Image-to-Text OCR

The problem

Text stored inside an image is harder to search, copy, or use in downstream applications. Optical character recognition provides a way to extract that content.

What I built

Developed an OCR application that extracts text from images using Python and Tesseract, with Docker for the application environment and Git for version control.

Why it matters to my work

This project sits at the intersection of data processing and practical applications. It complements my professional experience with Python, OpenCV, TensorFlow, and data-focused systems.

Context

This was an academic project at Polytechnic of Milan in 2021. A live demo and accuracy benchmarks are not available on this site.