Human Face Recognition Using HAAR Cascade Classifier and Gender Recognition Using Caffemodel with SMTP

Abstract

Due to the non-modeling nature and wide range of applications, facial recognition has always been a persistent study field. Computer vision is now a broad subject that uses high-level programming to automatically execute tasks such as detection, identification, and classification using input images/videos. They are superior than the regular human visual system, even using deep learning approaches. A computer system that detects or confirms a person based on their facial characteristics from a digital picture or video source is known as face recognition. This technology enables us to influence security systems, biometric identification, gait analysis, social networking, and other areas. Because of its non-intrusiveness, accuracy, and speed, live face recognition has gained a lot of traction in security systems. In our project, we created a facial recognition system that uses the Local Binary Pattern Histogram (LBPH) approach to treat real-time human face recognition in low and high-level images. Our research was specifically focused on developing a system that is based on a human gesture known as Face. This is a four-step process. Face detection using the Haar cascade classifier is the first. Face recognition using LHBP classifiers, which are produced from learned faces, is the second option. The third step is to identify the person's gender, and the last step is to record the attendance with the date and time, save it in a database, and email it to the owner by using SMTP. A graphical user interface (GUI) was also employed to make it more user-friendly.