Bringing AI to to the visually impaired.
Point the camera in front of you, and the app will identify the object or environment
The text-to-speach sounds like a real person
Choose from a male or female voice.
Select a Reporting Interval from 2s to 30s
SmartEyes will begin taking photos on a user defined interval (2-30 seconds)
An image is automatically uploaded to the cloud to be analyzed by Google Vision
Google Vision analysis the image through their machine learning, and tags the image
The contents of the image are stated with iSpeech
Researcher at the University of Texas - RGV