This project started with Reading and Solving captchas from the Golestan site. Steps:
- Collecting captchas using an API.
- Convert captcha backgrounds to black and white.
- Split created picture to alphabet and digits by cropping the picture.
- Train the handmade Dataset from Golestan captchas
- Implement KNN to the trained dataset.
- Save the model to the .sav file for decreasing the running time of the program.
- Get the captcha's text as the output by 96% accuracy.
Install the dependencies.
pip3 install -r requirements.txt
Run modelTrainer.py for train model using Datasets.
After the model created and saved in directory you should run captchaSolver.py for solving speciefic captcha.
-
modelTrainer.py: trains the model
-
captchaSolver.py: captcha solver
-
cropLettersFromImage.py: image preproccessing and cropping
-
TrainAndSolver.py: captcha solving proccess in notebook
-
Datasets: training dataset captchas
-
Golestan-Captchas: test captchas