2025/08/26 by Narayanan, P., Anantha
Engineering · Materials Science · #Industrial Vision Systems and Defect Detection #Collagen: Extraction and Characterization #Machine Learning in Materials Science
paper · doi:10.82374/jiei.2025.1216076
Automated inspection systems powered by deep learning are revolutionizing quality control in leather and footwear manufacturing by replacing subjective, time-consuming manual methods with objective, high-throughput solutions. This review presents a comprehensive analysis of deep learning-driven inspection approaches for defect detection in leather and footwear, covering both conventional image processing techniques and state-of-the-art architectures such as convolutional neural networks (CNNs), YOLO series models, and vision transformers. Key application areas include color prediction and sorting, leather species identification, and defect segmentation/classification, with emphasis on integration into real-time industrial workflows. The study examines how the adoption of AI-based inspection improves product quality compliance, reduces rejection rates, and enhances manufacturing competitiveness. It also highlights the transition toward Industry 4.0-aligned inspection systems and identifies current challenges such as dataset scarcity, small-defect detection limitations, and integration with high-speed production lines. Finally, the review proposes future research directions for developing adaptive, domain-specific deep learning models that support scalable, reliable, and sustainable leather and footwear production.