In a bid to enhance the user experience on its portal and bridge the gap between online and offline shopping, Snapdeal will launch image search feature called SnapSearch. SnapSearch will allow users to click a picture of something they like, upload it on the website and then browse through similar products available on the platform.
As per Anand Chandrasekaran, chief product officer at Snapdeal, the feature will go live on the website over the next couple of days and will work across several categories.
Adds Anand, “We are launching it first for watches, women fashion, some categories of men’s fashion etc, and will be expanding it to other categories in the near future.”
In August, the company had launched a similar feature called Find My Style, which uses intelligent technology solutions and smart algorithms to pre-empt customer needs. Using this feature, customers can describe the product they want to buy. The feature then shows products which match the given description. This enables the user to easily choose the most desirable option without having to browse through a diverse range of available products. As per Chandrasekaran, SnapSearch is one of the iterations of Find My Style.
Like Find My Style, SnapSearch has also been developed at Snapdeal’s multimedia research lab, which has a commitment of $100 Mn from the company. SnapSearch will employ sophisticated image recognition tools and auto-classify into a category which makes the searches faster. The product can be used not just by buyers, but also by sellers to check similar inventory, proximity-based searches or to check the success of similar items.
To recognise images and show similar results, companies employ computer vision, where massive computing power is used to give computers the ability to recognise images. For this, large computer networks known as deep neural networks are trained using a set of images. When the computer is shown images similar to the one it has already seen, it is able to perform a match.