Your browser is no longer supported. For the best experience of this website, please upgrade to a newer version or another browser.

Your browser appears to have cookies disabled. For the best experience of this website, please enable cookies in your browser

We'll assume we have your consent to use cookies, for example so you won't need to log in each time you visit our site.
Learn more

Similarity breeds content

New software could revolutionise how shoppers search for clothes by recognising outfits in images.

This autumn sees the launch of new technology that will enable consumers to search for products similar to those they see when browsing in shops, in magazines, or even when walking down the street.

Called FindSimilar, the technology can be integrated into a retailer’s website or mobile app.

For example, if a retailer offers the app, its customers can take a photo of a product they like, such as a top or skirt, in a competitor’s store and then see if the retailer offering the app stocks similar items. And it doesn’t just have to be in a store - the technology will work if customers take pictures of friends whose outfits they like, people in the street or even catwalk models.

The technology was developed by software developer Cortexica. It works by mimicking the process between
the human eye and the brain to spot similarities between products.

It gives consumers the ability to constantly compare products and find inspiration. Iain McCready, chief executive of Cortexica, says: “It’s a bit like putting your own shop assistant into a competitor’s store. We all recognise that feeling of frustration after hunting for an item of clothing we’ve seen or admired, or the experience of finding something and wishing we could find a better or more affordable alternative. Our software is the answer to these problems.”

The company explains the software in technical terms: “Cortexica’s team of neuroscientists, visual search scientists and machine learning engineers have replicated the way the eye and neurons interact when recognising and interpreting an image.

“Cortexica uses what is called ‘parallel probabilistic computation’, which enables its software to learn over time, mimicking the calculations made by biological neurons in the visual cortex of the human brain.”

Because the technology takes into account colours, styles and patterns, the photos taken do not have to be of an item of clothing. Users could take a picture of a pattern, wallpaper or colour they like and then use FindSimilar to locate products with a similar style.

FindSimilar is being tested by a number of UK fashion retailers but is not due to go live until the autumn.

However, this type of technology is sure to give consumers an entirely new way of filtering and personalising product, making them much more likely to go on to buy.

Have your say

You must sign in to make a comment

Please remember that the submission of any material is governed by our Terms and Conditions and by submitting material you confirm your agreement to these Terms and Conditions. Links may be included in your comments but HTML is not permitted.