Get the latest tech news
Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual)
Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams) - ses4255/Versatile-OCR-Program
This OCR system is specifically designed to extract structured data from complex educational materials—such as exam papers—in a format optimized for machine learning (ML) training. This includes automatic generation of natural language descriptions for visual content (e.g., “This figure shows the process of mitosis in four stages”) to enhance downstream model training. Below are actual examples of outputs generated by this system using real-world materials (2017 EJU Biology & 2014 University of Tokyo Math), including English-translated semantic context and extracted data.
Or read this on Hacker News
