•  
  •  
 

Abstract

Facial recognition has become an invaluable and rapidly advancing technology that plays a crucial role in various daily applications. From identity authentication to video surveillance, mobile payment, and even law enforcement and security measures. Despite the remarkable progress, facial recognition is still a dynamic research field and confronts several challenges. One of the main challenges is the high variability in facial images due to factors like facial expressions, lighting conditions, aging, and the presence of accessories. Additionally, the computational complexity and the time concerns surrounding face recognition systems have raised considerations that need to be addressed. This research presents a new face recognition system that is quick, extremely accurate, and based on the inventive metaheuristic Coronavirus Optimization Algorithm. The major goal of the proposed system is to maximize the rate of recognition accuracy along with reducing the training time for security systems. The metaheuristic algorithm has been employed to optimize the features set and fine-tuning the parameter of the machine learning models. The proposed system has been evaluated on four facial datasets (i.e., MUCT, CASIA-WebFace, ORL, LFW). The experimental findings obtained from the provided system are compared with current methodologies and demonstrate that the suggested system achieves a high level of identification accuracy, while requiring little processing effort and complexity, even in uncontrolled conditions within accuracy in a range from 92.2% reaching up to 100%, and a training time from 657813.55 to 1.8 Millisecond.

Download

Share

COinS