A Generating Distorted CAPTCHA Images Using a Machine Learning Algorithm

Abstract

 CAPTCHAs (Completely Automated Public Turing Test to Tell Computers and Humans Apart)
have become universal in web security systems to differentiate between automated bots and human users. This
research presents a novel approach for generating and classifying distorted CAPTCHA images utilizing machine
learning techniques. The process involves developing a random text and rendering it onto an image, introducing
distortion for security. The proposed method involves developing CAPTCHA images by combining text rendering
and controlled distortion techniques. These images are then utilized to train a random forest classifier for accurate
recognition. A Random Forest classifier is employed to recognize the generated CAPTCHA images. Experimental
results demonstrate the approach's efficacy in achieving high validation accuracy. The validation accuracy of the
classifier demonstrates its effectiveness in deciphering distorted images. Thus addressing the challenge of creating
CAPTCHAs that are both human-readable and resistant to automated recognition.