At its annual I/O conference today, Google announced an upgrade to multi-search, which can query objects around you at the same time.
With a new feature called Scene Exploration, Google seeks to make searches more natural by combining understanding of all types of information (text, speech, visual, etc.).
it is built on multiple search In Google Lens, which launched last month, it’s possible to search entire “scenes” at once.
Google uses a grocery store shelf as an example to demonstrate scenario exploration, showing how it can instantly identify items that meet certain criteria.
How does scene exploration work?
When you use MultiSearch for visual search with Google, it is now able to identify objects in a single frame.
With scene exploration coming at some point in the future, you’ll be able to use multiple searches to pan your camera and gather insights about multiple objects in a wider scene.
Google said in a blog post:
“Imagine you’re trying to pick the perfect candy bar for your friend who’s a bit of a chocolate connoisseur. You know they like dark chocolate but not nuts, and you want to give them something premium.
With scene exploration, you’ll be able to scan entire shelves with your phone’s camera and see useful insights superimposed in front of you.
Scene exploration is a powerful breakthrough in our devices’ ability to understand the world the way we do – so you can easily find what you’re looking for – and we look forward to bringing it to multi-search in the future. “
During the Google I/O keynote, it was pointed out that scene exploration uses computer vision to instantly connect the multiple frames that make up a scene and identify all the objects within it.
When the scene browser recognizes an object, it also leverages Google’s knowledge graph to display the most useful results.
source: Google
Featured image: Poetra.RH/Shutterstock
