A person may be automatically identified from an image or video source using a face recognition system. The work of facial recognition is accomplished by extracting facial characteristics from an image of the subject's face. The primary goal of video-based face recognition is to recognize a video face-track of renowned persons using a vast lexicon of fixed face images, while rejecting unfamiliar individuals. Current approaches detect faces by using probability models on a frame-by-frame basis, which is computationally costly when the data set is huge. For face identification and tracking in color images, a weighted Quantum Wolf Optimization is presented in this study. The suggested technique is compared to current approaches, and the test results show that superior categorization efficiency and high confident value are attained owing to little error.

Face Recognition, Video Face Tracking, WQWO, frame-by-frame, classification.