skyduy/CNN_keras

CNN | Keras/PyTorch | CAPTCHA recognition(卷积神经网络、Keras/PyTorch框架、验证码识别)

50
/ 100
Established

This helps automate the reading of those wavy, distorted image puzzles designed to prove you're human. You feed it CAPTCHA images like "5WNAU.jpg", and it tells you the letters and numbers within them. This is for anyone who needs to automatically process information from websites or systems that use these specific visual verification tests.

291 stars. No commits in the last 6 months.

Use this if you need to programmatically extract text from standard image-based CAPTCHAs, like the ones with distorted letters on a noisy background.

Not ideal if you are dealing with modern CAPTCHAs like reCAPTCHA v2/v3, image selection puzzles, or audio-based verification.

data-entry-automation web-scraping bot-development optical-character-recognition CAPTCHA-solving
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

291

Forks

94

Language

Python

License

MIT

Last pushed

Nov 18, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/skyduy/CNN_keras"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.