Researchers at the University of Bradford have found that facial recognition technology can achieve 100 percent recognition even with just half a face visible.
The study has been published in Future Generation Computer Systems and is the first to use machine learning to test how accurate facial recognition technology is for different parts of the face. The team achieved 100 percent recognition rates for just three-quarter and half faces.
The power of artificial intelligence for facial recognition
To analyse the technology, the team used a machine learning technique called a convolutional neural network. It draws on a feature extraction model called VGG, which is currently one of the most widely used models for facial recognition.
The lead researcher, Professor Hassan Ugail from the University of Bradford, commented: “The ability humans have to recognise faces is amazing, but research has shown it starts to falter when we can only see parts of a face. Computers can already perform better than humans in recognising one face from a large number, so we wanted to see if they would be better at partial facial recognition as well.”
Individual facial parts including the nose, cheek, forehead or mouth had low recognition rates in the experiments.
What will facial recognition data be used for in the future?
Professor Hassan explained:”We’ve now shown that it’s possible to have very accurate facial recognition from images that only show part of a face and we’ve identified which parts are most useful. This opens up greater possibilities for the use of the technology for security or crime prevention.”
Hassan noted: “Our experiments now need validating on a much larger dataset. However, in the future it’s likely that image databases used for facial recognition will need to include partial images as well, so that the models can be trained correctly to recognise a face even when not all of it is visible.”