required. The system has been tested with interactive games and a spelling program. Results demonstrate overall detection accuracy of 95.61% and an average rate of 28 frames per second.

BackgroundTo assess the effects of warm compress (WC) on tear film lipid layer, blink pattern and Meibomian gland function in patients with dry eye following femtosecond laser small incision lenticule extraction (SMILE) and laser-assisted subepithelial keratomileusis (LASEK).Methods We enrolled 37 eyes of 37 participants, each with dry eye for more than 2 years following SMILE (25 eyes) or LASEK (12 eyes). WC was performed using a spontaneously heating eye mask. Tear film break-up time (TBUT), tear film lipid layer thickness (TFLLT), blink pattern, Meibomian secretory function scores (MGS), visual acuity, spherical equivalent (SE), keratometry, central corneal thickness (CCT) and aberration were assessed before and after WC.ResultsAfter WC, the following mean values all increased relative to baselines: CCT, SE, minimum (Min-), maximum (Max-) and average (Ave-) TFLLT, TBUT, total MGS (TMGS), number of glands secreting any liquid (MGL), and complete blink rate (CBR) (p values ranging from < 0.001 to 0.042). Partial blink frequency (PBF) and partial blink rate (PBR) decreased (p = 0.002 in both cases). The decrease of PBF was higher in SMILE subgroup than in LASEK (p = 0.030). TBUT variation was positively correlated with that of Ave-TFLLT and TMGS (p = 0.046, 0.028, respectively). Max-TFLLT variation was correlated with that of TMGS (p = 0.020).ConclusionsWC may temporarily increase tear film thickness and stability, decrease partial blink, and partly augment Meibomian gland function in dry eye patients after corneal refractive surgeries. Future studies are required to investigate long term clinical efficacy and safety.

The emerging Deep fake Detection System has been a major threat to digital media integrity since its introduction in 2017; early applications of the technology have been largely based on applications of face- swapping techniques using auto encoders and generative adversarial networks (GANs).Owing to the fast pace of development of these synthetic media generation techniques, these methods have outpaced more traditional detection methods, leading to an urgent need for more adaptive solutions. The system creates a solution to the problem by designing a new self-learning detection system that does not require pre-existing datasets. Compared to traditional methods, which have to be provided with large amounts of labelled data, our implementation uses incremental machine learning algorithms that are incrementally refined based on user feedback and confidence-based learning mechanisms. By leveraging transfer learning and online learning paradigms, the platform learns to adapt to emerging deep fake variations in real-time. Results of current implementation show promising results in detecting artifacts from eye blinking patterns, facial micro-expressions and audio-visual synchronization errors. Further work will be done to incorporate transformer-based architectures for better temporal analysis, add text deep fakes detection. The project will serve to build an open source, continually improving defence against synthetic media manipulation that will further increase the authenticity and security of digital media.

Monitoring the concentration level of a learner is important to maximize the learning effect, giving proper feedback on tasks and to understand the performance of learners in tasks. In this paper, we propose a personal concentration level monitoring system when a user performs an online task on a computer by analyzing his/her pupillary response and eye-blinking pattern. We use low-priced web camera to detect eye blinking pattern and a portable eye tracker to detect pupillary response. Experimental results show good performance of the proposed concentration level monitoring system and suggest that it can be used for various real applications such as intelligent tutoring system, e-learning system, etc.

Spatio-temporal information is very important to capture the discriminative cues between genuine and fake faces from video sequences. To explore such a temporal feature, the fine-grained motions (e.g., eye blinking, mouth movements and head swing) across video frames are very critical. In this paper, we propose a joint CNN-LSTM network for face anti-spoofing, focusing on the motion cues across video frames. We first extract the high discriminative features of video frames using the conventional Convolutional Neural Network (CNN). Then we leverage Long Short-Term Memory (LSTM) with the extracted features as inputs to capture the temporal dynamics in videos. To ensure the fine-grained motions more easily to be perceived in the training process, the eulerian motion magnification is used as the preprocessing to enhance the facial expressions exhibited by individuals, and the attention mechanism is embedded in LSTM to ensure the model learn to focus selectively on the dynamic frames across the video clips. Experiments on MSU-MFSD and Replay Attack databases show that the proposed method yields state-of-the-art performance with better generalization ability compared with several other popular algorithms.

In this paper, we propose a novel approach to assess driver's arousal states based on the analysis of eyeblink characteristics. We focus on a non-intrusive and driver-independent system. We use Hidden Markov Models (HMMs) to classify eyeblink patterns from the video of the drivers, and the arousal states are estimated from the histogram variations of these typical blink patterns. A strong correlation between the eyeblink patterns derived from this approach and those derived from the recorded EOG (electro-occulography) waveforms can be observed. The arousal assessment results are also verified against the rating results by a trained rater.

