HUMAN-BIOMETRIC SENSOR
INTERACTION AUTOMATION
USING THE KINECT
ZACH MOORE
•Can the Kinect 2 be used to determine
Human-Biometric Sensor Interaction errors
automatically in real-time?
RESEARCH QUESTION
METHODOLOGY
•Phase 1: Programming
•Phase 2: Construction
•Phase 3: Pilot Study
•Phase 4: Data Collection
PHASES
KINECT BODY TRACKING
• All face values are a built in
feature of the Kinect.
• These track the eyes, nose,
and mouth corners.
• 17 upper body points
tracked not including the
face.
KINECT MEASUREMENT CHECKS
CORRECT PRESENTATION
INCORRECT PRESENTATION
CLASSIFYING ERRORS
•Subject chooses the type of luggage that
closely represents what they usually carry in
an airport
•They can bring their own, or choose from a
selection
•Given mock passport and immigration form
PROTOCOL
• They walk up to the booth and give the forms to the
agent (test admin)
• The test admin asks them to provide their 10-print
samples
• Once that’s done, they start he iris capture process.
• This is where the Kinect is determining any errors
• They provide one sample, gather their belongings, and
walk away from the booth
PROTOCOL
Pilot
Ground
Truth
Scenario
PROCESS MAP
Research Question: Can the Kinect 2 be
used to determine Human-Biometric Sensor
Interaction errors automatically in real-time?
Booth and
usability study.
Proved the Kinect
was reliable.
My thesis. Will
determine if the
Kinect can be used
to classify errors
automatically.
Future work. Provide
real-time feedback
to users to test if
Kinect affects
throughput.
•Reviewed the video footage of all 100 subjects
•Used to determine if presentation was correct or
incorrect
•Exported the AOptix logs
•Used to determine the HBSI metric
•All done after the data collection had
concluded
GROUND TRUTH CLASSIFICATION
•Used the body points from the Kinect sensor
•This data was used to determine if the
presentation was correct or incorrect
•Monitored the AOptix state change over the
network
•Used to determine HBSI Metric
•All done in real-time
KINECT CLASSIFICATION
AOPTIX STATES[1] [2] [3] [4] [5]
[6] [8] [11] [13] [15]
[21] [22] [23] [25]
CLASSIFICATION PROCESS
RESULTS
GENDER REPORT
Female
Male
Category
47.0%
53.0%
Gender
Gender Count
Male 47
Female 53
Total 100
AGE BREAKDOWN
49+41-4833-4026-3218-25
40
30
20
10
0
Age Group
Count
11
10
7
31
41
Age Breakdown
ETHNICITY
Indian
Arab
M
ixed
H
ispanic
Asian
or Pacific Islander
O
ther
African
Am
erican
Asian
Caucasian
70
60
50
40
30
20
10
0
Ethnicity
Count
112224
8
23
57
Subject Ethnicity
CLASSIFICATION RESULTS
GROUND TRUTH CLASSIFICATIONS
EXAMPLE INTERACTION
Subject ID Ground Truth Classification Kinect Classification Correct Classification
066 FTD FTD Y
066 FTD FTD Y
066 FTD FTD Y
066 FTD FTD Y
066 SPS SPS Y
GROUND TRUTH COMPARED TO KINECT
•Cause:
•The AOptix device switched states so quickly, that
the Kinect did not detect the change
•The Kinect has a fixed frame refresh rate (30fps)
•From the Kinect’s point of view, no error
occurred, so it did not classify the presentation
“NONE” CLASSIFICATION
“NONE” CLASSIFCATION
Refresh FrameRefresh Frame
Kinect
AOptix
Subject ID Ground Truth Classification Kinect Classification Correct Classification
028 FTD FTD Y
028 FTD FTD Y
028 FTD NONE N
028 FTD NONE N
028 FTD NONE N
028 SPS SPS Y
“NONE” EXAMPLE
HBSI METRICS CLASSIFIED AS “NONE”
CI
DI
FTD
FTP
SPS
Category
3
1
52
13
1
