Computer Vision · intermediate · concept 159 of 311 · Updated Nov 4, 2026
OCR & Document AI
Reading text out of scans, PDFs, and photos, then understanding the document's structure: tables, forms, signatures, layouts. Classic OCR engines like Tesseract now share the field with vision-language models that read a whole invoice and answer questions about it directly.
Top AI contributors on this
- Yann LeCunAMI Labs / NYU
- Andrew NgDeepLearning.AI / AI Fund
- Fei-Fei LiWorld Labs / Stanford University
- Andrej KarpathyAnthropic
- Kaiming HeMIT / Google DeepMind
- Ross GirshickAnthropic
Key terms
OCRLayout analysisTable extractionDocument VQAHandwriting recognition
Learn these first
Where you meet it in the real world
Invoice processing, KYC document checks, digitizing archives, receipt scanning, accessibility
Videos
▶ What is Document AI? ↗
Google Cloud Tech · YouTube
▶ LLMs and AI Agents: Transforming Unstructured Data ↗
IBM Technology · YouTube
Guides and articles
Courses, papers, and more