A Docker-powered microservice for intelligent PDF document layout analysis, OCR, and content extraction. This tool provides advanced PDF layout analysis with VGT and LightGBM models, supporting 150+ languages for OCR, and converting PDFs to multiple formats including Markdown and HTML. Built with Clean Architecture principles to support human rights documentation workflows.
Fund this project
HURIDOCS (Human Rights Information And Documentation Systems)
huridocs.org/
github.com/huridocs/pdf-document-layout-analysis