Portfolio Details

Each project in this portfolio reflects my hands-on experience in solving real-world problems using data science, machine learning, and full-stack development. From predictive models to intelligent web applications, these solutions are built with a focus on scalability, functionality, and impact.

Project Information

  • Project Name: Drag-and-Drop OCR Web App
  • Category: Optical Character Recognition (OCR)
  • Model Type: EasyOCR (Deep Learning-based Text Extraction)
  • Github Repo: Link
  • Live Link: Link

Technologies Used

This project is built using Python and Streamlit for the frontend and interface, with EasyOCR for text extraction from images. It supports multiple image formats including PNG, JPG, and screenshots, and works seamlessly for both printed and handwritten text. Pandas is used for processing extracted data when needed, and the UI is enhanced with custom CSS for a clean, responsive design.

Details of Project

Ever typed an entire paragraph from an image manually? You're not alone — and this tool fixes that.

The Drag-and-Drop OCR Web App is a clean, lightweight tool that lets you instantly extract text from any image. Whether it's a textbook page, scanned notes, a diagram, or a screenshot, just drag & drop the file and get clean, usable text in seconds — no signup, no fuss.

It's especially useful for students, researchers, and professionals who often encounter uncopyable text in images. The app is free, fast, and effective — making it a time-saving productivity booster.

Project Features

  • Drag-and-drop support for PNG, JPG, and screenshot images.
  • Extracts text from both printed and handwritten content.
  • Built using EasyOCR for high accuracy and multilingual support.
  • No login or signup required — privacy-focused and lightweight.
  • Optimized for students, researchers, and anyone handling visual text data.