#45 · Primary category： Computer Vision
chandra
OCR model that handles complex tables, forms, handwriting with full layout.
Project last updated：06/26/26
GitHub Stars
12.2K
Forks
1.2K
Contributors
5
License
Apache-2.0
Why we included this project
Chandra turns scanned images and PDFs into structured Markdown, HTML, or JSON without flattening the page into a single text block. That matters for the hard cases: dense tables, forms with checkboxes, handwritten notes, math, and multi-column layouts where simpler OCR tools lose the structure. The output is machine-readable, so teams building search indexes, extraction pipelines, or publishing workflows can feed it straight into their systems instead of re-parsing. It supports more than 90 languages, which helps when your documents aren't all in English. The open weights run locally through Hugging Face or a vLLM server, and a CLI plus a small web app let you test it before you build anything around it.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)