Eye Movements Biometrics Where you look shows who you are

Slides:



Advertisements
Similar presentations
Introduction to Eye Tracking
Advertisements

Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Practical Gaze Tracking Peter Elliott CS 498 Spring 2009.
Electro-Oculography (EOG) Measurement System The goal : To measure eye movement with maximum accuracy using skin electrodes around the eyes that detect.
PALM VEIN TECHNOLOGY.
Video- and Audio-based Biometric Person Authentication Motivation: Applications. Modalities and their characteristics. Characterization of a biometric.
Iris Recognition By Mohammed, Ashfaq Ahmed. Introduction Iris Recognition is a Biometric Technology which deals with identification based on the human.
Authentication for Humans Rachna Dhamija SIMS, UC Berkeley DIMACS Workshop on Usable Privacy and Security Software July 7, 2004.
Biometrics and Authentication Shivani Kirubanandan.
Biometrics Kyle O'Meara April 14, Contents Introduction Specific Types of Biometrics Examples Personal Experience Questions.
Eye Movements and Visual Attention
Eye tracking: principles and applications 廖文宏 Wen-Hung Liao 12/10/2009.
 An eye tracking system records how the eyes move when a subject is sitting in front of a computer screen.  The human eyes are constantly moving until.
BIOMETRICS By: Lucas Clay and Tim Myers. WHAT IS IT?  Biometrics are a method of uniquely identifying a person based on physical or behavioral traits.
Eye movements: a primer Leanne Chukoskie, Ph.D.. Two classes of eye movements Gaze-stabilizing – Vestibulo-ocular reflex (VOR) – Optokinetic Nystagmus.
Access Control Via Face Recognition. Group Members  Thilanka Priyankara  Vimalaharan Paskarasundaram  Manosha Silva  Dinusha Perera.
Department of ORL-HNS Maastricht University Medical Centre The Netherlands comparison video-oculography and electro-nystagmography using the search coil.
Biometrics Authentication Technology
PRESENTATION ON BIOMETRICS
Biometric Technologies
Research Background: Depth Exam Presentation
Counting How Many Words You Read
INTRODUCTION TO BIOMATRICS ACCESS CONTROL SYSTEM Prepared by: Jagruti Shrimali Guided by : Prof. Chirag Patel.
By Diana Liwanag. Overview The problem What are biometrics? –What are the different types? Short video of a system with a fingerprinting device. Identifying.
What does it mean to us?.  History  Biometrics Defined  Modern Day Applications  Spoofing  Future of Biometrics.
By Kyle Bickel. Road Map Biometric Authentication Biometric Factors User Authentication Factors Biometric Techniques Conclusion.
RAJAT GOEL E.C.-09. The information age is quickly revolutionizing the way transactions are completed. Using the proper PIN gains access, but the user.
Mobile eye tracker construction and gaze path analysis By Wen-Hung Liao 廖文宏.
WP 6: Analysis and evaluation Hans H. K. Andersen Cogain Kick-Off Tampere, Finland.
Presented By Bhargav (08BQ1A0435).  Images play an important role in todays information because A single image represents a thousand words.  Google's.
National Taiwan Normal A System to Detect Complex Motion of Nearby Vehicles on Freeways C. Y. Fang Department of Information.
Perceptive Computing Democracy Communism Architecture The Steam Engine WheelFire Zero Domestication Iron Ships Electricity The Vacuum tube E=mc 2 The.
Sparse Coding: A Deep Learning using Unlabeled Data for High - Level Representation Dr.G.M.Nasira R. Vidya R. P. Jaia Priyankka.
Introduction to Machine Learning, its potential usage in network area,
EYE TRACKING TECHNOLOGY
EYE-GAZE COMMUNICATION
Analyzing Eye Tracking Data
INSTRUCTIONAL DESIGN Many definitions exist for instructional design 1. Instructional Design as a Process: 2. Instructional Design as a Discipline: 3.
Eye Movement & Reading Awareness lab
SIE 515 Design Evaluation Lecture 7.
Presented by Jason Moore
Human-Operator Monitoring System
11.10 Human Computer Interface
Eye Movement & Reading Awareness lab
EYE-GAZE COMMUNICATION
A Seminar Report On Face Recognition Technology
MSC projects for for CMSC5720(term1), CMSC5721(term2)
Biometrics.
Artificial Intelligence Lecture No. 5
Enhancing User identification during Reading by Applying Content-Based Text Analysis to Eye- Movement Patterns Akram Bayat Amir Hossein Bayat Marc.
How do we realize design? What should we consider? Technical Visual Interaction Search Context of use Information Interacting/ transacting.
Computer Vision Lecture 2: Vision, Attention, and Eye Movements
COMPUTER VISION Tam Lam
Facial Recognition [Biometric]
Biometrics.
Outline Announcements Syllabus General Introduction to Computer Vision
Identifying Confusion from Eye-Tracking Data
A SEMINAR REPORT ON BIOMETRICS
眼動儀與互動介面設計 廖文宏 6/26/2009.
iSRD Spam Review Detection with Imbalanced Data Distributions
Driver Verification Using Eye Movements and Blinking
Presented by: k.ramya krishna
A visual surveillance using real-time curve evolution based on the level-set method and pan-tilt camera Good afternoon ~ sir. Today I want to talk about.
Finding your way: The accessibility considerations for Digital Signage and Wayfinding November 2018.
Visual-based ID Verification by Signature Tracking
Visuals.
Experimental Evaluation
Name of Research Program: TRUST, SPRING 2011
Eye-Based Interaction in Graphical Systems: Theory & Practice
Accessibility.
Presentation transcript:

