# ddddocr

带带弟弟 通用验证码识别OCR pypi版

Repository: https://github.com/sml2h3/ddddocr
Canonical: https://ross.abutalabs.com/products/ddddocr
Homepage: https://ddddocr.com
Language: Python
License: MIT
License Family: permissive
Topics: ocr, ddddocr, captcha
Last push: 2026-03-10T16:49:52+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 100
- inputs: {"age_days": 1876, "days_push": 176, "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 14665, forks 2336 (observed 2026-08-28T04:11:07.405393+00:00)

## What it is
DdddOcr is a Python library for offline, local recognition of various CAPTCHA types, including alphanumeric, Chinese character, and slider CAPTCHAs, using deep learning models trained on large volumes of generated data. It also supports object detection in images and importing custom-trained models, with a minimal-dependency, easy-to-use API.

## Use cases
- recognize text from captcha images
- solve alphanumeric captchas offline in python
- detect slider captcha gap position
- read chinese character captchas
- detect text regions in images
- use a custom trained ocr model for captchas
- batch recognize captcha images with multithreading

## When to choose
- you need offline, local captcha recognition without paid APIs
- you want a simple pip-installable OCR SDK with minimal setup
- you need to handle slider or Chinese captchas
- you want to plug in your own trained captcha models

## When to avoid
- you need to solve reCAPTCHA, hCaptcha, or other interactive commercial captchas
- you need general-purpose document OCR rather than short captcha strings
- you require 32-bit Windows or Linux support
- you need a hosted API service with managed scaling

## Facets
- artifact type: library
- maturity: active
- function: ocr, computer-vision, image-processing, machine-learning
- domain: computer-vision, image-processing, developer-tools
- platform: python, windows, cross-platform
- tags: captcha-recognition, captcha-solving, slider-captcha, object-detection, offline-ocr, deep-learning, automation, linux, macos

## Member repositories
- sml2h3/ddddocr (main) score 64
- sml2h3/dddd_trainer (plugin) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.405393+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 2026-08-29T17:12:25.724863+00:00, confidence not recorded.
  - readme: https://github.com/sml2h3/ddddocr (fetched 2026-08-28T04:11:07.405393+00:00, sha 79b544e60548)
  - registry_pypi: https://pypi.org/pypi/ddddocr/json (fetched 2026-08-29T08:05:43.822031+00:00, sha 37441311b4c5)
- Data as of 2026-08-30T08:39:29.467469+00:00.