Blog: Computers Can See You--If You Have a Mug Shot; aulity of facial recognition systems

Computers Can See You--If You Have a Mug Shot
Wall Street Journal (09/03/11) Carl Bialik

Carnegie Mellon University (CMU) researchers recently presented data suggesting that facial recognition tools could identify individuals based on posed mug shots. The researchers demonstrated that, in principle, 33 percent of people photographed could be matched with a database of photos taken from Facebook. As part of the study, the researchers used images of 93 volunteers and compared them to Facebook photos of people on the CMU network. The results mean no one using facial-recognition software can claim "I can recognize any person in the U.S. at this very moment," says CMU's Ralph Gross. The problem is taking one image and comparing it to a wide set of images to find a single correct match. Comparing photos of just one person is easier and has achieved much more success. In a recent U.S. National Institute of Standards and Technology test, facial recognition software misidentified individuals in photographs just one percent of the time. Compared to Facebook images, closed-circuit (CC) TV images will probably be even more difficult to use with facial recognition systems, according to computer-vision experts. "Identifying faces in CCTV-quality images requires human experts," says University of Cambridge professor John Daugman.

View Full Article

Blog: How Rare Is that Fingerprint? Computational Forensics Provides the First Clues

How Rare Is that Fingerprint? Computational Forensics Provides the First Clues
UB News Services (12/07/10) Ellen Goldbaum

University at Buffalo researchers have developed a method to computationally determine how rare a particular fingerprint is and how likely it is to belong to a specific crime suspect. The Buffalo researchers created a probabilistic method to determine if a fingerprint would randomly match another in a database. The researchers say their study could help develop computational systems that quickly and objectively show how important fingerprints are to solving crimes. "Our research provides the first systematic approach for computing the rarity of fingerprints in a scientifically robust and reliable manner," says Buffalo professor Sargur N. Srihari. Determining the similarity between two sets of fingerprints and the rarity of a specific configuration of ridge patterns are the two main types of problems involved in fingerprint analysis, Srihari says. The Buffalo method relies on machine learning, statistics, and probability.

View Full Article

Blog: Automated Biometric Recognition Technologies 'Inherently Fallible,' Better Science Base Needed

Automated Biometric Recognition Technologies 'Inherently Fallible,' Better Science Base Needed
National Academy of Sciences (09/24/10) Molly Galvin ; Christopher White

A National Research Council (NRC) study found that biometric systems designed to automatically recognize individuals based on biological and behavioral traits are inherently fallible, and no single trait was found to be stable and distinctive across all groups. "For nearly 50 years, the promise of biometrics has outpaced the application of the technology," says Hewlett-Packard technologist Joseph N. Pato. "While some biometric systems can be effective for specific tasks, they are not nearly as infallible as their depiction in popular culture might suggest." Biometric systems provide "probabilistic results," meaning that confidence in results must be tempered by an understanding of the inherent uncertainty in any given system, according to the NRC report. The report identifies several features a biometric system should have, including the ability to anticipate and plan for errors, and calls for additional research to strengthen biometric science and improve its effectiveness.

View Full Article

Blog: Fingerprints and Faces Can Be Faked, But Not Brain Patterns

Fingerprints and Faces Can Be Faked, But Not Brain Patterns
ICT Results (02/05/09)

The European Union-funded HUMABIO project is combining new types of biometric recognition systems with the latest sensor technologies to develop better security applications. HUMABIO researchers have developed sensorial and connectivity hardware for specific biometric applications, as well as new software to extract the biometric profile of individuals, which is based on physiology and behavior characteristics. HUMABIO's biometrics include using electrocardiograms to record heart rhythms and electroencephalograms to record brain patterns. The project has developed a prototype headgear system that uses two electrodes to take both readings. The technology is still in the proof-of-concept stage, but project coordinator Dimitrios Tzovaras says the researchers are very pleased with the results so far. "This is the first time this type of biometrics has been used for identification, and it solves most of the problems other biometric systems face," Tzovaras says. The project has been working on other types of biometrics that are much closer to commercialization, including gait or walking analysis, and analyzing a person's seated posture. The project also has been working on improving facial- and voice-recognition systems, and combining multiple biometric techniques into a multimodal biometric identification system that is more secure than individual biometric techniques.

View Full Article

Blog: Why Veins Could Replace Fingerprints and Retinas as Most Secure Form of ID

Why Veins Could Replace Fingerprints and Retinas as Most Secure Form of ID
Times Online (UK) (11/11/08) Harvey, Mike

Finger vein authentication is starting to gain traction in Europe. Easydentic Group in France says it will use finger vein security for door access systems in the United Kingdom and other European markets. The advanced biometric system, which verifies identities based on the unique patterns of veins inside the finger, has been widely introduced by Japanese banks in thousands of cash machines over the last two years. Hitachi developed the technology, which captures the pattern of blood vessels by transmitting near-infrared light at different angles through the finger, and then turns it into a digital code to match it against preregistered profiles. Veins are difficult to forge and impossible to manipulate because they are inside the body, according to Hitachi. The company also says finger vein technology is more affordable than iris scanning or face/voice recognition and has a lower false rejection rate than fingerprinting. Finger vein authentication is primarily used in Japan for ATMs, door access systems, and computer log-in systems.

View Full Article

Security: National Institute of Standards and Technology Shows On-Card Fingerprint Match Is Secure, Speedy; getting better, but ...

National Institute of Standards and Technology Shows On-Card Fingerprint Match Is Secure, Speedy
NIST Tech Beat (04/01/08) Brown, Evelyn

Researchers at the National Institute of Standards and Technology say a new fingerprint identification technology for use in personal identification verification (PIV) cards is both fast and secure. As part of the authentication process for the technology, the cardholder enters a personal identification number to authorize the reading of fingerprint data from the card, and a card reader matches the stored data against the newly scanned image of the cardholder's fingerprints. In one model, biometric data on the card would travel across a secure wireless interface, which would eliminate the need to insert the card into a reader. In a second model, biometric data from the fingerprint scanner would be sent to the PIV smart card for matching by a processor chip embedded in the card, and the stored data would never leave the card. "If your card is lost and then found in the street, your fingerprint template cannot be copied," says computer scientist Patrick Grother. Ten cards with a standard 128-byte-long key and seven cards that use a more secure 256-byte key passed the security and timing test using wireless, but only one of three teams met NIST's criteria for accuracy. A new round of tests on the technology, which offers an improvement in protection against identity theft, will begin shortly.
Click Here to View Full Article