This study explores the burgeoning field of human clothing detection in images through sophisticated deep-learning techniques. With humans prevalent in the majority of global imagery, accurately processing human-centric data is pivotal across diverse applications. Early research primarily focused on facial detection and localization, yet challenges persisted in recognizing nuanced features such as body clothing. Recent advancements have propelled automated human analysis into various domains, including medical diagnostics, sports analytics, entertainment, virtual fitting rooms, and fashion inventory management. The complexity of human clothing detection lies in the diverse shapes, styles, and variations inherent in attire. This study addresses this intricate task by employing image segmentation methodologies, targeting different modules such as upper body, lower body, and full-body coverage. Leveraging advanced deep learning architectures, notably the U2Net framework, our approach aims to achieve robust and precise segmentation of various clothing elements. By dissecting clothing components at a granular level, our methodology contributes to the broader landscape of computer vision, empowering applications with enhanced human-centric insights and functionalities. The accuracy is estimated to be at around 80%.