# ypwhs/captcha_break

验证码识别

Repository: https://github.com/ypwhs/captcha_break
Canonical: https://ross.abutalabs.com/products/captcha_break
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: captcha-breaking, keras-tutorials, deep-learning, keras, ocr, captcha, jupyter-notebook, pytorch-tutorial, crnn, ctc-loss
Last push: 2022-02-25T08:48:08+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3480, "days_push": 1650, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2822, forks 667 (observed 2026-08-28T04:07:24.061641+00:00)

## What it is
A tutorial repository demonstrating how to break captcha images using deep learning with Keras, including a CNN and CRNN with CTC loss. It provides Jupyter notebooks covering data generation, model building, and training for captcha recognition.

## Use cases
- recognize captcha images with deep learning
- learn how to train a CRNN with CTC loss
- generate synthetic captcha training data
- tutorial on keras image classification
- ocr for short text images

## When to choose
- learning deep learning-based captcha recognition
- studying CRNN and CTC loss implementations
- following a hands-on Keras tutorial with notebooks

## When to avoid
- production captcha solving at scale
- projects requiring modern maintained OCR libraries
- environments without GPU support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, ocr, machine-learning, image-processing
- domain: deep-learning, computer-vision, tutorials
- platform: python
- tags: captcha-breaking, keras, crnn, ctc-loss, jupyter-notebook, tensorflow, natural-language-processing, gpu

## Member repositories
- ypwhs/captcha_break (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.061641+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 2026-08-30T07:38:18.778686+00:00, confidence not recorded.
  - readme: https://github.com/ypwhs/captcha_break (fetched 2026-08-28T04:07:24.061641+00:00, sha 42a429ed8ad6)
- Data as of 2026-08-30T08:39:29.467469+00:00.