AI-Based Fabric Defect Detection Using Deep Learning Fabric quality inspection is a critical process in the textile industry to ensure defect-free products. Traditional manual inspection methods are timeconsuming, labour-intensive and prone to human error, especially in high-speed production environments. To address these limitations, this project proposes an AI-based fabric defect detection system using deep learning techniques. The system utilizes computer vision and Convolutional Neural Networks (CNNs) to automatically detect and classify defects in fabric images. The process includes image acquisition, preprocessing, dataset preparation, model training, and defect detection. The trained model analyses fabric images and identifies defects such as holes, stains, mis weaves, and broken yarns with high accuracy and consistency. Experimental results demonstrate that the proposed system significantly improves detection speed, accuracy, and reliability compared to traditional inspection methods. It reduces manual effort, minimizes material waste, and enhances overall product quality. The system can be integrated into real-time industrial production lines for automated quality control. In conclusion, the AI-based fabric defect detection system provides an efficient and intelligent solution for modern textile inspection and supports the advancement of smart manufacturing and Industry 4.0.