Auditory Vision

undefined

Overview

undefined

Finding objects is Extremely difficult for Blind People. They need to touch all over the surface to just find a single object.The goal of the project is to dictate the objects surrounding them using speech services and Machine learning.

undefined

Goals

undefined

1. Object Recognition
2. Object Dictation

undefined

Specifications

undefined

The interface is Camera integrated with CoreML to integrate our Machine Learning Model for Object Recognition and UITapGestureRecogniser for Object Dictation.

undefined

Apple Frameworks Used

undefined

1.Vision

undefined

To Access Camera and parse it to multiple frames to analyze it piece by piece to pass it that input data to model for Object Prediction

undefined

2.AVFoundation

undefined

After the prediction from the model we use AVFoundation framework to convert the processed output from the model that is text and convert it to speech for understanding to blind people.

undefined

3.UIKit

undefined

To Access Single Tap and Double Tap events from UITapGestureRecogniser