https://coin-counter.azurewebsites.net
- General Information
- Used Dataset
- Used Technologies
- Development process
- Architecture Diagram
- How does it work
- Demo
- Screenshots
- Team
AI coin counter app is a web application which enables users to upload photos of their coins and then return the total value of these coins. Due to the lack of a big enough dataset, the only coins that are detected are polish zlotys: 1zl, 2zl, 5zl. By doing this project, we wanted to address a problem of people having trouble counting little coins manually. It is mainly directed to saleswomen and salesmen for whom it eases tasks of counting money. Moreover, during COVID pandemic solution like this could potentially decrease the amount of contact between people, by eliminating the necessity of touching money after other person.
The app was created as a 2-week project (no. 2) for a class "Introduction to applications and solutions based on Artificial Intelligence". The theme of a project was to create an app which brings some innovation to this world and has a potential of bringing benefits for people.
We created custom dataset of coin photos. We found some photos in the internet, but the vast majority of them were taken by ourselves. Because of that the size of the dataset was not very impressive. We have managed to gather 130 photos for our model.
Custom Vision Service - Azure
Azure Storage
Azure Web Services
React.js 17.0.2
- Making photos of coins for a training model
- Creation of prediction (detection) system using one of Azure Cognitive Services -
Custom Vision
. - Implementation of a frontend application using
React.js
. - Connecting trained model with a frontend application using
REST API
andAzure Storage
. - Storing keys in
Azure Key Vault
service to increase security. - Deployment of application using
Azure Web Services
.
- A user opens the web application (hosted in
Azure App Service
), then uploads a photo of some coins (Polish złoty) and clicks the Upload button. - The web application sends the image to
Azure Blob Storage
. Azure Blob Storage
returns a url of the uploaded resource.- The web application sends the image url to
Custom Vision API
. Custom Vision API
returns predictions (detections) of coins.- The web application sums a total value of coins and presents it to the user.
See a demo (in polish):
- Przykładowe działanie:
- Przykładowe działanie:
Krzysztof Szałankiewicz