Abstract:

The project caters to the needs of visually challenged people by making an application that is helpful to them. The goal was to create an application that is very efficient and simple to use.

Introduction:

This project aims to help people with the problems of visual impairments. This can essentially be very helpful to the elderly and people with visual impairments to search for any object at any time or listen to any text they have just by taking a picture of it. We aim to remove the dependency that these people have on others to carry out their day-to-day tasks and make them self-sufficient and self-reliant.

Problem Statement:

People with limited vision have difficulty in differentiating between daily objects.They are left reliant on their close ones to carry out their daily tasks. We wish to make it easier for them.

Methodology:

We first started with learning Android Studio and getting comfortable with it. Then we made a basic layout of buttons and text view on the home screen for our app. We then implemented TensorFlow API into our Object Detection app. After the Image Detection was done, we started working on the text to speech by using Android's own TTS library. Lastly, after all the basic functionality was implemented. We finished the project by working on the GUI making it clean, simple and compact.​ Since every member had work split into the different tabs, we had to work in uniformity to not disrupt someone's work.

Outcome(Results):

The app we've created has a lot of potential for helping people with vision impairments when they're partially blind. There are still many improvements that can be made to make this app even better, and we will continue to try to improve it.

Contributors :

Adwit Mittal : https://github.com/AdwitM Alan Marc Louis : https://github.com/Louis-Alan Dhruv Lawaniya : https://github.com/DhruvLawaniya Rahul Khanna : https://github.com/XLazer4