Monday, August 09, 2004

THEORY OR REAL-WORLD TESTS

THEORY OR REAL-WORLD TESTS: WHICH ROAD SHOULD FUSION BIOMETRICS TAKE?
By Yona Flink
Over the years there has been various discussions on whether combining twoor more biometrics (Fusion or Layered) enhances the accuracy of the biometric process for verification and identification. I have been of the opinion, that by intelligently layering two different biometrics, the resulting error rates would be reduced. However, on the occasions that I presented such a position, others turned to mathematical proofs andstatistical documentation using a paper by Professor Daugman. I have great respect for Professor Daugman positions, but the basis of Professor Daugman's paper are based on a different premise than those taken my myselfand others. The below documents are in the following order:
  • A brief outline of Professor Daugman's paper.
  • An email to the BC that I sent a year ago outlining a proposal forlayered biometrics.
  • An article appearing in Wave this month.Combining Multiple Biometrics John Daugman, The Computer Laboratory, Cambridge University Overview This short note investigates the consequences of combining two or morebiometric tests of identity into an "enhanced" test.

There is a common and intuitive assumption that the combination of different tests must improve performance, because "surely more information is better than less information." On the other hand, a different intuition suggests that if astrong test is combined with a weaker test, the resulting decision environment is in a sense averaged, and the combined performance will lie somewhere between that of the two tests conducted individually (and hence will be degraded from the performance that would be obtained by relying solely on the stronger test). There is truth in both intuitions. The key to resolving the apparent paradoxis that when two tests are combined, one of the resulting error rates (False Accept or False Reject rate) becomes better than that of the stronger of thetwo tests, while the other error rate becomes worse even than that of the weaker of the tests. If the two biometric tests differ significantly in their power, and each operates at its own cross-over point, then combiningthem gives significantly worse performance than relying solely on the stronger biometric. Example: Combination of two hypothetical biometric tests, one stronger thanthe other: Suppose weak Biometric 1 operates with both of its error rates equal to 1 in 100, and suppose stronger Biometric 2 operates with both of its error ratesequal to 1 in 1,000. Thus if 100,000 verification tests are conducted with impostors and another 100,000 verification tests are conducted with authentics, Biometric 1 would make a total of 2,000 errors, whereas Biometric 2 would make a total of only 200 errors. But what happens if thetwo biometrics are combined to make an "enhanced" test? If the "OR" Rule is followed in the same batch of tests, the combined biometric would make 1,099 False Accepts and 1 False Reject, for a total of 1,100 errors. If instead the "AND" Rule is followed, the combined biometric would make 1,099 False Rejects and 1 False Accept, thus again producing atotal of 1,100 errors. Either method of combining the two biometric tests produces 5.5 times more errors than if the stronger of the two tests hadbeen used alone. Conclusion: A strong biometric is better alone than in combination with aweaker one... when both are operating at their cross-over points. To reap any benefits from combination, the equations above show that the operating point of theweaker biometric must be shifted to satisfy the following criteria: If the"OR" Rule is to be used, the False Accept rate of the weaker test must be made smaller than twice the cross-over error rate of the stronger test. If the "AND" Rule is to be used, the False Reject rate of the weaker test mustbe made smaller than twice the cross-over error rate of the stronger test. The following is a position I took on layered biometrics in an email about ayear ago to the List. I do not think that the below disproves ProfessorDaugman's premise, but only points out that the premise from which I andothers have based their conclusions are different from that of Professor Daugman.The idea of layered biometrics has come about because of False Rejection. The layered biometrics issue may therefore be approached from another pointof view by not layering the biometrics but subjectively comparing the statistical results. At first, this may sound very non-scientific, butlet's first examine the problem of FR. Let us take for our examination two widely used biometric technologies forAccess Control: Hand Geometry and Face. In our example, both these system will be used for an access control system. The Hand Geometry reader will beour primary biometric system with the Facial Verification being our secondary system. Hand Geometry has a field proven EER of 0.2%. For our example, we will set the Hand Geometry reader's security at a threshold level of 60 which gives us a FAR of 0.08%. What we are saying in essence is that any person that verifies at or below the threshold level of 60 is who heclaims and anyone over the threshold level of 60 is an imposter and will notbe granted access. If a person verifies at 61, how much more of an imposteris he than the person that verified at a threshold level of 59 or 60? And if that same person verified at 69 or 75, is he more of an imposter than theperson that verified at a threshold level of 40? From the stand point ofthe set threshold level, anyone above 60 is an imposter and anyone at 60 or below is not an imposter. When we set a threshold level, there is a clear YES or a NO and no 'possible'. In the real world, we know that people may not always verify at the same level day in and day out. Should we reject a legitimate user because theuser failed by 0.05% and was verified at 61 instead of the minimum threshold level of 60? There may be a case for 'parallel biometrics'. In the case of parallel biometrics, we state that any person that does not meet the minimum threshold level will be verified by a second biometric technology. In this case, Facial Verification will be used. Let us assume that two persons, George and Giles were verified at the Hand Geometry reader and George received a verification level of 65 ( FA% 0.11%) and Giles received a verification level of 85 (FA 0.28%. George came pretty close toour required FA% of 0.08%, but could not be allowed access because he missed the threshold level by 0.03%. Close but no prize. Now, George and Giles are given a second chance to prove that they are who they claim. Both George and Giles look at the camera and receive the following verification levels: George is verified at a FA level of 7 % and Giles at 3 %. In the Facial, Giles came out better than George. If we hadbeen using Facial Verification alone and our access control threshold had been set for 98%, neither George nor Giles would have gained access. But now we are using Facial Verification in parallel with Hand Geometry. George did better than Giles with Hand Geometry but Giles did better than George with Facial. Do we deny both access because the did not meet the facial minimum requirements or should be combine both the Hand Geometry and Facial and divide by 2 or just toss a coin? Or should we ask an additional question: What is the probability of animposter achieving 99.89% accuracy for Hand Geometry and 93 % accuracy withFacial Verification based on George's two templates residing on the biometric database. In other words, what is the statistical possibility ofan imposter have facial characteristics that match the facial template onthe database by a similarity level of 97% and that the same imposter has hand geometry that matches that on the database by an accuracy level of 99.89%? Is not the possibility far less than 0.08%, which is our verification threshold on the Hand Geometry reader? What may be required in order to resolve the issues of falsely rejected legitimate users is an algorithm that is weighted in favor of the primary biometric technology and weighs the primary biometrics' rejection level against the secondary's evaluation of how accurately the rejected user matches the secondary biometric template in comparison to the level that he was rejected by the primary biometric technology. The levels of weighing each of the biometrics acceptance/rejection levels will be subjective and based on security requirements.

