(2011) Image Quality, Performance, and Classification - the Impact of Finger Location
(2011) Image Quality, Performance, and Classification - the Impact of Finger Location
-
Upload
international-center-for-biometric-research -
Category
Technology
-
view
440 -
download
0
description
Transcript of (2011) Image Quality, Performance, and Classification - the Impact of Finger Location
![Page 1: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/1.jpg)
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation
IMAGE QUALITY, PERFORMANCE, AND CLASSIFICATION – THE IMPACT OF FINGER LOCATIONPurdue University: Michael Brockly | Stephen Elliott
![Page 2: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/2.jpg)
RESEARCH QUESTIONS
• How does Henry Classification differ across finger locations?
• Does image quality differ across finger locations?
• Does minutiae count differ across finger locations
• Does finger location impact performance?
![Page 3: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/3.jpg)
RESPONSIVE
• Further the understanding of Henry Classifications
• Refine zoo plot analysis• Support ideal finger theories based on
image quality and minutiae
![Page 4: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/4.jpg)
SENSOR
• Identix DFR-2080• Optical touch• 500 dpi• 15mm x 15mm
platen
![Page 5: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/5.jpg)
SUBJECTS
• Examined a subject pool of 190 users.• Collected from a multi-sensor study• Many subjects were missing images due
to error, either data collection or Failure to Acquire (FTA)
• Reduced the subject pool to 169 subjects to ensure equal numbers of fingers
![Page 6: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/6.jpg)
SUBJECT SUBSET
• 169 subjects• 118 male, 49 female• 148 office workers, 16 manual laborers
6154534947434038373635343331302928272625242322212019
40
30
20
10
0
Age
Frequency
User distribution of age
![Page 7: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/7.jpg)
SUBJECT SUBSET
• Each subject provided six successful impressions for each of:• Left index• Right index• Left middle• Right middle
• 4,080 samples in total
![Page 8: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/8.jpg)
HENRY CLASSIFICATIONS
• Neurotechnology Megamatcher v4.0.0
• Whorl• Left Slant Loop• Right Slant Loop• Tented Arch• Plain Arch• Scar
![Page 9: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/9.jpg)
HENRY CLASSIFICATIONS
Henry LI LM RI RM
# % # % # % # %
Whorl 322 31.6 235 23.0 301 29.5 212 20.8
Left Slant Loop
421 41.3 675 66.2 259 25.4 46 70.0
Right Slant Loop
190 18.6 35 3.4 366 35.9 714 4.5
Tented Arch 54 5.3 46 4.5 24 5.2 5 2.8
Plain Arch 32 3.1 24 2.4 39 3.8 14 1.4
Scar 1 0.1 5 0.5 2 0.2 5 0.5
![Page 10: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/10.jpg)
LEFT INDEX
Henry LI LM RI RM
# % # % # % # %
Whorl 322 31.6 235 23.0 301 29.5 212 20.8
Left Slant Loop
421 41.3 675 66.2 259 25.4 46 70.0
Right Slant Loop
190 18.6 35 3.4 366 35.9 714 4.5
Tented Arch 54 5.3 46 4.5 24 5.2 5 2.8
Plain Arch 32 3.1 24 2.4 39 3.8 14 1.4
Scar 1 0.1 5 0.5 2 0.2 5 0.5
![Page 11: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/11.jpg)
LEFT MIDDLE
Henry LI LM RI RM
# % # % # % # %
Whorl 322 31.6 235 23.0 301 29.5 212 20.8
Left Slant Loop
421 41.3 675 66.2 259 25.4 46 70.0
Right Slant Loop
190 18.6 35 3.4 366 35.9 714 4.5
Tented Arch 54 5.3 46 4.5 24 5.2 5 2.8
Plain Arch 32 3.1 24 2.4 39 3.8 14 1.4
Scar 1 0.1 5 0.5 2 0.2 5 0.5
![Page 12: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/12.jpg)
RIGHT INDEX
Henry LI LM RI RM
# % # % # % # %
Whorl 322 31.6 235 23.0 301 29.5 212 20.8
Left Slant Loop
421 41.3 675 66.2 259 25.4 46 70.0
Right Slant Loop
190 18.6 35 3.4 366 35.9 714 4.5
Tented Arch 54 5.3 46 4.5 24 5.2 5 2.8
Plain Arch 32 3.1 24 2.4 39 3.8 14 1.4
Scar 1 0.1 5 0.5 2 0.2 5 0.5
![Page 13: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/13.jpg)
RIGHT MIDDLE
Henry LI LM RI RM
# % # % # % # %
Whorl 322 31.6 235 23.0 301 29.5 212 20.8
Left Slant Loop
421 41.3 675 66.2 259 25.4 46 70.0
Right Slant Loop
190 18.6 35 3.4 366 35.9 714 4.5
Tented Arch 54 5.3 46 4.5 24 5.2 5 2.8
Plain Arch 32 3.1 24 2.4 39 3.8 14 1.4
Scar 1 0.1 5 0.5 2 0.2 5 0.5
![Page 14: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/14.jpg)
IMAGE QUALITY
• Aware M1 Pack v3.0.0
• Fingerprint image quality is a prediction of a matching software’s performance
