L'observatoire Data & Créativité by iligo | SEEING AI

SEEING AI – TALKING CAMERA APP FOR THE BLIND

Microsoft Corporation is an American multinational technology company that develops, manufactures, licenses, supports and sells computer software, consumer electronics, personal computers, and related services.

People in the blind or low vision community have much struggle in life.
Microsoft noticed an emerging trend in computer vision : image classification errors were decreasing at a rate of 50 percent year-over-year, meaning it was likely that it would catch up to human accuracy in the near future.
A data scientist working with machine learning and natural language processing at Microsoft wanted to help people with visual impairments by bringing together the power of the cloud and AI to deliver an intelligent app designed to help them navigate their day.

Seeing AI uses the smartphone camera to recognize and narrate the world to people with little or no vision.
Functions include the ability to describe scenes (mentioning what furniture and other objects are around you), people (estimations of their age, gender, emotions and clothing etc) and text recognition (to take a letter or magazine and read out the text).
With a recent update to the app brought several new functions including light detection, colour and handwriting recognition.

The app uses real time AI on-device to guide them to take a better photograph resulting in higher accuracy.
After recognizing image captured by camera, AI analyzes information then turn it into spoken audio.
Key features include – Real-time text reading, document structure understanding, audio-based barcode locator and product recogniser, face recognition and emotion/age/gender description, currency recognition, colour recognition, audible light detector and handwriting reader…