Drishti is a project at Incubate Nepal that incorporates machine learning and AI to develop a cross-platform mobile application for cash recognition.
The application is used by the visually impaired community to recognize different currency bills and perform their daily cash transactions easily. This user-friendly app uses the flashlight, phone accessibility feature, and gestures to provide desired results. (Add more general information about project. What the purpose of the project is? Motivation?)
- Mobile application
- Computer vision model
- Website
- Tech 1 - version 1.0
- Tech 2 - version 2.0
- Tech 3 - version 3.0
- Frontend: Java
- Data science : Experimentation: Pytorch Training: Tensorflow & Python Deployment: Android tflite library
- Website: HTML, CSS, JavaScript, PHP
Describe how to install / setup your local environment / add link to demo version.
Show examples of usage:
put-your-code-here
List of features ready and TODOs for future development
- Audio feedback in native language
- Ad-free
- Available offline
- Summing up the transactions and showing the history
- Vibration
To-do list:
- Wow improvement to be done 1
- Wow improvement to be done 2
Project is: in progress
Drishti app is peculiarly developed for the blind and low vision community.To understand the need of our end users, the team studied and empathized with them rather than b digging into the financial problems faced by the blind and low vision community in the first place.
After interviewing more than 50 visually impaired individuals, we found that they are already using some cash recognizing apps but are not satisfied with them. Some interviewees also shed light on their daily difficulties while traveling. They have suggested to include some additional features of location tracking and user friendly GPS in our future iterations.Our basic goal is to make a robust application which could benefit them.
| As a/an | I want to | So that I can | Status of progress |
|---|---|---|---|
| User | Scan the currency notes at a bank | Confirm the total sum of money I received | Done |
| User | Identify the bills in the dark using my flashlight | Transact money during the evening too | To do |
| Developer | Get the feedback from the users | Make necessary upgrades in the application | To do |
| Product Owner | Know the progress made in the application during each iteration | Prioritize the future goals for the project | In progress |
| User | Recognize the bills without having to ask others | Be independent in my financial affairs | In progress |
| User | Have a simple UI in my application | Easily navigate into the app | Done |
| User | Have the buttons labeled in the app | Properly recognize the buttons using my phone’s screen reader | Done |
| Software engineer | Easily get the source code of the app | Modify the app and improve its accuracy | To do |
| User | See the history of my scanned notes in a day | I can keep a record of my expenditure list conveniently | Done |
Created by @flynerdpl - feel free to contact me!