The following is an outline of Josef Kittle's paper at the Biometric Conference in Hong Kong. http://www.wave-report.com/other-html-files/currentwave.htm ****ICBA 2004, First International Conference on Biometric Authentication By John LattaHong Kong, July 15 - 17, 2004 Challenge of Biometric Fusion Josef Kittle, University of Surrey, UK, gave a keynote presentation on"Fusion of Intramodal and Multimodal Biometric Experts." It was one of themost interesting of the conference. One example in facial recognition wasbased on color channels. Three different methods related to the color channels netted TER, total error rates, of 5.8, 5.8 and 4.8. But when combined using a fusion process, the TER dropped to 1.9. This is anintramodal fusion because the same biometric modality was used, i.e., facial. Another example used face, voice and lips for the biometrics. In this case the HTER (1/2 TER) varied from .74 to 13.3. When it was fused andall modalities were used, the HTER dropped to .15. The last example was the fusion of face and voice with the HTER of 1.8 and 1.23. But the fused HTER was only .28. Logic draws us to the expectation that the use of more than one and even multiple biometric measures would result in lower error rates. Professor Kittle showed that the real challenge comes in operational environments. In these environments: Not all sensors are assumed to be able to collect their respective biometric for every individual in the authentication/identification process, The potential for fusion is limited to the number of biometrics used at the time of enrollment, and Some biometrics are of higher reliability that others. Operational expectations are that the use of biometrics will force the evaluation in the direction of the biometric with the highest confidence. Note that this is the case with Hong Kong Immigration which has both fingerprints and images. The images are not used as a biometric. In fusion, we would expect that the weights applied to the sensors used for authentication/ identification should be based on the reliability of the biometric. The WAVE asked the question: How does one compensate for these issues in operational environments? In response, it was stated this is oneof the issues to be addressed in the R&D of multimodal systems. The promise of fusion also carries with it the need for more research.What is of interest here is that in theory there is no improvement possibleby layering, combining or fusing two or more biometrics, yet in practice the test results indicate something else.

Yona Flink

OptiSec Ltd. Israel yona@optisec-systems.com

Mobile: +972 54 430 8727

11 comments:

job opportunitya said...

