부산대학교 도서관

Accurate identification of panic among individuals is a challenging but valuable application in the rapidly growing field of emotion recognition, particularly in the public security and healthcare industries. To recognize the panic emotion in a pedestrian crowd, this study introduces a facial expression recognition network (FER-net) as an advanced deep-learning network aimed at recognizing panic states. Then a panic recognition model based on face alignment (FA) and convolutional neural network (CNN) is proposed. This model can obtain greater accuracy in detecting minor emotions indicating panic by maintaining the ideal alignment of facial features. To validate this proposed model, experiments were designed. The experiment results showed a significant increase in panic detection rates compared with conventional models, and the possibility of the FER-net as a reliable tool for use in reality. Finally, this study emphasizes the positive effects of using face alignment with CNNs and can be taken as a new emotion detection technique that concentrate on unpleasant feelings like panic emotion.