Computational Intelligence - February 2017 - 26

Watchlist
(FRGC 2.0 Database)

Phase II
High Quality

Doddington
Detector

Probability
Density Function

Input Images

Posterior Probability (Phase II)
P(S |AG, AI) = 0.6046
P(G|AG, AI) = 0.0000
P(W/L|AG, AI) = 0.3954

P(S) = 0.9472
P(G) = 0.0264
P(W/L) = 0.0264

Bayesian Inference

Phase I
Posterior Probability (Phase I)
P(S |AG, AI) = 0.8759
P(G|AG, AI) = 0.1171
P(W/L|AG, AI) = 0.0071

Low Quality

Evidence Accumulation
Likelihoods
Average Genuine
P(AG|S) = 2.634. 10-3
P(AG|G) = 1.055. 10-3
P(AG|W/L) = 2.585. 10-3

Average Imposter
P(AI |S ) = 7.706. 10-1
P(AI |G) = 9.226. 10-1
P(AI |W/L) = 2.275. 10-1

Posterior Probability
(Accumulation)
P(S |AG, AI) = 0.8407
P(G|AG, AI) = 0.0000
P(W/L|AG, AI) = 0.1593

figure 7 illustrative example for the watchlist landscape.

In the terminology of border crossing passage, the results
should be interpreted as follows assuming the subject is on the
watchlist, in the optimistic (Phase II) and pessimistic scenario
(Accumulated evidence), 18 out of 100 and 5 out of 100 persons of interest respectively, have a chance to fail the watchlist
match due to impersonation.

nario is interpreted in terms of e-borders as follows: being on
the watchlist, 12 out of 100 persons of interest will be mismatched (avoid being detected).

Scenario III
Travelers in the 'Sheep' category on the watchlist (third session in Figure 10). Two-phase evidence accumulating process is well-suited for this category of travelers. Consider a
Scenario II
typical 'Sheep' traveler. The probability to belong to the catTravelers in the 'Goats' category on the watchlist (second sesegory of 'Sheep' is confirmed with a probability of 0.9612
sion in Figure 10). Consider a typical 'Goat' traveler. Risk of
estimated at Phase II, and with a similar probability of
misidentification is detected at Phase II with a probability of
0.9315 in the case of two-phase watchlist inference. That is,
0.1199. The two-phase approach decreases this risk by
93-96 out of 100 persons of interest are recognized normalimproving the detection rate from 0.1199 to 0.3919. This scely. The same tendency holds for the
other travelers in this category,
except for one: subject 04211 was
P (AI|S) = {7.566,7.786}
P (AG|S ) = {2.327,2.941}
mis-classified as a 'Goat' with probaP (AG|G ) = {7.713,13.385}
P (AI|G) = {8.903,9.550}
bility of 0.3110.
P (AG|W/L) = {1.061,4.109}
P (AI|W/L) = {1.716,2.811}
(a)
P (S) = {0.905,0.990}
P (G) = {0,0.057}
P (W/L) = {0,0.057}
(c)

(b)
P (S|AG,AI) = {0.6672,1.0000}
P (G|AG,AI) = {0.0000,0.3139}
P (W/L|AG,AI) = {0.000,0.0397}
(d)

figure 8 example for the watchlist landscape: interval probabilities of doddington's likelihoods,
categories, and posteriors. (a) genuine likelihood (·10−3); (b) imposter likelihood (·10−1);
(c) categories; (d) posterior.

26

Ieee ComputatIonal IntellIgenCe magazIne | February 2017

VI. Summary, Discussion,
and Conclusions

Our study addresses the risks of a
future generation of automated
watchlist checking in mass-transit
systems, such as e-borders. It is
understood that non-biometric traveler documents can be forged, stolen, or even worse,-they can be



Table of Contents for the Digital Edition of Computational Intelligence - February 2017

Computational Intelligence - February 2017 - Cover1
Computational Intelligence - February 2017 - Cover2
Computational Intelligence - February 2017 - 1
Computational Intelligence - February 2017 - 2
Computational Intelligence - February 2017 - 3
Computational Intelligence - February 2017 - 4
Computational Intelligence - February 2017 - 5
Computational Intelligence - February 2017 - 6
Computational Intelligence - February 2017 - 7
Computational Intelligence - February 2017 - 8
Computational Intelligence - February 2017 - 9
Computational Intelligence - February 2017 - 10
Computational Intelligence - February 2017 - 11
Computational Intelligence - February 2017 - 12
Computational Intelligence - February 2017 - 13
Computational Intelligence - February 2017 - 14
Computational Intelligence - February 2017 - 15
Computational Intelligence - February 2017 - 16
Computational Intelligence - February 2017 - 17
Computational Intelligence - February 2017 - 18
Computational Intelligence - February 2017 - 19
Computational Intelligence - February 2017 - 20
Computational Intelligence - February 2017 - 21
Computational Intelligence - February 2017 - 22
Computational Intelligence - February 2017 - 23
Computational Intelligence - February 2017 - 24
Computational Intelligence - February 2017 - 25
Computational Intelligence - February 2017 - 26
Computational Intelligence - February 2017 - 27
Computational Intelligence - February 2017 - 28
Computational Intelligence - February 2017 - 29
Computational Intelligence - February 2017 - 30
Computational Intelligence - February 2017 - 31
Computational Intelligence - February 2017 - 32
Computational Intelligence - February 2017 - 33
Computational Intelligence - February 2017 - 34
Computational Intelligence - February 2017 - 35
Computational Intelligence - February 2017 - 36
Computational Intelligence - February 2017 - 37
Computational Intelligence - February 2017 - 38
Computational Intelligence - February 2017 - 39
Computational Intelligence - February 2017 - 40
Computational Intelligence - February 2017 - 41
Computational Intelligence - February 2017 - 42
Computational Intelligence - February 2017 - 43
Computational Intelligence - February 2017 - 44
Computational Intelligence - February 2017 - 45
Computational Intelligence - February 2017 - 46
Computational Intelligence - February 2017 - 47
Computational Intelligence - February 2017 - 48
Computational Intelligence - February 2017 - 49
Computational Intelligence - February 2017 - 50
Computational Intelligence - February 2017 - 51
Computational Intelligence - February 2017 - 52
Computational Intelligence - February 2017 - 53
Computational Intelligence - February 2017 - 54
Computational Intelligence - February 2017 - 55
Computational Intelligence - February 2017 - 56
Computational Intelligence - February 2017 - Cover3
Computational Intelligence - February 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202311
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202308
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202305
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202302
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202211
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202208
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202205
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202202
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202111
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202108
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202105
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202102
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202011
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202008
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202005
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202002
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201911
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201908
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201905
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201902
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201811
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201808
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201805
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201802
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter12
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall12
https://www.nxtbookmedia.com