Astonshing blog. I relished in the site and you
know I will be going to it again! Surfing the internet
hepls me to find blogs that arfe just as good.
Once you sign on, check for my blog.

oakleyses said...

tory burch outlet, tiffany and co jewelry, coach outlet store online, polo ralph lauren outlet, chanel handbags, true religion outlet, ray ban outlet, red bottom shoes, burberry outlet online, prada outlet, kate spade outlet online, nike free, polo ralph lauren, christian louboutin shoes, nike air max, christian louboutin outlet, coach outlet, louis vuitton outlet online, burberry outlet online, true religion, nike shoes, longchamp handbags, coach purses, oakley sunglasses, ray ban sunglasses, oakley vault, tiffany jewelry, louis vuitton outlet, nike air max, prada handbags, coach outlet, michael kors outlet online, michael kors outlet online, gucci handbags, michael kors outlet, louis vuitton, longchamp outlet, jordan shoes, michael kors outlet store, kate spade handbags, louis vuitton handbags, cheap oakley sunglasses, michael kors outlet online, louis vuitton outlet, christian louboutin, longchamp outlet online, michael kors outlet online

oakleyses said...

louis vuitton outlet online, louis vuitton handbags, oakley sunglasses, burberry outlet online, prada outlet, coach purses, longchamp outlet online, michael kors outlet online, jordan shoes, nike outlet, louis vuitton outlet, tiffany and co jewelry, michael kors outlet store, coach outlet, chanel handbags, tiffany jewelry, nike free, longchamp handbags, christian louboutin, true religion, christian louboutin shoes, polo ralph lauren outlet, michael kors outlet online, louis vuitton outlet, michael kors outlet, longchamp outlet, burberry outlet online, louis vuitton, ray ban sunglasses, cheap oakley sunglasses, coach outlet, gucci handbags, coach outlet store online, christian louboutin outlet, tory burch outlet online, michael kors handbags, red bottom shoes, polo ralph lauren, kate spade outlet online, oakley vault, nike air max, ray ban outlet, michael kors outlet online, prada handbags, kate spade outlet, true religion outlet, nike air max

oakleyses said...

hollister, ralph lauren, air max pas cher, nike free pas cher, scarpe hogan, nike roshe run, converse pas cher, air jordan, nike air max, new balance pas cher, air max, louis vuitton pas cher, vans pas cher, nike roshe, louis vuitton, hollister, timberland, sac vanessa bruno, michael kors canada, longchamp pas cher, longchamp, abercrombie and fitch, north face pas cher, sac michael kors, chaussure louboutin, ralph lauren pas cher, true religion outlet, mulberry, ray ban uk, burberry pas cher, louis vuitton uk, north face, barbour, michael kors uk, lululemon, nike air max, nike blazer pas cher, sac louis vuitton, hermes pas cher, nike air force, lacoste pas cher, ray ban pas cher, guess pas cher, true religion jeans, oakley pas cher, tn pas cher, nike free

oakleyses said...

north face jackets, lululemon outlet, babyliss pro, vans outlet, birkin bag, insanity workout, giuseppe zanotti, asics shoes, mac cosmetics, abercrombie and fitch, canada goose outlet, ghd, nike roshe, uggs on sale, ugg boots, nike trainers, herve leger, soccer shoes, ugg soldes, replica watches, p90x workout, soccer jerseys, ferragamo shoes, beats headphones, uggs outlet, longchamp, valentino shoes, ugg outlet, marc jacobs outlet, jimmy choo shoes, ugg, instyler ionic styler, mcm handbags, mont blanc pens, new balance outlet, uggs outlet, chi flat iron, canada goose, ugg boots, reebok shoes, canada goose outlet, canada goose outlet, hollister, nike huarache, wedding dresses, bottega veneta, celine handbags, north face outlet, nfl jerseys

oakleyses said...

moncler, links of london uk, moncler, moncler outlet, juicy couture outlet, uggs canada, moncler outlet, supra shoes, canada goose pas cher, hollister canada, louboutin, hollister clothing, baseball bats, iphone 6 case, toms outlet, canada goose, swarovski uk, replica watches, wedding dress, juicy couture outlet, timberland shoes, converse shoes, parajumpers outlet, pandora jewelry, gucci, moncler, hollister, moncler, thomas sabo uk, swarovski jewelry, nike air max, pandora charms, vans, montre femme, oakley, pandora uk, louis vuitton canada, karen millen, converse, air max, ray ban, lancel, coach outlet, ralph lauren, canada goose, moncler, ugg, canada goose

oakleyses said...

