Optical Character Recognition (OCR)
Intelligence service that unlocks information within images by detecting and extracting both printed and handwritten text.
Availability
- Synchronous: Processing API task for immediate results
- Asynchronous: Workflow task for bulk processing
Structured Output
Highly structured JSON with extracted text plus precise bounding box coordinates for each text area, line, and individual word.
Advanced Applications
- Document digitization and indexing
- Product information extraction
Coordinate Data
Enables applications beyond text extraction, supporting layout analysis and targeted content manipulation.
Related terms
Intelligence (AI) Service
Machine learning tasks that tag, caption, moderate, scan and read files.
Document Detection
Intelligence task that finds and straightens a document in a photo for OCR.
Processing API
Transforms files through tasks added to a Filestack URL.
Workflows
Background processing of uploaded files with tasks and logic rules.
More in Intelligence
This page is one of 94 terms in the Filestack glossary.
Browse all terms