About

Small, honest, local OCR

BrowserOCR is a static web application for turning one JPEG, PNG, WebP, BMP, TIFF, or HEIC image into editable text. It intentionally excludes accounts, uploads, PDF, translation, batch processing, and server fallbacks.

How it works

ONNX Runtime Web executes PP-OCRv6 in a dedicated Web Worker. TypeScript handles local image decoding, normalization, detection post-processing, line crops, CTC decoding, and reading order.

Model attribution

The detector and recognition models are PP-OCRv6 by PaddlePaddle, distributed under the Apache License 2.0. BrowserOCR uses the official Tiny detector, Tiny recognizer, and optional Small recognizer ONNX exports. See the versioned model manifest and license copy.

Image decoder attribution

TIFF decoding uses the MIT-licensed UTIF library. HEIC/HEIF decoding uses the pure-Rust WASM decoder maintained in the open-source heictosize.com repository and distributed here under AGPL-3.0. See the bundled license notice.

Limits

OCR results can contain errors. High accuracy changes recognition only and cannot recover lines missed by the shared detector. Always verify critical text against the original image.

Contact

Questions, bug reports, and support requests are welcome at [email protected].