OCR Optical Character Recognition
Reading text out of images — receipts, invoices, old books, signs.
Classic tools: Tesseract (open source), AWS Textract, Google Vision. Modern VLMs (GPT-4V, Claude) do OCR + understanding as a bonus.
Reading text out of images — receipts, invoices, old books, signs.
Classic tools: Tesseract (open source), AWS Textract, Google Vision. Modern VLMs (GPT-4V, Claude) do OCR + understanding as a bonus.