louis vuitton, nike outlet, nike free run, nike air max, polo outlet, longchamp outlet, nike free, replica watches, nike roshe, ray ban sunglasses, oakley sunglasses, ray ban sunglasses, louis vuitton outlet, uggs on sale, louis vuitton outlet, longchamp outlet, prada outlet, ray ban sunglasses, tory burch outlet, ugg boots, tiffany jewelry, sac longchamp pas cher, christian louboutin, tiffany and co, louis vuitton, replica watches, louis vuitton outlet, oakley sunglasses, christian louboutin uk, polo ralph lauren outlet online, ugg boots, michael kors pas cher, louboutin pas cher, polo ralph lauren, longchamp pas cher, burberry pas cher, jordan shoes, gucci handbags, nike air max, air max, longchamp outlet, jordan pas cher, prada handbags, oakley sunglasses wholesale, kate spade outlet, christian louboutin outlet, christian louboutin shoes, oakley sunglasses, cheap oakley sunglasses

oakleyses said...

michael kors outlet online, michael kors outlet, replica handbags, nike tn, nike free uk, coach purses, burberry outlet, michael kors, polo lacoste, nike blazer pas cher, nike air max, hollister pas cher, ray ban uk, guess pas cher, michael kors, true religion outlet, hogan outlet, michael kors outlet online, nike air max uk, uggs outlet, michael kors outlet, new balance, michael kors outlet online, uggs outlet, mulberry uk, nike air force, abercrombie and fitch uk, lululemon canada, north face uk, ray ban pas cher, burberry handbags, michael kors outlet online, kate spade, true religion outlet, ralph lauren uk, sac hermes, nike air max uk, vans pas cher, converse pas cher, hollister uk, nike roshe run uk, true religion jeans, north face, michael kors outlet, sac vanessa bruno, true religion outlet, oakley pas cher

oakleyses said...

new balance shoes, chi flat iron, nike trainers uk, vans outlet, ghd hair, ipad cases, iphone cases, mont blanc pens, bottega veneta, ferragamo shoes, mac cosmetics, herve leger, timberland boots, s6 case, wedding dresses, nike air max, iphone 6 cases, ralph lauren, soccer jerseys, valentino shoes, oakley, longchamp uk, baseball bats, soccer shoes, nike roshe run, babyliss, beats by dre, north face outlet, iphone 6s cases, nike huaraches, north face outlet, hermes belt, iphone 6s plus cases, celine handbags, lululemon, hollister clothing, mcm handbags, asics running shoes, nfl jerseys, abercrombie and fitch, insanity workout, jimmy choo outlet, iphone 5s cases, iphone 6 plus cases, hollister, instyler, giuseppe zanotti outlet, p90x workout, reebok outlet, louboutin

oakleyses said...

juicy couture outlet, juicy couture outlet, ugg, pandora jewelry, moncler, replica watches, moncler outlet, pandora uk, ugg,uggs,uggs canada, gucci, canada goose uk, swarovski crystal, converse, marc jacobs, canada goose outlet, moncler, supra shoes, ugg pas cher, hollister, swarovski, thomas sabo, pandora jewelry, moncler outlet, louis vuitton, moncler uk, louis vuitton, canada goose outlet, canada goose jackets, canada goose, canada goose, links of london, toms shoes, montre pas cher, pandora charms, doudoune moncler, moncler, barbour uk, louis vuitton, ugg uk, karen millen uk, moncler, ray ban, coach outlet, barbour, lancel, louis vuitton, hollister, louis vuitton, canada goose outlet, ugg,ugg australia,ugg italia, wedding dresses, nike air max

Xiaozhengm 520 said...

2016-4-18 xiaozhengm
louis vuitton outlet online
ralph lauren outlet
longchamp bags
coach outlet
pandora jewelry
coach outlet
celine bags
nike air max
louis vuitton outlet stores
kate spade
longchamp outlet
jordan shoes
oakley sunglasses
gucci outlet
true religion
nike uk
louis vuitton outlet
louboutin pas cher
oakley outlet
jordan shoes
coach outlet online
michael kors outlet
oakley sunglasses
ray ban sunglasses
true religion outlet
toms outlet
tory burch outlet
michael kors outlet
air jordan retro
nike air max
coach factorty outlet
coach outlet
coach factorty outlet
timberland boots
toms
instyler curling iron
louis vuitton handbags
adidas originals
louis vuitton outlet
ralph lauren outlet