Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ozankaraali/yolov3-recaptcha
Solve Recaptcha with YoloV3
https://github.com/ozankaraali/yolov3-recaptcha
Last synced: 3 months ago
JSON representation
Solve Recaptcha with YoloV3
- Host: GitHub
- URL: https://github.com/ozankaraali/yolov3-recaptcha
- Owner: ozankaraali
- License: mit
- Created: 2019-12-28T12:25:22.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2023-03-25T01:59:21.000Z (almost 2 years ago)
- Last Synced: 2024-08-02T01:25:27.045Z (7 months ago)
- Language: Python
- Size: 3.75 MB
- Stars: 103
- Watchers: 4
- Forks: 26
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-yolo-object-detection - ozankaraali/yolov3-recaptcha - recaptcha?style=social"/> : Solve Recaptcha with YoloV3. A proof of concept Recaptcha solver using YOLOv3 on Tensorflow 2.0 and Selenium. This tutorial shows that with a better trained object detection weight file, ReCaptcha can be easily solved. (Applications)
- awesome-yolo-object-detection - ozankaraali/yolov3-recaptcha - recaptcha?style=social"/> : Solve Recaptcha with YoloV3. A proof of concept Recaptcha solver using YOLOv3 on Tensorflow 2.0 and Selenium. This tutorial shows that with a better trained object detection weight file, ReCaptcha can be easily solved. (Applications)
README
# YOLOv3-ReCaptcha
A proof of concept Recaptcha solver using YOLOv3 on Tensorflow 2.0 and Selenium. This tutorial shows that with a better trained object detection weight file, ReCaptcha can be easily solved.
## Installation
Install requirements and download pretrained weights:
```
$ pip3 install -r ./docs/requirements.txt
$ wget https://pjreddie.com/media/files/yolov3.weights
```
Download [ChromeDriver](https://sites.google.com/a/chromium.org/chromedriver/downloads) and put it into $PATH.
## Quick start
In this part, we will use pretrained weights to make predictions on ReCaptcha.
```
$ python selenium_demo.py
```
## TODO:
- Click images using their pixel positions after finding objects and click VERIFY.
- Using NLP to find relation between "find buses" -> "bus" etc.
- Solve multiple screens such as "skip" or "until no objects left".
## Credits:
[YunYang1994](https://github.com/YunYang1994/TensorFlow2.0-Examples), [Igor Savinkin](https://stackoverflow.com/questions/32249190/improve-recaptcha-2-0-solving-automation-script-selenium/32415298), [Joseph Chet Redmon](https://pjreddie.com/darknet/yolo/)