![Page 15: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/15.jpg)
IMAGE QUALITY
![Page 16: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/16.jpg)
RIGHT INDEX
![Page 17: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/17.jpg)
RIGHT MIDDLE
![Page 18: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/18.jpg)
LEFT INDEX
![Page 19: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/19.jpg)
LEFT MIDDLE
![Page 20: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/20.jpg)
MINUTIAE COUNT
• Aware M1 Pack v3.0.0
• The count of local ridge characteristics
![Page 21: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/21.jpg)
MINUTIAE COUNT
![Page 22: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/22.jpg)
LEFT INDEX/MIDDLE
![Page 23: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/23.jpg)
RIGHT INDEX/MIDDLE
![Page 24: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/24.jpg)
IMAGE QUALITY AND MINUTIAE
![Page 25: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/25.jpg)
ZOO PLOT
• Neurotechnology Megamatcher v4.0.0• Performix v3.1.9
• Calculated by a minutiae-based matcher
![Page 26: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/26.jpg)
ZOO PLOT OVERVIEW
• Maps the relationship between a user’s genuine and imposter match results defines four additional classes of worms, doves, chameleons, and phantoms
![Page 27: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/27.jpg)
CLASSIFICATIONS OF ANIMALS
• Chameleons always appear similar to others, receiving high match scores for all verifications. Chameleons rarely cause false rejects, but are likely to cause false accepts.
• Phantoms lead to low match scores regardless of who they are being matched against; themselves or others.
![Page 28: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/28.jpg)
CLASSIFICATIONS OF ANIMALS
• Doves are the best possible users in biometric systems. They matching well against themselves and poorly against others.
• Worms are the worst users of a biometric system. Where present, worms are the cause of a disproportionate number of a system’s errors.
![Page 29: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/29.jpg)
ADVANTAGES OF ZOO PLOTS OVER ROC/DET CURVES
• Traditional methods of evaluation focus on collective error statistics such as Equal Error Rates (EERs) and Receiving Operating Characteristic (ROC) curves.
• These statistics are useful for evaluating systems globally, but ignore problems associated with individuals and subgroups of the population. The biometric menagerie is a formal approach to user-centric analysis.
![Page 30: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/30.jpg)
ADVANTAGES OF ZOO PLOTS OVER ROC/DET CURVES
• In many real world situations it has been observed that user groups performance varies based on any number of demographic factors.
• Researchers and system integrators are interested in identifying which of these groups are performing poorly as they may be causing a disproportionate number of verification errors.
![Page 31: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/31.jpg)
ZOO PLOT
![Page 32: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/32.jpg)
ZOO PLOT
Worms
Phantoms
Chameleons
Doves
![Page 33: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/33.jpg)
ZOO ANIMAL BY LOCATION
![Page 34: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/34.jpg)
RIGHT INDEX
![Page 35: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/35.jpg)
RIGHT INDEX
![Page 36: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/36.jpg)
RIGHT INDEX
![Page 37: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/37.jpg)
LEFT MIDDLE
![Page 38: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/38.jpg)
FUTURE WORK
• Determine if these results hold true for other fingerprint sensors
• Deeper analysis of the impact of poor performing animals
![Page 39: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/39.jpg)
CONTACT INFORMATION
• Michael Brockly• Undergraduate Researcher at BSPA Lab• [email protected]
• Stephen Elliott PhD• Associate Professor at BSPA Lab• [email protected]
![Page 40: (2011) Image Quality, Performance, and Classification - the Impact of Finger Location](https://reader034.fdocuments.in/reader034/viewer/2022051817/5479ee09b37959442b8b4910/html5/thumbnails/40.jpg)
BIOMETRICS LABBiometric Standards, Performance and Assurance LaboratoryDepartment of Technology, Leadership and Innovation
Questions?