-
-
GUI
Inspiration
we wanted to build a solution that helps people quickly and accurately identify genuine Indian coins using machine learning and computer vision.
What it does
The Indian Coin Detection App is an AI-powered tool that can recognize Indian coins from images. Users can take a picture or upload an image, and the app will classify the coin based on its denomination and authenticity. It provides real-time results, helping users verify coins with ease.
How I built it
- Tech Stack: Python, TensorFlow, OpenCV
- Dataset: Collected and preprocessed images of various Indian coins from different angles and lighting conditions
- Model Training: Used a Convolutional Neural Network (CNN) to train the model to classify and detect coins accurately
- Web App: Built a user-friendly interface with React.js, allowing users to upload images and view results in real time
Challenges I ran into
- Data Collection: Finding high-quality images of Indian coins from various sources was challenging
- Model Accuracy: Ensuring the model could distinguish between genuine and counterfeit coins required multiple iterations
- Deployment: Optimizing the model for fast predictions without compromising accuracy was a key hurdle
Accomplishments that I'm proud of
- Successfully trained a machine learning model with high accuracy in classifying Indian coins
- Built a functional web app that integrates AI-powered coin detection
- Optimized the model to run efficiently on a web-based platform
What I learned
- Deep learning techniques for image classification
- Using OpenCV for image preprocessing
- Deploying machine learning models in real-world applications
- Optimizing AI models for speed and accuracy
What's next for Indian Coin Detection App
- Mobile App: Develop a mobile-friendly version for easier access
- User Feedback Integration: Allow users to report misclassifications and refine the model further
Built With
- machine-learning
- opencv
- python
- streamlit
Log in or sign up for Devpost to join the conversation.