A revolutionary “virtual tape measure” – known as Body Shape Recognition For Online Fashion – promises to make badly fitting clothes (and even badly lit fitting rooms) a thing of the past, advising the user on which size dress, trouser or top they should buy in every retailer.

The web-based body-scanner would take detailed measurements of the body via webcam or smartphone, create a 3D image of the user, then advise on which size garment to buy whenever they visit the website of a participating retailer.

Taking multiple measurements of the body, the system aims to ensure the best possible fit, saving shoppers and retailers millions of pounds a year in return postage costs, as well as eliminating the need to send back clothes that are the wrong size or fit.

Currently, between 30 and 60% of all clothes bought online are returned to the shop.

Body scanning is already starting to make a mark in the clothing retail sector, but these often involve the user stepping into a machine that “photocopies” the body.

Body Shape Recognition For Online Fashion promises to make badly fitting clothes a thing of the past

The new software – being developed by London College of Fashion and computer vision experts at the University of Surrey – requires only a photo of the user in their underwear, their height, and an internet connection.

Philip Delamore from London College of Fashion said: “The potential benefits for the fashion industry and for shoppers are huge.

“Currently, it’s common for online shoppers to order two or three different sizes of the same item of clothing at the same time, as they’re unsure which one will fit best.”

Professor Adrian Hilton from the University of Surrey says: “It’s unrealistic to expect online clothes shoppers to have the time or inclination to take a series of highly accurate body measurements of themselves. The new system makes it all very easy.”

The 18-month project Body Shape Recognition for Online Fashion is being developed in collaboration with body-mapping specialists Bodymetrics and digital creative agency Guided.

The research builds on previous work by the University of Surrey in developing 3D body-shape templates from single-view images, which has been used commercially in creating animated representations of people for games such as The Sims.

Plans to launch the new system are anticipated within two years.