An open-source Laravel application that extracts terms from images or PDF files using OCR (Optical Character Recognition).
The project aims to achieve the best extraction accuracy possible, experimenting with different approaches and techniques to improve results.
To build a reliable and extensible tool for term extraction, contributing to research, linguistics, and data-driven applications.
This project explores and tests multiple tactics and OCR configurations to find the optimal balance between accuracy and performance.
Released under the MIT License — open for personal and commercial use.