eBay is introducing a new feature that uses computer vision technology to make sellers’ listing photos easier on the eyes and more effective in Google Shopping for both Android and iOS.
The feature removes the background of a seller’s listing photo and replaces it with a white background, optimizing listings for Google Shopping, and improving the shopping experience for buyers by making search look and feel more streamlined.
Because many images posted on the marketplace are created by small business sellers or C2C (Consumer To Consumer) sellers, the images often have clutter in the background.
Besides improving the images for Google Shopping and shoppers browsing the marketplace, cleaning up the images by removing the background will also positively impact results when shoppers user eBay’s Image Search function.
How It Works
Sellers can easily use this feature by going into the Sell flow from their mobile device. After they take or upload their photos within the eBay listing flow on their Android or iOS device, the seller can leverage the background removal tool to make a first pass at adding the white background for any of their photos. The seller can also touch up any missing areas or use the photo as is.
The Technology Behind Image Clean-up
eBay’s computer vision algorithm processes the photo completely, using the processor on the user’s mobile phone, to separate the foreground from the background clutter. Doing so enables eBay to change the background to a uniform white for a consistent look and feel.
The current approach is based on these assumptions:
● Pixels along the image border are predominantly background
● The foreground and background have sufficient contrast to indicate different coloring
eBay developers built color models for the foreground and background and solved for unknown pixels in the mask using conditional random fields.
The output of the algorithm is a mask made up of the probability of foreground for each pixel. For example, when this is 100%, the pixel is entirely associated with the foreground, and when it is 0%, it is entirely associated with the background. This mask is then used to blend the foreground with a white image resulting in the desired image.
The confidence in background removal is measured by a factor that eBay calls “separability,” which estimates how difficult it is to separate the foreground from background.
The closer the separability score is to the maximum value of 100%, the more likely the algorithm can easily separate the foreground from the background.
eBay uses this to guide the tool on whether it should show an auto-cleanup result to the user or let the user do manual touchup to remove the background.
Low contrast images and images with background clutter will typically produce a low separability score.
Images that score close to 100% on separability will trigger a bonus flow through Automatic Cleanup, in which the background removal tool will attempt to remove the background without seller input.
The seller can then choose whether they want to use the photo as is, or make edits and do touchups of their own.
eBay Hack Week Innovation and Feature Availability
The Hack Week competition was also instrumental in getting Image Search off the ground at eBay.
Leveraging the latest advances in computer vision and AI, eBay continues to work on additional features that will make users’ lives easier.
This feature is now rolling out on Android and iOS devices in the U.S., U.K. Germany, and Australia and will be rolling out to all other regions in the next month.
What do you think about this new feature, and will you be using it to clean up your images for your eBay listings?
Please use the comments section below or head over to our Facebook Group for Small Business Sellers and interact with other small business owners.