With news nowadays referring to a war on terrorism and threatening protagonists living hidden around us, the theme of surveillance and public identification is often in the spotlight. Governments are seeing the growth of fear, due to recent terrorist attacks in Europe, as a good reason to intensify surveillance systems. Many people, though are concerned about their privacy, which would be furtherly violated by such decisions. Some extreme cases are even alluding to a conspiracy drawn up by western governments in order to intensify their control over population. Either case, in favour or against, facial recognition, the most effective biometric* authentication system of mass identification is surely a subject of large interest.

*other biometrics information are fingerprints, iris recognition, speech recognition,veins recognition, palm print, retina, DNA, hand geometry and odour/scent.


Facial recognition experts used James Foley’s killer’s eyes to guess what he looks like under the mask.


The history of facial recognition is relatively recent.

1964 – Bledsoe, Chan Wolf, and Bisson

Created the first semi-automated system for face recognition which required an administrator to locate features on photographs before it calculated distances and ratios to a common reference point, which were then compared to reference data.

Woody Bledsoe, His Life and Legacy by Michael Ballantyne, Robert S. Boyer, and Larry Hines. AI Magazine Volume 17 Number 1 (1996) (© AAAI)

1970 – Goldstein, Harmon and Lesk

Used 21 specific subjective markers such as hair colour and lip thickness to automate subjects recognition. However, in this technique as in the previous one the measurements and locations were manually computed.

1988 – Kirby and Sirovich 

Applied principle component analysis, a standard linear technique. This was considered somewhat of a milestone as it showed that less than one hundred values were required to accurately code a suitably aligned and normalized face image.

1991 – Turk and Pentland

Discovered that while using the eingenfaces techniques, the residual error could be used to detect faces in images. This discovery enabled reliable real-time automated face recognition systems.

1996 – Christoph von der Malsburg and graduate students of the University of Bochum in Germany and the University of Southern California

Introduced a system for recognizing human faces from single images out of a large database containing one image per person. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small get of sample image graphs.

Face recognition by Elastic Bunch Graph Matching, Wiskott, Fellous, Kruger, and von der Malsburg, In Intelligent Biometric Techniques in Fingerprint and Face Recognition, Chapter 11, pp. 355-396, (1999).

The funding was from the United States Army Research Laboratory.
The software was sold as ZN-Face and used by customers such as Deutsche Bank and operators of airports and other busy locations.

2001 – Super Bowl 

The technology first captured the public’s attention from the media reaction to a trial implementation at the Super Bowl, which captured surveillance images and compared them to a database of digital mugshots.

2002 – Face recognition in CCTV in Newham, London

In Newham they placed 2.5 million CCTV cameras for facial recognition, they estimated to reduce the crime of the 34%. However, with big disappointment t
he system in Newham actually never work, like other examples in Tampa, Florida and at the Boston’s Logan Airport. No one has been catch with this system during that year. However, probably the fact that people is aware to be observed by these technologies is a deterrent by itself and it can reduce the crime rate anyway.

Here is an interesting article in regard from The Guardian: Robo Cop.

2006 – Face Recognition Grand Challenge (FRGC) 

The results indicated that the new algorithms are 10 times more accurate than the face recognition algorithms of 2002 and 100 times more accurate than those of 1995. 

2007 – Facelt by Identix 

It can pick out someone’s face in a crowd and compare it to databases worldwide to recognize and put a name to a face.

2007 – Polar Rose technology 

It can guess from a photograph, in about 1.5 seconds, what any individual may look like in three dimensions, and claimed they “will ask users to input the names of people they recognize in photos online” to help build a database.

2009 – Face First 

Airborne Biometrics Group, Inc introduced this Infinitely Scalable Face Recognition Platform, they are currently leaders in facial recognition technology.

“We recognized the lack of integrated service offerings in the world of facial recognition and so we built our platform with the goal of giving the public access to complex technology at a commodity price.”

Joseph Rosenkrantz, CEO and founder of Airborne Biometrics Group, Inc.


Veri Look SDK – VeriLook algorithm implements advanced face localization, enrollment and matching using robust digital image processing algorithms with the same high recognition quality on PCs, embedded and mobile devices.

digiKam – KDE

iPhoto – Apple

OpenCV – Open Source

Photoshop Elements – Adobe Systems

Picasa – Google

Picture Motion Browser  – Sony

Windows Live Photo Gallery – Microsoft


Besides surveillance, which is the most obvious use for this technology, some of the potential uses already in consideration are for ATMs, which would recognise the face without need of password and for mobile devices to unlock them, as it’s currently happening with fingerprints.

However, facial recognition is a mighty technology as it doesn’t require the physical presence of the person and because current technological progress made it very quick and easy to scan people faces. Therefore, the above uses would be very limited and irrelevant, facial recognition could be used for way bigger things. It might be use is communication for example.

Or what if we make these machines recognise emotions and not only faces (behaviometrics is a technology which is already able to detect behaviours and identify people in these way).
What if an environment can literally recognise a person and be adapted for it? How cool would it be to enter at work and your favourite song starts (like the intro song for wrester) or you favourite scent is sprayed in the air?
Obviously the shadow of marketing is quite scaring in this, they could start bombarding people with customised advertising. Although, that’s surely a consequence to keep under consideration, on the other hand if always scared of marketing outcomes, technological progress wouldn’t have moved anywhere.

Here is a discussion about possible futures for facial recognition and surveillance technologies in general:



– Facial recognition technology: How well does it work? – By Kevin Rawlinson, BBC News

– Is YOUR photo already on the FBI’s new facial recognition database? – By Mark Prigg, Daily Mail


– Facial Recognition Technology: An analysis with scope in India, Dr.S.B.Thorat, S.K.Nayak, Miss.Jyoti P Dandale, (IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 1, 2010

– Our Biometric Future: Facial Recognition Technology and the Culture of Surveillance (Critical Cultural Communication) – Kelly A. Gates

– An Image Preprocessing Algorithm for Illumination Invariant Face Recognition

– Ralph Gross and Vladimir Brajovic, The Robotic Instite, H. John Heinz III College, Carnegie Mellon University, Pittsburgh, PA

– Quo vadis Face Recognition? – Ralph Gross, Jianbo Shi Robotics Institute Carnegie Mellon University Pittsburgh, PA 15213 – Jeffrey F. Cohn Department of Psychology University of Pittsburgh Pittsburgh



– The White House, Office of Science and Technology Policy

Neuro Technology, Biometric and Artificial Intelligence Technologies

Face recognition using eigenfacesTurk, M.A. ; Media Lab., MIT, Cambridge, MA, USA ; Pentland, A.P.


Face Recognition – FBI.gov – National Science and Technology Council (NSTC), Committee on Technology, Committee on Homeland and National Security, Subcommittee on Biometrics

Wikipedia.org – Facial recognition system

Mind Map - Facial Recognition