Google is working with a chip designer Movidius to build deep learning into smartphones, allowing the devices to identify objects in images and videos without extra apps or even internet access.

With the new capability, smartphones could recognize faces in photos or translate signs, according to The Wall Street Journal. “This means future products can have the ability to understand images and audio with incredible speed and accuracy, offering a more personal and contextualized computing experience,” a Movidius blog post explained.

As a part of the partnership, Google will buy Movidius’s new chip, the MA2450, for an unspecified sum. “By working with Movidius, we’re able to expand this technology beyond the data center and out into the real world, giving people the benefits of machine intelligence on their personal devices,” the head of Google’s machine intelligence group Blaise Agϋera y Arcas said in the post.