BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation...
CONTRIBUTORS TO THEPRESENTATION  •   Michael Brockly     •   Jacob Hasslegren  •   Kevin O’Connor      •   Rob Larsen  •  ...
AGENDA  •   What are biometrics?  •   The missing pieces of biometric testing  •   The HBSI model  •   Evolution of the mo...
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation...
BIOMETRIC TESTING  • Traditional biometric testing     – Algorithm testing        • Well established metrics        • Well...
TESTING AND EVALUATION  • Essentially trying to understand how a    system performs    – Maybe more fundamentally – who or...
GAPS IN BIOMETRIC TESTING   • There have been several papers on the     contribution of individual error on     performanc...
GAPS IN BIOMETRIC TESTING   • Training     – How do users get accustomed to devices     – Can they remember how to use the...
GAPS IN BIOMETRIC TESTING   • Accessibility      – How many people know people (!) who have        problems with interacti...
GAPS IN BIOMETRIC TESTING   • Human Factors     – Testing and evaluating biometric systems by       looking at how the use...
GAPS IN BIOMETRIC TESTING   • It the error always subject centric?      – The role of the device?      – The role of the o...
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation...
DEVELOPMENT OF THE MODEL  • The HBSI model is concerned with the    data collection portion of the biometric    model     ...
HBSI MODEL                                                  Usability                              Human    Ergonomics    ...
UNDERLYING MODEL
MODALITY TESTING AND HBSI    Year        Hand                 Finger                  Iris            Face                ...
MODEL DEVELOPMENT - V1
MODEL DEVELOPMENT - V2
INCLUSION OF OTHER MODELS  • General Biometric Model  • Operation Times Model    (Lazarick, Kukula, et.al)
Fuji, et. al (2011)
HBSI METRICS V2      Metrics created and validated for:      • Iris      • Fingerprint (different sensors)      • Signatur...
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation...
UNDERLYING MODEL EXAMPLES   More actors:   • Subject (typically     the biometric donor)   • Operator   • Other people in ...
UNDERLYING MODEL EXAMPLES            Additional variables:            Subject conditions            • moisture,           ...
DETERMINATION OF ERRORS V1  • Process:    – Recorded in real time as the study is      underway    – Interactions are code...
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation...
MOTIVATION  • Video coding is time consuming  • Inter-rater reliability    – Requires good robust definitions
DEFINING MOVEMENT                                                                          Jake Hasselgren (2011)   Slouch...
MICROSOFT ® SDK INTERFACE
MICROSOFT ® KINECT™ SKELETALTRACKING SYSTEM                                        Source:Source: http://msdn.microsoft.co...
SLOUCHING  • Dictionary Definition       • Slouching-A gait or posture characterized by an         ungainly stooping of th...
SLOUCHING  • Tracking Points to be used:    •   Shoulder_Right    •   Shoulder_Left    •   Shoulder_Center    •   Head    ...
SLOUCHINGHighlight what isslouchingBreak it into left right                           • Left Slouching:                   ...
SOLUTIONS TO THE CHALLENGESOF DEFINING  • A multi point approach can help solve    the majority of the problems when    de...
HEAD DISPLACEMENT  • Definition of Head Movement:  • Voluntary or involuntary motion of head    that may be relative to or...
HEAD DISPLACEMENT                    •   Critical Tracking Points (TPs):                        1.   Head (H)             ...
DEFINITION OF HEAD MOVEMENTBASED ON TRACKING POINTS Head Movements            Tracking Points Definition                  ...
HOW WILL THIS WORK?A QUICK ROADMAP                                           Feedback to                         Automatic...
ACTIVITIES   • Link behavior and interaction to the     image   • Understand the basic performance     characteristics   •...
The benefit is to examinethe information associatedwith the sample, but alsothe video interaction of theimage.HBSI V3 has ...
QUESTIONS?Get Involved in shaping these projects – contact elliott@purdue.edu to participate in the                       ...
KEEP UPDATED  • Scan the QR code with your phone or    follow this link for more information:  • http://eepurl.com/kxG-r
Upcoming SlideShare
Loading in …5
×

(2012) Human Factors and Ergonomics Society Presentation at Purdue University

1,091 views

Published on

Presentation gave at the Purdue University Human Factors and Ergonomics Society student group.

