Recognize English text from raw image bytes.
Automatically enhances and retries if the first OCR pass is low-quality.
docType — hint the document type to apply correct handwriting policy.
Recognize English text from an image file path.
Automatically enhances and retries if the first OCR pass is low-quality.
docType — hint the document type to apply correct handwriting policy.
Recognize text from a PDF file (renders page to image first).
page — zero-based page index (default 0).
scale — render quality (default 2.0, higher = better OCR but slower).
docType — hint the document type to apply correct handwriting policy.
Uses native PDF rendering — no third-party packages needed.