Biometrics: Past, Present And Future

Biometrics:Past, Present and FutureAnil K. JainMichigan State Universityhttp://biometrics.cse.msu.edu/January 25, 2021IAPR/IEEE Winter School on Biometrics

Outline Introduction What is Biometrics? Why Biometrics? Past Present Future

Biometric Recognition “Automated recognition of individuals based on their behavioraland biological characteristics” ISO/IEC JTC1 2382-37:2012 Bios: life; Metron: measure (Morris,1875)33

Why Biometrics?3.14159What you are? Unique Stable NaturalWhat you know?What you have? Lost Stolen Forgot CrackedAccess Method4

Biometrics is Application pting-automotive-biometrics

Past

Habitual Criminal Act(1855)“What is wanted is a means of classifyingthe records of habitual criminal, such thatas soon as the particulars of thepersonality of any prisoner (whetherdescription, measurements, marks, orphotographs) are received, it may bepossible to ascertain readily, and withcertainty, whether his case is in theregister, and if so, who he is”7

Scotland Yard(1905)8

FBI (1924)1924: US Congress authorizes DOJ to collect fingerprints and arrest information9

Michigan Forensics BureauAFIS (1989); 15K comparisons/sec; no latent search1960Courtesy: James Blanchard, Michigan State Police10

Identimate (1972)First commercial use of biometrics11

Present

9/11 Attacks (2001)13

US-VISIT (2003)14

Walt Disney Theme Park (2005)15

Aadhaar (2008)1568 3647 4958Basic demographic data and biometricsstored centrallyNameParentsGenderDoBPoBAddressUID 1568 3647 495810 fingerprints, 2 irises & face imageCentral UID database“To empower residents of India with a unique identity and a digital platform to authenticate anytime, anywhere.”https://uidai.gov.in/

Authentication (ongoing)https://uidai.gov.in/aadhaar dashboard/auth trend.phpTwo-factor authentication: 40 M authentications/day17

Apple Touch ID (2013)Tactile SwitchCapacitive Single-Touch SensorStainless Steel Detection RingLaser-Cut Sapphire Crystal

Apple Face ID (2017)19

In-display Fingerprint Sensor (2018)20

Entry/Exit system at Airports (2019)Exit (leaving the country)Entry (arriving from ts-facial-recognition/index.html (8th October 2019)21

Amazon Go tter-of-if-but-when/#67d1a28d6f5222

Authentication AccuracySame Person?Fingerprint: TAR 99.96% @ FAR 0.01% (FVC-ongoing)Iris: TAR 99.82% @ FAR 0.01% (NIST IREX II)Face: TAR 99.7% @ FAR 0.1% (NIST FRVT 2010)23

Identification AccuracyMATCHProbeGallery Face: FNIR 0.058 @ FPIR 0.001 (12M gallery) Fingerprint: (Ten fingers): FNIR 0.001 @ FPIR 0.001 (5M gallery);Single finger: FNIR 0.019 @ FPIR 0.001 (100K gallery) Iris: (Both eyes): FNIR 0.0059 @ FPIR 0.001 (500K gallery)[1] NIST FRVT 1:N Identification: https://pages.nist.gov/frvt/html/frvt1N.html[2] NIST FpVTE: 8034.pdf[3] NIST IREX 10 Identification Track: https://pages.nist.gov/IREX10/24

Future

Spoofs (Minority Report, 2002)26

Targeted Advertisement (Minority Report, 2002)27

Biometrics at Scale28

Network of CCTV CamerasTitle Scene, Person Of Interest, CBS (2011-16); An ex-assassin and a wealthy programmer savelives via a surveillance AI that sends them the identities of civilians involved in impending crimes.29

l.html

WANTEDFor storming the US Capitol on Jan 6, 2021

Recognition with Noisy & Incomplete DataRankFace ImageMatch1Non-Match2Aerial ImageryWatchlist Soft Biometrics(e.g., gait, shirt color, etc.)Imaged TargetSurveillance tion com content&view article&id ltitude-and-range-briar&catid 296

Privacy33

Take Home Message Biometric ensures a person is who he claims to be and not whohe denies to be Drivers: Applications (Security, fraud, civil-ID, payment, ) Enablers: Matching algorithm, processor, memory & sensor(fingerprint reader/matcher embedded in a mobile costs 1) Challenge: Recognize anyone, anywhere, anytime in real time34

Biometric Recognition “Automated recognition of individuals based on their behavioral and biological characteristics” ISO/IEC