Biometric Recognition Through Eye Movements Using a Recurrent Neural Network

Jia, Shaohua; Koh, Do Hyong; Seccia, Amanda; Antonenko, Pasha; Lamb, Richard; Keil, Andreas; Schneps, M. H.; Pomplun, Marc

doi:10.1109/icbk.2018.00016

Cited by 25 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jia, et al [54] proposed a framework for biometric identification through eye movement. They used RNN to learn dynamic eye features and temporal dependencies from a dataset captured from a sequence of raw eye movement recordings.…”

Section: Classification Methods For Biometric Systemsmentioning

confidence: 99%

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Akinyelu

Blignaut

2020

IEEE Access

View full text Add to dashboard Cite

Eye tracking is becoming a very important tool across many domains, including humancomputer-interaction, psychology, computer vision, and medical diagnosis. Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome. Some of these methods suffer from poor image quality and variable light conditions. The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking. The availability of large-scale datasets has further improved the performance of deep learning-based methods. This paper presents a survey of the current state-of-the-art on deep learning-based gaze estimation techniques, with a focus on Convolutional Neural Networks (CNN). This paper also provides a survey on other machine learning-based gaze estimation techniques. This study aims to empower the research community with valuable and useful insights that can enhance the design and development of improved and efficient deep learning-based eye-tracking models. This study also provides information on various pre-trained models, network architectures, and open-source datasets that are useful for training deep learning models.

show abstract

Section: Classification Methods For Biometric Systemsmentioning

confidence: 99%

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Akinyelu

Blignaut

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Most earlier works (e.g., [21]) require explicit classification of eye movement signals into physiologically-grounded events, from which hand-crafted features are extracted and fed into statistical and/or machine learning models. Since the recent introduction of deep learning to the field of eye movement biometrics [22,23], end-to-end biometric authentication has become more common. The current state-of-the-art model is DeepEyedentificationLive (DEL) [24] which utilizes subnets that separately focus on "fast" (e.g., saccadic) and "slow" (e.g., fixational) eye movements.…”

Section: Eye Movement Biometricsmentioning

confidence: 99%

Eye Know You Too: A DenseNet Architecture for End-to-end Eye Movement Biometrics

Lohr¹,

Komogortsev²

2022

Preprint

View full text Add to dashboard Cite

Plain convolutional neural networks (CNNs) have been used to achieve state-of-the-art performance in various domains in the past years, including biometric authentication via eye movements. There have been many relatively recent improvements to plain CNNs, including residual networks (ResNets) and densely connected convolutional networks (DenseNets). Although these networks primarily target image processing domains, they can be easily modified to work with time series data. We employ a DenseNet architecture for end-to-end biometric authentication via eye movements. We compare our model against the most relevant prior works including the current state-of-the-art. We find that our model achieves state-of-the-art performance for all considered training conditions and data sets.

show abstract

“…The combined accuracy of smartphone hand position and touch-typing [13] detection leads to an accuracy of 93.9% with the proposed model. Models from [14,15] both utilized the specialized LSTM cell. Using this LSTM cell, the ECG signal-based authentication reached accuracies of 100% [20] for using the MITDB dataset and 99.73% [21].…”

Section: Novel Smartphone Authentication Techniquesmentioning

confidence: 99%

“…This is where the RNNs have the potential to dramatically improve how biometric authentication is performed and improve upon current sensor-based authentication methods. This can be seen in [14], where researchers authenticated based on eye movement patterns. RNNs perform best with time-series data, which allows multiple neural networks to work together to verify the identity of a user.…”

Section: Introductionmentioning

confidence: 99%

Applications of Recurrent Neural Network for Biometric Authentication & Anomaly Detection

2021

View full text Add to dashboard Cite

Recurrent Neural Networks are powerful machine learning frameworks that allow for data to be saved and referenced in a temporal sequence. This opens many new possibilities in fields such as handwriting analysis and speech recognition. This paper seeks to explore current research being conducted on RNNs in four very important areas, being biometric authentication, expression recognition, anomaly detection, and applications to aircraft. This paper reviews the methodologies, purpose, results, and the benefits and drawbacks of each proposed method below. These various methodologies all focus on how they can leverage distinct RNN architectures such as the popular Long Short-Term Memory (LSTM) RNN or a Deep-Residual RNN. This paper also examines which frameworks work best in certain situations, and the advantages and disadvantages of each proposed model.

show abstract

Biometric Recognition Through Eye Movements Using a Recurrent Neural Network

Cited by 25 publications

References 15 publications

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Eye Know You Too: A DenseNet Architecture for End-to-end Eye Movement Biometrics

Applications of Recurrent Neural Network for Biometric Authentication & Anomaly Detection

Contact Info

Product

Resources

About