OCR model in Document Intelligence (prebuilt-read) limited to extracting handwritten and printed text, lines, words and languages. It underpins the other models and suits scans that are mostly text.
Also called prebuilt-read.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Read model in context, with comparison tables and the common traps.
Terms in this definition
- OCR
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.
- Azure Document Intelligence in Foundry Tools
Foundry Tool that pulls text and fields out of forms and documents using read, layout, prebuilt models (such as invoice and receipt) and custom models.
- prebuilt-read
Extraction analyzer in Content Understanding that performs OCR on words, paragraphs, formulas and barcodes but ignores layout. Running it synchronously is available only in preview.