Facial recall

Closed circuit television is a very useful and important tool for anyone seeking to improve security. Its very presence can be a powerful deterrent to potential criminals, even when there are no cameras inside the boxes. With good cameras installed correctly, the images they provide can prove invaluable in identifying the perpetrators of crime.

The major drawback of CCTV, however, is that it is all rather reactive. When a crime has been committed, it can be a long and painstakingly arduous job for operators to wade through hours of footage from multiple cameras in an effort to try to ascertain if the crime itself, or any of the culprits, were captured. This is an all-too-familiar scenario for operators, regardless of whether the system uses digital recording or analogue.

The benefit of using facial recognition technology is that it allows CCTV systems to be proactive. Systems fitted with this technology can alert operators when faces matching those on a database of known offenders appear on the scene. For example, shopping centre security managers could be alerted when known shoplifters enter into any part of a retail centre. This then allows them to focus their security resources on these known individuals and keep an eye on them in anticipation of catching them in the act.

The advantage here is that the security resources are already watching the most likely offenders, rather than looking at recorded footage after the fact. If a crime is committed, they are able to confirm instantaneously that the crime was carried out by a known shoplifter. Fundamentally, facial recognition built into a CCTV system brings with it a wealth of information. The system not only records images, but also identifies the perpetrator. The faces of the people present are there for all to see, as well as for the system to match against its database.

Ultimately, however, the strength of the system lies in the information within the database – you can only identify people who are in that database. That means that the majority of people scanned by the system will not be found within the database, and their faces will then be forgotten by the system. Only those with a match against those held within the database will be brought to the operator's attention.

Backwards scanning
Of course, not all crimes are committed by known individuals. A facial-recognition enabled CCTV system can greatly assist in the retroactive scanning of recorded information as well. Once a new offender's face can be shown to the system, not only should it be able to alert operators when that individual is seen again, it can also search through its archives to see if that person was seen in the past, and could perhaps be linked to other crimes or incidents, allowing a more complete pattern of behaviour to be established.

‘Poor specification, installation, training and system use can completely remove the intended advantages of the system’

Many of you will have heard something of facial recognition already, probably that it doesn't work, or at least, not very well. Some of the first system implementations were certainly very ambitious, perhaps overly so, and have suffered because of this. However there are lessons that have been learned from these systems that can be brought to bear on new installations. Mostly, these revolve around the best way to implement and install these systems.

There have also been many innovations around the algorithms that these systems use. One of the most exciting and promising of these is the use of three-dimensional facial recognition, as opposed to the more common format of current two-dimensional systems. Obviously, the added dimension inherent within 3D systems offers better accuracy and greater flexibility.

Learning curve
They also overcome some of the problems associated with 2D systems, such as reliance on constant ambient illumination. As a result, 3D systems are seen by many as the obvious future path for facial recognition systems as a whole, and the current take-up of this technology is very good. However, facial recognition technology, in common with other biometric systems, is not simple to install or use. Poor specification, installation, training and system use can completely remove the intended advantages of the system, and the same can be said of any other modern, complex security technology.

Installers should discuss the intended use and environment in detail with the system manufacturers to confirm that the system is fit-for-purpose. If the equipment has been specified and installed to give optimum use in any given location, and system operatives receive professional training, it should then lead to professional use of the system. Existing case studies where all of this has occurred show many good applications of the technology, with users benefiting from early adoption.