Abstract:
Fabric defect detection intrigues but challenges. Due to the complexity of fabric textures and defects, many fabric defect detection methods are still suboptimal. This paper proposes a GAN-based fabric defect detection framework.
Considering real-world challenges, the proposed fabric defect detection system can learn existing fabric defect samples and automatically adapt to different fabric textures during different application periods. We customize a deep semantic segmentation network to detect different fabric defect types. We also trained a multistage GAN to generate reasonable defects in defect-free samples.
First, a texture-conditioned GAN is trained to investigate defect distributions given different texture backgrounds. We generate reasonable defective patches from a novel fabric. Next, a GAN-based fusion network places the defects.
Finally, the well-trained multistage GAN updates fabric defect datasets and fine-tunes the semantic segmentation network to better detect defects under different conditions. Our proposed method is tested on representative fabric samples.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
