Our hack allows the visually impaired to recognize real world objects using Google Glass and the Alchemy API. To do this, we leverage the image capturing capabilities of Google Glass which enables users to take photos of objects and extract textual information from them using a very powerful OCR system. After extracting the text, we perform Natural Language Processing on it using the Alchemy API. This newly generated data is fed back to the Google Glass and the user is notified through the builtin text-to-speech system. This system allows the user to understand anything from what type of can they're holding to what pills are in their medicine bottle.

Share this project: