A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. Digital images, such as those taken by a digital camera or a phone, represent a physical image such as a person’s face in a format that can be processed using computer technologies. Image recognition is the technology that recognises objects in photographs.. Facial recognition is achieved by comparing selected facial features from the image and a facial database
Hundreds of research teams around the world, have been working on these technologies for years. An example of one of these systems commercially available systems is called ‘mflow’ which has been developed to track people through an airport. In the product description they developers detail how the process includes automatic facial detection, without knowledge of the passenger. The facial image is analysed and the major features are mapped. With this information the passengers route through the airport is traced providing information to the airline on how long it takes this person to get to the departure gate. It also allows for identification of VIPs and for upselling products to relevant customers.
So how does it work, A digital image is made up of pixels and every image can be represented as two-dimensional array, where every element of that array contains colour information for one pixel. The computer system then identifies pixels in the area of specific facial features and then compares this against a database of images.
Identifying and recognising objects in images can then be developed to identify the same object over a series of images which then presents the ability to track an object. This in turn provides the ability to track people in video footage.
This system has been in use insecurity systems for a number of years, tracked moving objects trigger an alert at the security company, initiating investigation.
Although very useful, it raises concerns about privacy. Can a private company hold details of our personal images and trace them without our consent. All of these are issues to be viewed in the context of the GDPR regulation in Europe
Dykegate Lane, Dingle, Co. Kerry, Ireland V92 VX86
tel: 00353 669152222
Email: info@compucara.ie