HBSI Metrics Classified as "NONE" by Kinect
• 70 instances of “NONE”
classification total
• Of these 70, the ground
truth equivalent metric
classification is shown
Correct
Presentation
Incorrect
Presentation
Category
23.9%
76.1%
Ground
Truth
Correct
Presentation
PRESENTATION ACCURACY
Correct Presentation
Incorrect Presentation
Category
48.3%
51.7%
Kinect Presentation Classifications
Correct Presentation
Incorrect Presentation
Category
23.9%
76.1%
Ground Truth Presentation Classifications
ACCURACY OF KINECT CLASSIFICATIONS
Different Classification
Same Classification
Category
62.9%
37.1%
Kinect Classifications Compared to Ground Truth
ACCURACY BY METRIC
CI DI FI
FTD FTP SPS
Different Classification
Same Classification
Category
50.0%
50.0%
51.4%
48.6%
81.0%
19.0%
52.5%
47.5%
80.0%
20.0%
80.6%
19.4%
Kinect Classifications Compared to Ground Truth by Metric
•How accurate was the Kinect at determining
these errors when it did notice the state
change?
•By removing the observations that include
“NONE”, does the accuracy improve?
FURTHER QUESTIONS RAISED
REMOVING “NONE’ CLASSIFICATIONS
Subject ID Ground Truth Classification Kinect Classification Correct Classification
028 FTD FTD Y
028 FTD FTD Y
028 FTD NONE N
028 FTD NONE N
028 FTD NONE N
028 SPS SPS Y
Subject ID Ground Truth Classification Kinect Classification Correct Classification
028 FTD FTD Y
028 FTD FTD Y
028 SPS SPS Y
PRESENTATION ACCURACY – WITHOUT
“NONE”
Correct Presentation
Incorrect Presentation
Category
25.4%
74.6%
Ground Truth Presentation Classifications
Correct Presentation
Incorrect Presentation
Category
29.1%
70.9%
Kinect Presentation Classifications
ACCURACY OF KINECT CLASSIFICATIONS
– WITHOUT “NONE”
Different Classification
Same Classification
Category
85.7%
14.3%
Kinect Classifications Compared to Ground Truth
ACCURACY BY METRIC – WITHOUT
“NONE”
CI DI FI
FTD FTP SPS
Different Classification
Same Classification
Category
66.7%
33.3%
79.2%
20.8%
81.0%
19.0%
91.2%
8.8%
88.9%
11.1%
84.4%
15.6%
Kinect Classifications Compared to Ground Truth by Metric
CONCLUSIONS AND FUTURE
WORK
•The Kinect can be used to determine HBSI errors
in real-time
• The accuracy of which depends on the thresholds the
Kinect operates under
•The refresh rate of the Kinect was not high enough
to detect all state changes from the AOptix device
•This research provides a foundation for future work
CONCLUSIONS
• Increasing Kinect refresh rate or using different sensor
• Developing real-time feedback to both subject and test
administrator
• Test change in throughput and performance
• Adjusting Kinect thresholds for correct/incorrect
presentation classifications
• Use Kinect gesture recognition to use for different
modalities (fingerprint)
• Implement in operational testing
FUTURE WORK
QUESTIONS?

HBSI Automation Using the Kinect

Editor's Notes

  • #13 Booth and usability study Determined that it was a reliable measuring tool Ground Truth My thesis Can it be used to determine errors Future work Develop feedback and test to see if it affects throughput in any way
  • #14 1.
  • #29 Most of the “NONE” classifications occurred during FTD and DI interactions. The five that were not were ground truthed and it was determined that these were due to the Kinect not tracking the user for part of or the whole transaction.
  • #36 Jumped from 62.9 percent accuracy to 85.7% accuracy.