Published in: Education, Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
1,091
On SlideShare
0
From Embeds
0
Number of Embeds
41
Actions
Shares
0
Downloads
18
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide
  • NOTE – to everyone – this is the format for the ppt’s.
  • ALL : complete or change as necessary
  • (2012) Human Factors and Ergonomics Society Presentation at Purdue University

    1. 1. BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation EVOLUTION OF THE HUMAN BIOMETRICS SENSOR INTERACTION MODEL STEPHEN ELLIOTT HFES PRESENTATION – MARCH 29. 2012
    2. 2. CONTRIBUTORS TO THEPRESENTATION • Michael Brockly • Jacob Hasslegren • Kevin O’Connor • Rob Larsen • Carl Dunkelberger • Chris Clouser • Tyler Veegh • Craig Hebda • Thomas Cimino • Weng Kwong • Rob Pingry Chan • Brent Shuler
    3. 3. AGENDA • What are biometrics? • The missing pieces of biometric testing • The HBSI model • Evolution of the model • Summer 2012 meetings
    4. 4. BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation WHAT IS MISSING IN BIOMETRIC TESTING
    5. 5. BIOMETRIC TESTING • Traditional biometric testing – Algorithm testing • Well established metrics • Well understood testing methodologies • Operational testing – Harder to do • Access to environments • Test methodologies dependent in some cases on the test
    6. 6. TESTING AND EVALUATION • Essentially trying to understand how a system performs – Maybe more fundamentally – who or what is causing the errors
    7. 7. GAPS IN BIOMETRIC TESTING • There have been several papers on the contribution of individual error on performance – What causes these errors? • There are some papers that examine meta-data and the contribution of variables (age) and examines the training of algorithms
    8. 8. GAPS IN BIOMETRIC TESTING • Training – How do users get accustomed to devices – Can they remember how to use them – How do we provide good training to the users that has a consistent message
    9. 9. GAPS IN BIOMETRIC TESTING • Accessibility – How many people know people (!) who have problems with interacting with a biometric systems – How do we deal with accessibility and usability issues • Hearing and sight issues
    10. 10. GAPS IN BIOMETRIC TESTING • Human Factors – Testing and evaluating biometric systems by looking at how the users interact with the system • Are performance results different in an operational environment than collect in a lab? • Are these performance results due to the environment?
    11. 11. GAPS IN BIOMETRIC TESTING • It the error always subject centric? – The role of the device? – The role of the operator?
    12. 12. BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation OVERVIEW OF HBSI MODEL
    13. 13. DEVELOPMENT OF THE MODEL • The HBSI model is concerned with the data collection portion of the biometric model – Consistent and repeatable presentation to the sensor
    14. 14. HBSI MODEL Usability Human Ergonomics Biometric Sensor System Image Quality Human-Biometric Sensor Interaction (HBSI) Conceptual model for HBSI
    15. 15. UNDERLYING MODEL
    16. 16. MODALITY TESTING AND HBSI Year Hand Finger Iris Face DSV 2004 Age Mobile iris Illumination Different devices 2005 Co-Rec 2006 Height /Placement 2007 Habituation Force 2008 Gender 2009 Initial HBSI Calc Force Training 2010 Fixed iris 2011 Gender Device (different sensors) 2012 Hand alignment Force HBSI Detractors Forgery Finger interactions / Training / Kinect Kinect 2012 Interaction Age Interaction Age Interaction Age Interaction Age Interaction Age
    17. 17. MODEL DEVELOPMENT - V1
    18. 18. MODEL DEVELOPMENT - V2
    19. 19. INCLUSION OF OTHER MODELS • General Biometric Model • Operation Times Model (Lazarick, Kukula, et.al)
    20. 20. Fuji, et. al (2011)
    21. 21. HBSI METRICS V2 Metrics created and validated for: • Iris • Fingerprint (different sensors) • Signature Verification Record theenvironment (video and sometimesaudio) from different angles in order to watch the subjectand to classify their presentation -typically 3 videoangles and operator screen
    22. 22. BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation HBSI MODEL 3.0
    23. 23. UNDERLYING MODEL EXAMPLES More actors: • Subject (typically the biometric donor) • Operator • Other people in the environment
    24. 24. UNDERLYING MODEL EXAMPLES Additional variables: Subject conditions • moisture, • elasticity, • oiliness Collected conditions such as: • temperature • humidity
    25. 25. DETERMINATION OF ERRORS V1 • Process: – Recorded in real time as the study is underway – Interactions are coded – Metrics of the evaluation model are completed – Interaction errors are classified as HBSI terms
    26. 26. BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation KINECT AND THE HBSI MODEL V.3 CRAIG HEBDA | ROB PINGRY | WENG KWONG CHAN | BRENT SHULER
