# chineseocr

yolo3+ocr

Repository: https://github.com/chineseocr/chineseocr
Canonical: https://ross.abutalabs.com/products/chineseocr
Language: Python
License: MIT
License Family: permissive
Topics: yolo3, chinese-text-detect, chinese-ocr, opencv-dnn, darknet-text-detect, idcard, trainticket, ocr
Last push: 2022-08-29T02:53:47+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": 3046, "days_push": 1465, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6123, forks 1705 (observed 2026-08-28T04:09:36.207894+00:00)

## What it is
A Python OCR toolkit that combines YOLO3-based text detection with CRNN/Dense recognition for Chinese and English text in natural scene images. It supports text orientation detection, model conversion between darknet/keras/pytorch, and structured recognition of ID cards and train tickets, and can serve results via a web API.

## Use cases
- extract chinese text from photos
- ocr id card fields into structured data
- detect and read text in natural scene images
- train a custom crnn ocr model for chinese and english
- run ocr as a self-hosted web service
- recognize train ticket information from images

## When to choose
- you need Chinese scene-text OCR with detection and recognition in one pipeline
- you want trainable OCR models with darknet/keras/pytorch conversion
- you need structured extraction from ID cards or train tickets
- you want a self-hosted OCR web service with GPU support

## When to avoid
- you need actively maintained software with recent updates
- you only need printed-document OCR for Latin languages
- you want a plug-and-play OCR without downloading external model weights
- you need CPU-optimized real-time inference on edge devices

## Facets
- artifact type: library
- maturity: maintenance
- function: ocr, computer-vision, machine-learning, image-processing
- domain: computer-vision, image-processing, deep-learning
- platform: python
- tags: chinese-ocr, yolo3, crnn, text-detection, darknet, keras, idcard-recognition, scene-text, natural-language-processing, linux, docker, gpu

## Member repositories
- chineseocr/chineseocr (main) score 32
- chineseocr/darknet-ocr (mirror) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:36.207894+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 2026-08-29T17:47:59.708632+00:00, confidence not recorded.
  - readme: https://github.com/chineseocr/chineseocr (fetched 2026-08-28T04:09:36.207894+00:00, sha 6c82d5cd5123)
- Data as of 2026-08-30T08:39:29.467469+00:00.