APPLICATION OF DEEP LEARNING AND NEURAL NETWORK IN OBJECT IDENTIFICATION

(CASE STUDY OF VERITAS UNIVERSITY CHAPEL)

Abstract

This study examines the design and implementation of an intelligent object identification system leveraging deep learning and neural networks, with a focus on Veritas University Chapel as the case study. Traditional surveillance systems in such spaces face limitations in accuracy, adaptability, and real-time response. By utilizing YOLO v8, OpenCV, and Python, this study develops a robust framework capable of real-time monitoring, high detection accuracy, and scalability for diverse security needs. The research demonstrates that deep learning provides a significant improvement over conventional methods by enabling automated detection of objects in complex environments. Findings indicate reduced false positives/negatives and enhanced adaptability to lighting and occlusion challenges. The work contributes to academic discourse on AI-driven security systems and proposes directions for future research, including improved robustness, cross-domain applications, and blockchain integration for secure data management.