IRIS: Image Recognition Integrated Signalling - Colour Detection and Dictation for the Visually Impaired
We utilize state-of-the-art Artificial Intelligence to extract & identify subjects & features from live video footage, for active verbal communication of colour information directly in front of the user.
Detecting objects with a Convolutional Neural Network, we then utilize Support Vector Machines to classify different text-colour pairs under particular HSV value thresholds.
To run mannually, run the object_detection file to generate an image, then subsequently utilize the classifier colorProcessing to run the the text to audio generation.