A Systematic Review on Advancement of Image Segmentation Techniques for Fault Detection Opportunities and Challenges
Md. Motiur Rahman, Saeka Rahman, Smriti Bhatt, Miad Faezipour
Abstract
Fault and defect detection are critical for ensuring the safety, reliability, and quality of products and infrastructure across various industries. As traditional manual inspection methods face limitations in efficiency and accuracy, advancements in artificial intelligence, particularly image segmentation, have paved the way for automated and precise fault detection processes. A significant gap exists in current research regarding the integration and comparative analysis of classical and modern segmentation approaches across diverse application domains. This study addresses this gap by providing a systematic review that bridges traditional segmentation techniques with cutting-edge deep learning methodologies. Unlike previous reviews that focus solely on isolated techniques or specific domains, this paper offers a holistic analysis of methodological innovations, application breadth, and emerging trends. Emphasis is placed on the integration of deep learning models, hybrid approaches, and advancements like attention mechanisms and lightweight architectures. Additionally, the review highlights critical challenges and proposes future research directions aimed at enhancing model scalability, robustness, and adaptability. This systematic review addresses gaps in the field and provides useful insights for academia and industry, making it a key reference in fault detection using image segmentation.