    27. 27. MOTIVATION • Video coding is time consuming • Inter-rater reliability – Requires good robust definitions
    28. 28. DEFINING MOVEMENT Jake Hasselgren (2011) Slouched: Subject is not standing up straight during fingerprint scan. Head Movement: Subject’s head is not still during fingerprint scan. Body Movement: Subject’s body is not still during fingerprint scan. Upright: Subject is standing up straight during fingerprint scan. Labored Walking: Subject has bag or other item on shoulder when approaching device Pivoting Palm: Subject’s hand pivots on edge of device Rocking Fingers: Subjects fingers rock from one finger to the next when hand is placed on device Slapping Hand: Subject slaps hand on to the device Angled Fingers: Subjects fingers are at an angle other then 90 degrees from edge of the device
    29. 29. MICROSOFT ® SDK INTERFACE
    30. 30. MICROSOFT ® KINECT™ SKELETALTRACKING SYSTEM Source:Source: http://msdn.microsoft.com/en- http://www.genbetadev.com/herramientas/us/library/hh438998.aspx disponible-el-sdk-de-kinect-para- desarrollar-nuestras-propias-aplicaciones- usando-los-sensores
    31. 31. SLOUCHING • Dictionary Definition • Slouching-A gait or posture characterized by an ungainly stooping of the head and shoulders or excessive relaxation of body muscles. • Points of interest: • -Shoulders • -Head • -Spine • -Hips Source:http://www.merriam-webster.com/dictionary/slouch
    32. 32. SLOUCHING • Tracking Points to be used: • Shoulder_Right • Shoulder_Left • Shoulder_Center • Head • Spine • Hip_Center • Hip_Right • Hip_Left
    33. 33. SLOUCHINGHighlight what isslouchingBreak it into left right • Left Slouching: • Left shoulder will be lower then the right shoulder. • All points on left arm will be lower then base image. • Head will be tilted to left. • Left hip will be lower then right hip. • Spine point will move slightly up and right. =Movement Up =Movement Down
    34. 34. SOLUTIONS TO THE CHALLENGESOF DEFINING • A multi point approach can help solve the majority of the problems when describing what is slouching. • Use a combination of how much each point moves to determine if the subject is slouching or just moving one part of their body.
    35. 35. HEAD DISPLACEMENT • Definition of Head Movement: • Voluntary or involuntary motion of head that may be relative to or independent of body. • http://www.medical-dictionary.cc/what- does/head-movement-mean
    36. 36. HEAD DISPLACEMENT • Critical Tracking Points (TPs): 1. Head (H) 2. Shoulder_Center (SC) • Associated Tracking Points (TPs): 1. Shoulder_Right (SR) 2. Shoulder_Left (SL)
    37. 37. DEFINITION OF HEAD MOVEMENTBASED ON TRACKING POINTS Head Movements Tracking Points Definition Changes in Coordinates Lowering head H approaches SC X, Y, maybe Z too Nodding H moves back and forth from SC repeatedly X, Y, maybe Z too Head turning Turn to the left: H moved to the left X, Y, Z Turn to the right: H moved to the right Head tilted to one side Tilt to the left: H moved to the left X, Y Tilt to the right: H moved to the right Head bobbing H moves in random direction with minimal distance X, Y, Z Head sliding forward H moves forward Z Head wagging H moves in left and right rapidly X, Y Source: http://www.thefreedictionary.com/Head+Movements
    38. 38. HOW WILL THIS WORK?A QUICK ROADMAP Feedback to Automatic the identification Observation of user, customiz and error ed to their classification of interaction error error
    39. 39. ACTIVITIES • Link behavior and interaction to the image • Understand the basic performance characteristics • Relay back whether the interaction (or change in interaction) affects performance
    40. 40. The benefit is to examinethe information associatedwith the sample, but alsothe video interaction of theimage.HBSI V3 has (will have):• video and audio interaction – Watch the interaction – Understand who is contributing the error – Replay the interaction in real time as it was collected• Metadata collected and searchable
    41. 41. QUESTIONS?Get Involved in shaping these projects – contact elliott@purdue.edu to participate in the development of the model Teleconferences over the summer 2012 period • Other actors • Contribution of the operator to the error • Contribution of the test administrator to the error • HBSI workflow • Semi-automatic coding of the model using Kinect • New work • Accessibility study – hearing and sight impaired (started Jan 2012) • Contribution of cost to the model (started Jan 2011) • Examining the role of the impostor (thinking …. As this model only has been rested in a “genuine” environment) • Development of products that can help improve interactions
    42. 42. KEEP UPDATED • Scan the QR code with your phone or follow this link for more information: • http://eepurl.com/kxG-r

    ×