<![CDATA[Traditional web login systems using usernames and passwords have weaknesses in terms of security and are vulnerable to hacking attacks. Therefore, this research proposes the development of a web login system with a face recognition authentication method using artificial intelligence to overcome that problem. This project involves several main steps. First, a dataset of facial images will be collected, including variations in lighting conditions, poses, and facial expressions. Furthermore, the facial recognition model will train using the Haar Cascade Classifier and Local Binary Pattern algorithms. The trained model will be integrated into the web application using the appropriate programming language and framework, such as Python with Django. The web login interface will allow users to enter login information and take pictures of their faces. The system will use face detection and feature extraction techniques to extract facial features from uploaded images. These features will compare with the stored dataset of facial images using the trained facial recognition model. It is successful when there is a match, and the user will be granted access to the web application. To improve security, testing, and evaluation of the developed system will be carried out to measure its performance, including using metrics such as accuracy, precision, recall, and F1-score. All vulnerabilities of security or limitations identified during the evaluation will be addressed and fixed. Implementation will provide a more secure and user-friendly login experience. By utilizing the advances in facial recognition technology and artificial intelligence, this study aims a contribution to improving web authentication systems and protecting user data from unauthorized access]]>