Eye Movements Biometrics Where you look shows who you are Paweł Kasprowski, PhD Silesian University of Technology

Outline Eye movements at a glance How to measure eye movements Why do we measure it? Eye movements biometrics (EMB) – advantages EMVICompetition Summary

Physiology of eye movements Non-uniform picture quality across the visual field Area of high visual acuity zone Fovea Acuity drops outside Eyes in constant movement

Eye movements Oculomotor system Movement Elements Six muscles Three nerves Movement voluntary involuntary Elements Fixations Saccades Smooth pursuits Tremors, drifts

Eye movements Oculomotor system Movement Elements Six muscles Three nerves Movement voluntary involuntary Elements Fixations Saccades Smooth pursuits Tremors, drifts

Eye movements Oculomotor system Movement Elements Six muscles Three nerves Movement voluntary involuntary Elements Fixations Saccades Smooth pursuits Tremors, drifts

Eye movement measurement First researches: Emile Javal, 1879 First eye-tracker: Edmund Burke Huey, 1897 Different methodologies: Contact lens Elektro-oculography (EOG) Video-oculography (VOG)

Contact lenses Very accurate but very intrusive

Elektrooculography (EOG) Electric potentials measured with electrodes placed around the eyes Measures rather movement that gaze point

Videooculography (VOG) Detects eyes on face image Measures reflection of infrared light Purkinje images 1-4 Non-invasive May even be covert Computational power needed

Our eye tracker Frequency: 1 kHz Accuracy: about 1 degree

Eye movement visualization X-Y temporal graphs

Eye movement visualization Scan paths Olivier Le Meur, http://www.irisa.fr/temics/staff/lemeur/

Eye movement visualization Heat maps Tommy Strandvall, http://eyetracking.me

Eye movement usages Cognitive studies Medicine Usability of interfaces How our brain works Education, experience Medicine Diagnoses Usability of interfaces What attracts attention on an image? Advertisement, web pages Eye as a pointer Gaze instead of mouse? Adjusting image quality basing of a gaze point

Reading Every man reads differently Reading easy and difficult texts is different It is possible to find out education level!

