Automated Face Recognition System Using Convolutional Neural Network

The research is devoted to the development of an automated face recognition system based on a convolutional neural network (CNN). The proposed system uses modern methods of image pre-processing and classification, providing high accuracy and reliability of face recognition in various conditions. The CNN-based system model consists of two main blocks: geometric feature extractor and CNN feature classification. The scientific novelty of the work lies in the development of a comprehensive approach to creating an automated face recognition system based on convolutional neural networks, which includes effective methods of image pre-processing, feature extraction, and classification. The proposed methods allow increasing the accuracy and reliability of face recognition under different lighting conditions and other external influences. The practical significance of the work lies in the possibility of implementing the developed automated facial recognition system in various areas, such as security, access control, and mobile applications, which will ensure an increase in the level of security and ease of use of technologies. The proposed approaches can be used to improve existing facial recognition systems and develop new applications that require high accuracy and reliability.