Skip to content
Change the repository type filter

All

    Repositories list

    • DigitSnap

      Public
      This project provides a Flask-based web application for real-time handwritten digit recognition using a Convolutional Neural Network (CNN) model trained on the MNIST dataset. The system allows users to upload images of handwritten digits and get predictions for the full number (e.g., "1234") .
      Jupyter Notebook
      0100Updated Jun 18, 2025Jun 18, 2025
    • A lightweight Flask web app for recognizing handwritten Devanagari digits (0–9) using a trained CNN model. Users can upload digit images through a clean Bootstrap interface, and the app returns real-time predictions. Includes preprocessing with Pillow, Keras-based inference, and is ready for local or cloud deployment.
      Jupyter Notebook
      0100Updated Jun 18, 2025Jun 18, 2025
    • A fully Dockerized Flask-based API system for recognizing both Western and Devanagari handwritten digits. It features isolated containers for each model, managed via Docker Compose, and served through a unified UI with Nginx reverse proxy. Designed for local development and easy deployment on AWS EC2, the project supports RESTful API interaction.
      Python
      0100Updated Jun 9, 2025Jun 9, 2025
    • A Flask-based RESTful API for real-time handwritten digit recognition using a CNN model with TensorFlow.
      Jupyter Notebook
      0100Updated May 7, 2025May 7, 2025
    • This repository contains a Flask web application that acts as a unified interface for two different machine learning models—one for predicting decimal digits and another for predicting Devanagari characters. The app allows users to upload an image file, select the model type ('decimal' or 'devanagari'), and receive predictions.
      Python
      0100Updated May 7, 2025May 7, 2025
    • Python
      0100Updated Nov 25, 2024Nov 25, 2024