Face detection techniques have been expanded since the 1960s, and advances in machine learning and deep learning have revolutionized the field. Face detection algorithms are widely used in various applications, including security, surveillance and social media. TheViola–Jones object detection framework is the first to give a competitive object detection rate in real-time, introduced by authors Paul Viola and Michael Jones in 2001. However, it can be trained to detect different object classes, primarily inspired by the face detection problem. The most common features used for facial recognition include shape, color, and texture. These systems are often combined with other technologies, such as facial recognition, to improve accuracy and performance further. Face detection systems are becoming increasingly popular because they help identify people quickly and accurately. This review paper explores and reviews the basis of mathematical equations and the evaluation of various techniques and models, such as CNN-based models, their architecture and their pros and cons. In addition, facial color, gender bias, dataset bias, and facial features in low-resolution images are still a challenge that needs to be worked on