부산대학교 도서관

This paper illustrates a group photographing guidance system that enables to detect the eyes if closed and the face if occluded by another subject in group photo. To consider the practical issue, the proposed auxiliary system is designed to remind the photographer when any face of subject is occluded, or eyes closed. We perform eyes-closed detection on every detected face region. If the eyes of subject were closed during the shot, system will notice the photographer automatically. In this study, the Multi-task Cascaded Convolutional Networks (MTCNN) is applied for face detection. MTCNN is efficient for the group photo with a large amount subject. Compared with media-pipe contributed by Google, the number of human and bounding box detected by MTCNN is more accurate and complete. For eyes detection, a simple convolution neural network is used. In the experiments, we demonstrated that the results well-performed in terms of the occluded ratio of every covered face as well as whose eyes are closed.