This project implements a machine learning model to recognize handwritten digits using the popular MNIST dataset. It utilizes fundamental Python libraries such as NumPy, pandas, scikit-learn, and matplotlib for data processing, model training, and visualization.
The model is trained to classify grayscale images of handwritten digits (0–9). This is a classic supervised learning task using the MNIST dataset, which contains 70,000 labeled images. The primary goal is to achieve accurate recognition of digits using efficient data preprocessing and classification techniques.
- NumPy – For numerical operations and matrix manipulation
- pandas – For data handling and preprocessing
- scikit-learn – For machine learning models and evaluation
- matplotlib – For data visualization
- MNIST Dataset – Benchmark dataset for digit classification
- Loads and preprocesses the MNIST dataset
- Trains a classification model using
scikit-learn - Visualizes example digits and predictions
- Evaluates model performance with accuracy and confusion matrix
- Clone the Repository
git clone https://github.com/Naman-kr404/digit-recognition-model.git cd handwritten-digit-recognition - Install Required Packages
pip install numpy pandas scikit-learn matplotlib
- Run the Script
python digit_recognition.py
Accuracy score on the test dataset
Confusion matrix
Visualization of some predicted digits
handwritten-digit-recognition/
├── digit_recognition.py
├── README.md
├── requirements.txt
└── assets/
└── example_predictions.png
-
Integrate deep learning models (e.g., CNN with TensorFlow/Keras)
-
Deploy as a web app using Flask or Streamlit
-
Enable real-time digit prediction using user-drawn input
Contributions, issues, and feature requests are welcome! Feel free to check the issues page.
For questions or collaboration, contact: [spjnaman@gmail.com]