# JinpengLI/deep_ocr

make a better chinese character recognition OCR than tesseract

Repository: https://github.com/JinpengLI/deep_ocr
Canonical: https://ross.abutalabs.com/products/deep_ocr
Language: Python
License Family: other
Last push: 2017-11-12T10:49:29+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3629, "days_push": 3216, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1511, forks 481 (observed 2026-08-28T04:04:55.939238+00:00)

## What it is
A Python-based deep learning OCR tool built on Caffe that recognizes Chinese characters, positioned as a better alternative to Tesseract for Chinese text. It also includes experimental Chinese ID card recognition and Docker images for CPU-based deployment.

## Use cases
- recognize chinese text in images better than tesseract
- ocr chinese characters from screenshots
- extract text from chinese id card images
- train custom chinese character recognition models with caffe
- run chinese ocr in a docker container on cpu

## When to avoid
- you need a maintained project with recent updates or a license
- you need OCR for non-Chinese languages
- you need production-grade ID card recognition, which the author notes is unstable
- you work outside Linux/Ubuntu

## Facets
- artifact type: library
- maturity: abandoned
- function: ocr, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning
- platform: python, cli
- tags: chinese-ocr, caffe, character-recognition, id-card-recognition, tesseract-alternative, natural-language-processing, linux, docker

## Member repositories
- JinpengLI/deep_ocr (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.939238+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 2026-08-30T04:32:22.162139+00:00, confidence not recorded.
  - readme: https://github.com/JinpengLI/deep_ocr (fetched 2026-08-28T04:04:55.939238+00:00, sha 8f9b581280c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.