Grant: Discovery Grants Program - Individual
University of Toronto
$38,000.00
Eye Sense You: Biometric Solutions based on Eye movements and Pupilometry
EF 2024-25
Résumé
Eye movement biometrics including pupillometry is a relatively new biometric modality with great and growing potential in numerous applications such as human biometric recognition, human emotion recognition and characterization, medical and mental health assessment and diagnosis, and emerging virtual and augmented -reality applications among others. Eye biometric technologies have become relevant due to the emerging use of eye -tracking sensors and efficient signal processing and machine learning techniques, in addition to their spoofing resistant properties and relative implementation simplicity. Another advantage of eye movement biometrics is the possibility of using them for continued authentication of identity, emotions and behavior, since they can provide a fresh biometric reading every few seconds.
This proposal aims to investigate eye biometrics such as changes in the size and in the rate of the eye pupil, eye blink rate and transitions, eyelid state, and eye gaze tracking to verify user identity, detect user's emotional states like stress and depression, improve user-machine interfacing and thus anticipate /monitor their access, behavior and interaction in a variety of applications and environments. Note that existing eye movement biometrics have not achieved levels of performance acceptable for real -world as of yet. Also most related research requires the subjects to be in a controlled environment where they cannot move their heads and the light conditions are not varied. Our objective is to consider a wider set of applications, relax the control conditions and consider a more practical approach based on a non -invasive system and more realistic conditions. While at the same time improve the performance of the state of the art.
To accomplish our objectives, we will employ data from existing databases as well acquire our own data via experimentation. The conditions of signal acquisition will be varied to simulate a realistic environment. Therefore, data collection and analysis will be based on data collection in a research laboratory and then testing with simulated and real systems. Advanced computer vision signal processing and machine learning approaches such as neural networks and other discriminate, regenerative models and GAN methodologies will be explored and evaluated. Convolutional Neural Networks (CNN), and densely connected convolutional networks will be coupled with Long Short Memory (LSTM) models in a supervised learning mechanism to learn features that are unique and stable. objective will be to outperform in performance existing eye movement approaches, increase their robustness and diversify their applicability and their acceptability in real world applications. Preliminary results in the areas of user recognition and emotion detection show promise and support our expectations.
The proposed research will establish eye biometrics as a commercial viable technology with great benefit to Canada.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2023-04429
Name nom
Hatzinakos, Dimitrios
Department département
Electrical and Computer Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
38000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2514
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Digital signal processing
Research subject fr
Traitement des signaux numériques
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Eye Sense You: Biometric Solutions based on Eye movements and Pupilometry
Keywords
eye movement biometrics; pupilometry biometrics; signal processing; machine learning; user recognition; emotion recognition; usermachine interfacing
Application summary
Eye movement biometrics including pupillometry is a relatively new biometric modality with great and growing potential in numerous applications such as human biometric recognition, human emotion recognition and characterization, medical and mental health assessment and diagnosis, and emerging virtual and augmented -reality applications among others. Eye biometric technologies have become relevant due to the emerging use of eye -tracking sensors and efficient signal processing and machine learning techniques, in addition to their spoofing resistant properties and relative implementation simplicity. Another advantage of eye movement biometrics is the possibility of using them for continued authentication of identity, emotions and behavior, since they can provide a fresh biometric reading every few seconds.
This proposal aims to investigate eye biometrics such as changes in the size and in the rate of the eye pupil, eye blink rate and transitions, eyelid state, and eye gaze tracking to verify user identity, detect user's emotional states like stress and depression, improve user-machine interfacing and thus anticipate /monitor their access, behavior and interaction in a variety of applications and environments. Note that existing eye movement biometrics have not achieved levels of performance acceptable for real -world as of yet. Also most related research requires the subjects to be in a controlled environment where they cannot move their heads and the light conditions are not varied. Our objective is to consider a wider set of applications, relax the control conditions and consider a more practical approach based on a non -invasive system and more realistic conditions. While at the same time improve the performance of the state of the art.
To accomplish our objectives, we will employ data from existing databases as well acquire our own data via experimentation. The conditions of signal acquisition will be varied to simulate a realistic environment. Therefore, data collection and analysis will be based on data collection in a research laboratory and then testing with simulated and real systems. Advanced computer vision signal processing and machine learning approaches such as neural networks and other discriminate, regenerative models and GAN methodologies will be explored and evaluated. Convolutional Neural Networks (CNN), and densely connected convolutional networks will be coupled with Long Short Memory (LSTM) models in a supervised learning mechanism to learn features that are unique and stable. objective will be to outperform in performance existing eye movement approaches, increase their robustness and diversify their applicability and their acceptability in real world applications. Preliminary results in the areas of user recognition and emotion detection show promise and support our expectations.
The proposed research will establish eye biometrics as a commercial viable technology with great benefit to Canada.