Defective samples simulation through Neural Style Transfer for automatic surface defect segment
This addresses data scarcity in industrial defect segmentation, though it appears incremental as it builds on existing neural style transfer techniques.
The paper tackles the problem of limited defect samples in industrial quality inspection by proposing a neural style transfer-based simulation algorithm that generates synthetic defect samples for training segmentation models. Results show that a model trained only on generated simulation samples achieves an F1 score of 0.80, outperforming training with real samples.
Owing to the lack of defect samples in industrial product quality inspection, trained segmentation model tends to overfit when applied online. To address this problem, we propose a defect sample simulation algorithm based on neural style transfer. The simulation algorithm requires only a small number of defect samples for training, and can efficiently generate simulation samples for next-step segmentation task. In our work, we introduce a masked histogram matching module to maintain color consistency of the generated area and the true defect. To preserve the texture consistency with the surrounding pixels, we take the fast style transfer algorithm to blend the generated area into the background. At the same time, we also use the histogram loss to further improve the quality of the generated image. Besides, we propose a novel structure of segment net to make it more suitable for defect segmentation task. We train the segment net with the real defect samples and the generated simulation samples separately on the button datasets. The results show that the F1 score of the model trained with only the generated simulation samples reaches 0.80, which is better than the real sample result.