Computer vision

tesseract.js

naptha/tesseract.js

Tesseract OCR for browsers and Node.js using WebAssembly, suitable for image-to-text features in JavaScript apps.

Officiële repository openen ↗ Projecthomepage ↗
★ 38,7KSterren
⑂ 2,4KForks
49Openstaande problemen
JavaScriptTaal
Apache-2.0Licentie
Q90Redactionele score

Overzicht

Tesseract.js offers browser or server-side OCR without replacing the underlying Tesseract recognition model. It explicitly does not accept PDFs directly. Choose it for JavaScript integration and image workloads, after testing target devices.

Belangrijkste functies

  • Browser and Node.js
  • WASM engine
  • Language data
  • Reusable workers
  • Async API

Vereisten, installatie en snel aan de slag

Install tesseract.js with npm and follow the current worker example for your browser or supported Node.js version.

Gebruik

Compare clear, rotated, and low-contrast images. Reuse workers, limit concurrency, and render PDF pages separately if required.

How it works
A worker loads the WASM engine and language data, recognizes images, and can be reused across jobs. Business extraction remains separate.

Audience and requirements
JavaScript developers adding OCR. Compatible browser/Node.js and language assets.

Practical use cases
Screenshot text; reviewed form prefill; image batches.

Limitations and selection
No direct PDF support. Initialization and memory matter on mobile devices. Handwriting and tables require evaluation.

Related projects and selection
tesseract-ocr/tesseract：Upstream: this is the OCR engine wrapped by Tesseract.js.

JaidedAI/EasyOCR：Comparison: EasyOCR targets Python/PyTorch workflows; Tesseract.js targets JavaScript.

Source review
Editorial analysis of upstream sources, without runtime or benchmark testing. Proposed workflows are editorial suggestions.

Modelcompatibiliteit en gebruiksscenario's

Uses Tesseract language data and a WebAssembly engine, not a vision-language model interface.

Licentie- en risiconotities

The repository page identifies Apache-2.0. Read LICENSE; model weights and datasets may have separate terms.

Editorial source review 2026-09-09T05:00:00.950Z. README and live repository page verified; current stars/forks from GitHub HTML. Last-push metadata retained from 2026-09-05 discovery snapshot. No runtime benchmark. Integration proposals are editorial analysis.

Release en onderhoud

Reviewed 2026-09-09. Counters come from repository pages; features are based on upstream documentation. See Releases in the source links. Editorial analysis of upstream sources, without runtime or benchmark testing. Proposed workflows are editorial suggestions.

opencv

opencv/opencv

★ 90,7KC++

tesseract

tesseract-ocr/tesseract

★ 76,3KC++

yolov5

ultralytics/yolov5

★ 58KPython

faceswap

deepfakes/faceswap

★ 57,5KPython