FULL PDF
Abstract
In an era of rapid digital transformation, organizations face challenges in managing large inventories of IT assets across distributed environments. Traditional asset management systems often rely on manual entry, leading to inaccuracies, inefficiencies, and limited scalability. This paper proposes a scalable framework that integrates computer vision and machine learning to automate the detection, classification, and tracking of IT assets in real time. Leveraging image-based recognition and predictive analytics, the proposed system enhances accuracy and reduces operational overhead. The framework is evaluated in simulated and real-world office environments, demonstrating improvements in asset visibility and management efficiency. By focusing on automation and scalability, this research addresses a critical need in modern IT infrastructure governance
View more >>