Optical character recognition. It reads handwritten or printed text from documents and images, making it available for analysis, something Azure Language cannot do with scanned images by itself.
Also called optical character recognition.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains OCR in context, with comparison tables and the common traps.
Related terms
- Advanced data parsing
Structure-aware document processing: it applies OCR to scanned pages, joins tables spanning pages, recovers headers and produces chunks tagged with heading, page and table metadata, in contrast to fixed-size or page-by-page chunking.
- AI enrichment
Indexing-time process in Azure AI Search where skills such as OCR, key phrase extraction, entity recognition and image analysis turn raw content into fields that can be searched.
- Azure Vision in Foundry Tools
Foundry Tool for analysing images, reading text from them (OCR) and detecting faces. Image Analysis API versions 3.2 and 4.0 are both deprecated, with retirement set for 25 September 2028.
- Content extraction
Content Understanding begins here, converting whatever comes in to text plus metadata, by transcribing audio and video or by running OCR and layout analysis on documents.
- Data classification
Covers the methods Purview uses to recognise sensitive content, from pattern-based types and exact data match to machine-learning classifiers, fingerprinting and OCR. Labelling, DLP and retention all rely on what it detects.
- Foundry Tools containers
Docker images that let certain Foundry Tools, for example Language and Read OCR, run at the edge or on-premises with billing still going to Azure. Both custom and prebuilt features are offered this way.
- GPT-4 vision-preview
Preview model adding vision to GPT-4, with OCR, object grounding and video enhancements. Now retired, it gave way to gpt-4 turbo-2024-04-09 and later GPT-4o, so it should not be chosen for new image scenarios.
- Image Analysis
Azure Vision API that returns several visual features in a single request: for instance tags, a caption, text recognised by Read OCR and the bounding boxes of detected objects.