المستخلص: |
Facial recognition is receiving great attention due to the need to face important challenges when developing real applications in restricted environments, and although the performance of face recognition has been greatly improved with the development of neural networks, this paper uses a technology based on biometric standard artificial intelligence that can uniquely identify people by analyzing patterns based on a person's facial features and shape. This paper aims to develop a model that achieves the recognition of faces, using convolution neural networks, and to improve the efficiency of the system for detecting images of faces compared with previous similar research, and that the model is applicable. This paper uses convolution neural networks in the numerical analysis of pictures of people, and helps in identifying them, calculating accuracy and error, and then comparing them with previous studies. this study is based on the use of an approach that can improve CNN models is training the network with faces, it is inspired by the fact that the human visual system explicitly ignores occlusion and focuses only on uncovered areas of the face. One of the most important Other deep learning techniques such as capsul network (capsnets) can be used, which are considered new and important designs regarding artificial neural networks, and also other algorithms can be used to identify the face is like the Automated Support Algorithm (CVM).
|