Abstract: The Eye Blinking Car Accident Avoiding System (EBCAAS) is a novel approach to enhance driving safety by detecting and preventing accidents caused by driver drowsiness or distraction. The system uses a camera mounted on the dashboard of the vehicle to continuously monitor the driver's eyes and detect any abnormal blinking patterns that may indicate fatigue or distraction. Upon detection of such patterns, the system sends an alert to the driver in the form of visual or audio cues, reminding them to stay alert and focused on the road. Additionally, the system is equipped with an automatic emergency braking mechanism that can be activated in the event of a potential collision. The EBCAAS has the potential to significantly reduce the incidence of accidents caused by driver fatigue or distraction and improve road safety for all users. Accidents due to drowsiness can be controlled and prevented with the help of eye blink sensor using IR rays. It consists of IR transmitter and an IR receiver. The transmitter transmits IR rays into the eye

A New Perspective on Spontaneous Blinks

Optical Coherence Tomography (OCT) is often employed to observe the retinal layers in the human eyes. The retinal scans are susceptible to artefacts such as head movements or eye blinks. Along with this, the quality of the images is degraded by speckle noise caused due to the constructive and destructive interference of the waves used for capturing data. Recently, image restoration techniques have geared up in terms of quality with the exertion of deep learning. Despeckling using deep learning, in general, necessitates a large set of training images. On the contrary, deep image prior is a novel model that performs denoising operations using a single training image, based on a prior assumption about the noise distribution. This paper extends the concept of the deep image prior towards non-local restoration for speckle noise assuming that the speckle follows Gamma distribution. Such a framework can be incorporated to enhance the OCT images. The proposed framework is assessed qualitatively with visual comparisons and quantitatively using statistical measures like PSNR, CNR and ENL. Comparative studies confirm that the proposed method outperforms the existing methods in restoring speckled input images.

Recently we presented our concept of “videography with the slit lamp,” which provides an imaging solution for nearly every pathological finding in ophthalmology. This paper deals with the changes that must be made to prepare the slit lamp for documenting squint.To achieve this goal we propose:1. Changes in the observation system: minus lenses in front of the objective of the slit lamp to achieve a sharp image of both eyes (eg, −8 diopters [dpt] if the patient sits at a distance of 50 cm).2. Changes in the illumination system: minimizing the narrowed angle between illumination and observation axis by holding a “recentration” prism of 14 dpt horizontally in front of the slit light. This procedure creates equally sufficient illumination of the patient’s face and central corneal reflexes.3. Recording clinical findings with a digital recorder. This enables us to identify binocular eye positions, which sometimes last only part of a second, eg, in latent or intermittent strabism.4. Visualizing clinical findings by using Microsoft PowerPoint® to build up 9-gaze composites or adjust corneal reflexes on subsequent foils. Changes in binocular eye positions (eg, after surgery, but also during diagnostic covering) can be made visible by flickering between the foils to compare.

Effects of ambient illuminance and mobile phone screen brightness on tear film stability, visual fatigue, and blink patterns during reading.

Modern embedded systems are typically integrated as multiprocessor system on chips, and are often characterized by the complex behaviors and dependencies that system components exhibit. Different events that trigger such systems normally cause different execution demands, depending on their event type as well as on the task they are processed by, leading to complex workload correlations. For example in data processing systems, the size of an events payload data will typically determine its execution demand on most or all system components, leading to highly correlated workloads. Performance analysis of such complex system is often very difficult, and conventional analysis methods have no means to capture the possible existence of workload correlations. This leads to overly pessimistic analysis results, and thus to too expensive system designs with considerable performance reserves. We propose an abstract model to characterize and capture workload correlations present in a system architecture, and we show how the captured additional system information can be incorporated into an existing framework for modular performance analysis of embedded systems. We also present a method to analytically obtain the proposed abstract workload correlation model from a typical system specification. The applicability of our approach and its advantages over conventional performance analysis methods is shown in a detailed case study of a multiprocessor system on chip, where the analysis results obtained with our approach are considerably improved compared to the results obtained with conventional analysis methods.

BackgroundAbnormal blinking pattern is associated with ocular surface diseases. However, blink is difficult to analyze due to the rapid movement of eyelids. Deep learning machine (DLM) has been proposed as an optional tool for blinking analysis, but its clinical practicability still needs to be proven. Therefore, the study aims to compare the DLM-assisted Keratograph 5M (K5M) as a novel method with the currently available Lipiview in the clinic and assess whether blinking parameters can be applied in the diagnosis of dry eye disease (DED).MethodsThirty-five DED participants and 35 normal subjects were recruited in this cross-sectional study. DED questionnaire and ocular surface signs were evaluated. Blinking parameters including number of blinks, number of incomplete blinking (IB), and IB rate were collected from the blinking videos recorded by the K5M and Lipiview. Blinking parameters were individually collected from the DLM analyzed K5M videos and Lipiview generated results. The agreement and consistency of blinking parameters were compared between the two devices. The association of blinking parameters to DED symptoms and signs were evaluated via heatmap.ResultsIn total, 140 eyes of 70 participants were included in this study. Lipiview presented a higher number of IB and IB rate than those from DLM-assisted K5M (P ≤ 0.006). DLM-assisted K5M captured significant differences in number of blinks, number of IB and IB rate between DED and normal subjects (P ≤ 0.035). In all three parameters, DLM-assisted K5M also showed a better consistency in repeated measurements than Lipiview with higher intraclass correlation coefficients (number of blinks: 0.841 versus 0.665; number of IB: 0.750 versus 0.564; IB rate: 0.633 versus 0.589). More correlations between blinking parameters and DED symptoms and signs were found by DLM-assisted K5M. Moreover, the receiver operating characteristic analysis showed the number of IB from K5M exhibiting the highest area under curve of 0.773.ConclusionsDLM-assisted K5M is a useful tool to analyze blinking videos and detect abnormal blinking patterns, especially in distinguishing DED patients from normal subjects. Large sample investigations are therefore warranted to assess its clinical utility before implementation.