{"repo":"HRN-Projects/amazon-captcha-solver","free":true,"listed":false,"github":"https://github.com/HRN-Projects/amazon-captcha-solver","clone":"git clone https://github.com/HRN-Projects/amazon-captcha-solver.git","description":"A TensorFlow (Deep Learning - CNN) based solution for tackling captcha when collecting data from Amazon.","language":"Python","stars":28,"topics":["captcha","amazon-captcha","captcha-solving","captcha-solver","python","python3","tensorflow","keras","open-cv","hrn-projects"],"license":"GPL-3.0","category":"machine-learning","readme_excerpt":"Amazon Captcha Solver A Flask API based solution for tackling captcha when collecting data from Amazon. This is a Flask API based solution to solve the captcha, by accepting the captcha image from POST request. The API then calls the captcha solving script and sends the solved captcha text in return. The goal is to solve the captcha images from Amazon. Sample captcha image can be seen below - How to use : ## 1. Run the Flask API script - 2. To check the status of API, call the default method by accessing its IP - 3. To call the captcha solver function with 'requests' module and passing captcha image as file - How to contribute : ## 1. Please start with installing all the required packages from requirements file- 2. Then to initially run the model on test captchas, use following command - P.S. Notes : ## Regarding model file ### The current model file is built after training some 4K training set captcha images. Training can performed on much more larger dataset for better results, but current results aren't bad either :wink:. Regarding API code ### The API works fine but can be enhanced further according to use cases. The API's reponses would highly depend upon the training quality of the model file.","default_branch":null,"files":null,"tree":[],"storefront":"/r/HRN-Projects","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/HRN-Projects/amazon-captcha-solver/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}