Face Recognition from Video by Matching Images Using Deep Learning-Based Models

This paper explores the intersection of video recognition, computer vision, and artificial intelligence, highlighting its broad applicability across various fields. The research focuses on the applications, challenges, ethical dilemmas, and outcomes of artificial intelligence, which continues to grow in significance in the 21st century. We propose a systematic approach that incorporates models for face detection, feature extraction, and recognition. Our methodology includes the accurate segmentation of 100 human faces from video frames, with each face averaging 150x150 pixels. The feature extraction process yielded 1,000 face feature vectors, with an average size of 128, representing key characteristics for recognition. By applying a cosine similarity threshold of 0.7, we filtered irrelevant data and determined whether the two images matched. Our recognition system achieved 85% accuracy, demonstrating the effectiveness of the models and techniques employed. Additionally, ethical considerations were addressed, emphasizing the importance of data privacy, informed consent, cybersecurity, and transparency. This research advances the understanding of face recognition from video data and highlights the need for further exploration in this domain.