Yarbus (1967) The way we move our eyes depends on what we are looking for Yarbus, A. L. (1967), Eye Movements and Vision, New York: Plenum

Gender differences EyeTrackShop, MRC International

Gender differences EyeTrackShop, MRC International

Interface usability Checking if application, interface, web page or leaflet is readable and understandable Checking if users pay attention where we want FengGui, www.feng-guii.com

Eye as a pointer Gaze instead of mouse? Problem: vision is our input not output Eye pointing may be not comfortable "Midas touch problem" Possible usages: For disabled Adaptive interface PIN entering (eye signature) CEATEC, Fujitsu eye-tracking technology

Eye Movement Biometrics Identification of people based on their eye movements Another example of biometric identification method Weird Science: 10 Forms of Biometric Authentication http://threatpost.com

Advantages Physiological elements Behavioral elements Acceptability Oculomotor Plant Muscles Behavioral elements Depends on stimulus "Measures" knowledge and experience Subject must be conscious Acceptability Accessibility Multimodality

Acceptability Easy to use Non-intrusive May be done during normal activity Possible covert identification

Accessibility Expensive for now It changes! Simple VOG eye-trackers Tablets Smartphones Mirametrix, Samsung

Multimodal biometrics Video-based eye trackers may be easily combined with: Face recognition Iris scanning Mouse and keystroke dynamics Other imaging methods

Challenges Distinctiveness Repeatability as in every behavioral method

State of the Art Idea of Prof. Ober (1945-2007) First publications inventor of Ober2 eye tracker First publications KASPROWSKI, P., OBER, J. 2003. Eye movement tracking for human identification, In 6th World Conference BIOMETRICS’2003, London. (Best Poster on Technological Advancement) KASPROWSKI, P., OBER, J. 2004. Eye Movement in Biometrics, In Proceedings of Biometric Authentication Workshop, European Conference on Computer Vision in Prague 2004, LNCS 3087, Springer-Verlag. KASPROWSKI P., OBER J. 2005. Enhancing eye movement based biometric identification method by using voting classifiers. SPIE Defense & Security Symposium.

Research centers Texas State University (Komogortsev) Jumping point, reading, OPC, CEM, +Iris SC University, Finland (Bendarik, Kinnunen) Static point stimulus, task independent University of Patras, Greece (Rigas) Static images (faces) Silesian Univ. of Technology (Kasprowski) Jumping point, noninteractive

EMB Challenges Results are not comparable No established techniques Different equipment, experiments, methods No established techniques Lack of common databases Our idea: competition similar to FVC

Competition Competition uses ready-to-use datasets Competition goals Eye movement recordings without proper identification Some training data Search for the best classification algorithm Competition goals Popularize the EMB Provide single reference point with a set of datasets Highlight importance of data quality

EMVIC 2012 Official competition of: Task: Web page: IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012) Task: Assign every test sample to proper user id Web page: www.emvic.org www.kaggle.com/emvic

EMVIC Competition Four different datasets Jumping point type Dataset A (978 recordings of 37 persons) 8 sec, 4-100 rec. per person Dataset B (4168 recordings of 75 persons) 8 sec, 4-200 rec. per person Dataset C (116 recordings of 29 persons) Only left eye, 4 rec. per person, horizontal jumps Dataset D (108 recordings of 27 persons) Only left eye, 4 rec. per person, random jumps

Competition rules Publicly available: Evaluation Labeled training set Unlabeled testing set Evaluation Participants should correctly label unlabeled samples Training samples for building classification model Emvic.org and Kaggle competitions Only Dataset A for Kaggle

Competitors 45 users registered in the main competition 106 submissions Quatar, Wisconsin, Dehli, Brno, Alaska, Luxemburg… 49 competitors in Kaggle competition 524 submissions (only one daily limit per user)

Results Dataset A – 97% Dataset B – 95% Dataset C – 58% Dataset D – 67% Question: Why are the results so different for different datasets?

Why so different results? Number of samples per person About 26 per person in A, 55 in B, exactly 4 for C,D Sequences of samples in A, B Lack of calibration and worse data quality in A, B Horizontal movements only for C Random stimulus for D Last but not least: order of datasets Competitors started with Dataset A and didn't have enough time for C and D

Summary Eye movement biometrics has a lot of advantages Vision is the main human being's input It is not mature enough We need more generally available and comparable datasets

Thank you for your attention Paweł Kasprowski kasprowski@polsl.pl pawel@kasprowski.pl Drinks reception is waiting! Thank you for your attention