The new search tool is built on its Lumos machine learning platform, which aims to understand images and video, and is designed to be used without deep learning and computer vision training.
While, the AI-based tool recognizes photos at the "pixel level", it also enable the systems do things like recognize what type of scene the image is taken; whether it's a well-known landmark, and so on.
And the possibilities are enormous, imagine whereby someone could search through all the photos that his or her friends have shared to look for a particular image content instead of relying on tags or surrounding text.
Along the same line, the new search tool will help the network to better identify inappropriate image and video contents.
The company hopes that the computer vision models will get "pixel perfect" and with advancement in video and other immersive formats, Lumos will help unlock new possibilities, and pave the road for richer experiences in the near future.
