
Cutting-edge body recognition software which identifies people based on their physical shape and even clothes is set to be rolled out next year.
Everyday facial recognition technology has been refined to the extent that cameras can match an image in a database to someone’s height, width, hair and apparel.
This will allow an individual to be identified even if their face is obscured – by a balaclava, for example.
Or they will still be able to be spotted if part of their body is hidden by another person or an object.
Technology titan NEC Global is pioneering the body recognition software and hopes to apply it to busy security-controlled sites such as sports stadiums and airports.
If someone was photographed walking through a football ground’s security barrier, for example, this person would be able to be identified by cameras around the stadium even if their face were concealed.
The Tokyo-based inventor also suggested the body recognition system could help in situations like tracking down lost children in crowded places.
The Japanese firm, which boasts a 90 per cent match-rate with the software, said: ‘This technology analyses the entire appearance of a person’s photo image, such as their clothes and body shape, to determine whether they match with other images of people.
‘Using the image analysis and deep learning technologies that NEC has cultivated through facial recognition technology and other technologies, NEC was able to establish this high-precision technology that does not rely solely on facial images. ‘
Body recognition software forms part of the Tokyo-headquartered inventor’s Safer Cities initiative which aims to deploy technology to combat violent crime and terrorism.