Key Features
- 90+ language OCR: Text recognition benchmarked against cloud services
- Text detection: Line-level detection in any language
- Layout analysis: Identify tables, images, headers, footers on pages
- Reading order: Detect correct reading sequence of text blocks
- Table recognition: Extract row and column structure from tables
- LaTeX OCR: Recognize mathematical equations and formulas
- PDF support: Process multi-page PDF documents directly
FAQ
Q: What is Surya? A: Surya is a document OCR toolkit with 19.5K+ GitHub stars that performs text recognition in 90+ languages, layout analysis, table detection, and LaTeX OCR. It benchmarks favorably against cloud services like Google Vision and AWS Textract.
Q: How do I install Surya?
A: Run pip install surya-ocr. Then use CLI commands like surya_ocr image.png for text recognition or surya_layout image.png for page layout analysis.
Q: Is Surya free to use? A: Code is GPL licensed. Model weights are free for research, personal use, and startups under $2M funding/revenue. Commercial licensing is available for larger organizations.