Detecting Tagged People in Camera Images

Abstract

With the development of technology, cameras are used more widely. It is possible to evaluate the widespread use of cameras in various subjects in daily life. Especially face recognition systems are one of the most important areas of use of cameras. Facial recognition systems can be used in many areas such as cyber security, entertainment, security applications of daily used devices, and faster and easier transactions in financial areas. Although a lot of progress has been made in this regard, face recognition systems are still used widely enough because it is thought that they have weaknesses in terms of security. Many scientists are working on facial recognition. In this study, it is aimed to detect the faces of people determined from videos or live camera images in the best and safest way. Yolov4 object detection algorithm, a ready-made algorithm, was used for the detection of human faces on images. The faces of the people in the images were detected by training the data set we created in the Yolov4 algorithm. An accuracy of 99.1 has been achieved for detecting people's faces on images. The data set we created with pictures of certain people is trained in the CNN algorithm. The faces of the people detected on the images were classified on the model trained with the CNN algorithm for the identification of the people, and the accuracy value was examined for the detection of the identified people on the video recordings or live images from the cameras.