AUTOMATED DEFECT DETECTION IN FABRICS USING DEEP LEARNING MODELS

Fabric defect detection plays a crucial role in ensuring product quality in textile manufacturing. In this project, we propose a robust framework for fabric defect detection leveraging deep learning techniques, particularly Res-Net architecture. Our approach integrates preprocessing techniques for noise reduction and feature enhancement, followed by Res-Net-based convolutional neural networks for accurate defect classification. We conduct extensive experiments on benchmark datasets to validate the effectiveness of our proposed method.