Post on 18-Jun-2015
Facial Recognition
VSB2006 11:30
Rob Eisenlord Michael Waterfield
Jessica McCarthy Connor Rustemeyer
Subject Recognized: Connor Rustemeyer
History● 1960’s- First system required somebody to locate features on photographs
and calculate distances and ratios to compare to reference data● 1970’s- 21 specific subjective markers such as hair color and lip thickness
were used to automate the recognition ● 1988- Applied principal component analysis, a standard linear algebra
technique, so measurements didn’t have to be manually computed● 1991- Discovered that residual error could be used to detect faces in
images, a discovery that enabled reliable real-time automated facial recognition systems
● 2001- Facial recognition caught media and public’s eye during 2001 Super Bowl
● Major Players include: NEC Corporation, FaceFirst, Anviz Global Inc, and Smartmatic
How It Works● Images input through a digital video
camera● System analyzes characteristics of a
persons face ● Measures the overall facial structure,
including distances between eyes, nose, mouth, and jaw edges
● Measurements then retained in a database and then used as a comparison
● Each human face has approximately 80 nodal points that are detected
Examples of Nodal Points
https://www.youtube.com/watch?v=XOix5rt-Ioo
Crime Prevention • 2001 Super Bowl XXXV
• Tampa, FL Police Force supplied with free software• Identified a handful of criminals, but no arrests were made• 70,000+ fans scanned without
consent
• Places where this technology could be helpful:
• Airports• Casinos• Retail Stores• Office Buildings
Discussion QuestionWho would be against an
implementation of facial recognition security measures? Is this system unfair?
Facebook Facial Recognition● FaceDeep as accurate as the
human brain● 97.25% accuracy (humans
roughly 97.53%)● 9 layers of “neurons” able to
make 120 million connections in their database
● Better at identifying faces that FBI’s NGI (Next Generation Identification)
Google Glass (NameTag App)● This app allows access to
wide variety of information simply by looking at someone
● A person’s name, photos, and dating website profiles
● Takes pictures and analyzes pictures in a matter of seconds
Discussion QuestionWould you use this technology? If yes,
how would you use it? If no, does this possibility make you uncomfortable?
Do you think any of your current relationships would be different had you had this technology?
Customer Service• Retail
• Shoplifters• VIP Customers
• Hotel and Hospitality
Most high-profile customers are "quite happy to have their information available because
they want a quicker service, a better-tailored service, or a more personally tailored service“
(New York Times).
Discussion QuestionWould you sign consent
for facial recognition use in retail and hotel/hospitality? If not, what would need to change?
Do the pro’s outweigh the con’s?
Legislation• There are currently no U.S. laws limiting government
agencies or private companies from using facial recognition
• National Telecommunications and Information Administration
• Similar to DNA sequencing• Right to control access to and use of biometric data
• Balance between privacy and law enforcement
“Commercial facial recognition technology has the potential to provide important benefits and to support a new wave of technological innovation,” says John Verdi, the agency’s director of privacy initiatives, “but it also poses consumer privacy challenges.”
Works Citedhttp://www.nytimes.com/2014/02/02/technology/when-no-one-is-just-a-face-in-the-crowd.html?_
r=0
http://www.ex-sight.com/technology.htm
http://www.fbi.gov/about-us/cjis/fingerprints_biometrics/biometric-center-of-excellence/modalities/facial-recognition
http://travel.usatoday.com/hotels/post/2010/10/houston-hilton-hotel-installs-facial-recognition-technology/125937/1
http://www.pcworld.com/article/259470/regulation_of_facial_recognition_may_be_needed_us_senator_says.html
http://www.theguardian.com/technology/2014/may/04/facial-recognition-technology-identity-tesco-ethical-issues