# RQLuo/MixTeX-Latex-OCR

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

Repository: https://github.com/RQLuo/MixTeX-Latex-OCR
Canonical: https://ross.abutalabs.com/products/mixtex-latex-ocr
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: computer-vision, deep-learning, latex, machine-learning, ocr, onnx, python
Last push: 2025-04-24T09:51:00+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 18, release rhythm 8, longevity 54
- inputs: {"age_days": 767, "days_push": 496, "days_rel": 556, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1637, forks 97 (observed 2026-08-28T04:05:14.820097+00:00)

## What it is
MixTeX is a multimodal OCR application that recognizes LaTeX formulas, tables, and mixed Chinese/English text from images, running entirely offline on CPU. It is packaged as a lightweight Windows GUI program with ONNX-based inference requiring no GPU.

## Use cases
- convert screenshots of math formulas to LaTeX code
- extract tables from images as LaTeX table code
- OCR mixed Chinese and English text with formulas offline
- digitize exam or paper content without internet
- recognize equations on a computer without a GPU

## When to choose
- you need offline, privacy-preserving OCR on Windows without a GPU
- you need LaTeX output for formulas and tables, including bilingual Chinese/English text

## When to avoid
- you need OCR on Linux or macOS (only Windows packaging is provided)
- you need handwriting recognition or very large-scale batch document processing
- you need a cloud or GPU-accelerated OCR pipeline

## Facets
- artifact type: application
- maturity: active
- function: ocr, computer-vision, machine-learning, image-processing
- domain: computer-vision, image-processing, education
- platform: windows, python
- tags: latex-ocr, table-recognition, offline-inference, onnx, cpu-inference, formula-recognition, multimodal, natural-language-processing

## Member repositories
- RQLuo/MixTeX-Latex-OCR (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:14.820097+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 2026-08-30T03:46:40.063080+00:00, confidence not recorded.
  - readme: https://github.com/RQLuo/MixTeX-Latex-OCR (fetched 2026-08-28T04:05:14.820097+00:00, sha 600559d35965)
- Data as of 2026-08-30T08:39:29.467469+00:00.