نوع مقاله : مقاله پژوهشی
نویسندگان
1 استادیار ، دانشگاه امام علی (ع)،تهران، ایران
2 دانشجوی دکتری، دانشگاه اصفهان ،اصفهان،ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Human face recognition by drones is necessary for various applications, such as surveillance, search and security. The previous methods for face recognition are highly sensitive to limitations such as height, angle and distance from the face. In this article, a new approach for face detection and identification by deep learning is presented. The proposed method is done in three steps. In the first step, images are zoned with the selective search algorithm. In the second step, a deep network is proposed for box refinement operation to identify the target boxes with high accuracy and speed. Actually, a two-class classification problem is performed by deep learning to locate faces. In the third step, the localized images are trained to the proposed deep network to perform face recognition. In the architecture of the proposed method, the properties of widely used deep networks are used in combination, and a quantitative comparison of the proposed method with new methods in terms of computational complexity shows that training the proposed model requires less execution time than other methods. In addition, the evaluation of the proposed method on the DroneFace dataset shows that for different distance and height from the target, the proposed method has an average face recognition rate of 75.9 and an average face recognition rate of 84.6. Therefore, the proposed method has higher accuracy and efficiency than the new methods in this field and can be used for surveillance and security applications.
کلیدواژهها [English]