# Tesseract OCR

Tesseract Open Source OCR Engine (main repository)

Repository: https://github.com/tesseract-ocr/tesseract
Canonical: https://ross.abutalabs.com/products/tesseract-ocr
Homepage: https://tesseract-ocr.github.io/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: tesseract, tesseract-ocr, ocr, lstm, machine-learning, ocr-engine, hacktoberfest
Last push: 2026-08-25T15:34:02+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 62, longevity 100
- inputs: {"age_days": 4404, "days_push": 8, "days_rel": 40, "gap_med": 210, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 76200, forks 10771 (observed 2026-08-28T04:12:21.573329+00:00)

## What it is
Tesseract is an open-source OCR engine consisting of the libtesseract library and a command-line program, using an LSTM-based neural network (with legacy engine support) to recognize text in images. It supports over 100 languages, multiple input image formats, and outputs plain text, hOCR, PDF, TSV, ALTO, and PAGE formats.

## Use cases
- extract text from scanned pdf documents
- convert images of text to plain text
- ocr receipts and invoices
- recognize text in multiple languages
- add ocr to a document processing pipeline
- generate searchable pdfs from scans

## When to choose
- you need a free, self-hosted OCR engine with broad language support
- you want a library or CLI that integrates into document pipelines
- you need structured output like hOCR, TSV, or searchable PDFs

## When to avoid
- you need high accuracy on low-quality or complex-layout images without preprocessing
- you need handwriting recognition at state-of-the-art accuracy
- you want a ready-made GUI application

## Facets
- artifact type: library
- maturity: stable
- function: ocr, image-processing, machine-learning, cli
- domain: computer-vision, image-processing, pdf, developer-tools
- platform: windows, cpp, cli, cross-platform
- tags: lstm, traineddata, hocr, multilingual, text-recognition, natural-language-processing, linux, macos

## Member repositories
- tesseract-ocr/tesseract (main) score 86
- tesseract-ocr/tessdata (plugin) score 23
- tesseract-ocr/tessdoc (docs) score 75
- tesseract-ocr/tessdata_best (plugin) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.573329+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:14:23.982486+00:00, confidence not recorded.
  - readme: https://github.com/tesseract-ocr/tesseract (fetched 2026-08-28T04:12:21.573329+00:00, sha b34b7949c5f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.