# A Ceramic Rare Defect Amplification Method Based on TC-CycleGAN

## TL;DR

This paper introduces a new image augmentation method for rare ceramic defects using TC-CycleGAN, which improves image quality and detection accuracy.

## Contribution

A novel TC-CycleGAN framework optimized for ceramic defect augmentation with enhanced generator and discriminator structures.

## Key findings

- The proposed method reduced FID and KID values by up to 57% and 73% for specific defect types.
- Detection accuracy for rare defects increased by 1.2% and 3.9% using the augmented dataset.
- TC-CycleGAN outperforms existing methods in generating high-quality ceramic defect images.

## Abstract

The ceramic defect detection technology based on deep learning suffers from the problems of scarce rare defect samples and class imbalance. However, the current deep generative image augmentation techniques are limited when applied to the task of augmenting rare ceramic defects due to issues such as uneven image brightness and insufficient features of small-sized defects, resulting in poor image quality and limited improvement in detection results. This paper proposes a ceramic rare defect image augmentation method based on TC-CycleGAN. TC-CycleGAN is based on the CycleGAN framework and optimizes the generator and discriminator structures to make them more suitable for ceramic defect features, thereby improving the quality of generated images. The generator is TC-UNet, which introduces the scSE and DehazeFormer modules on the basis of UNet, effectively enhancing the model’s ability to learn the subtle defect features on the ceramic surface; the discriminator is the TC-PatchGAN architecture, which replaces the original BatchNorm module with the ContraNorm module, effectively increasing the discriminator’s sensitivity to the representation of tiny ceramic defect features and enhancing the diversity of generated images. The image quality assessment experiments show that the method proposed in this paper significantly improves the quality of generated defective images. For the concave type images, the FID and KID values have decreased by 49% and 73%, respectively, while for the smoke stains type images, the FID and KID values have decreased by 57% and 63% respectively. The further defect detection experiments results show that when using the data set expanded by the method in this paper for training, the recognition accuracy of the detection model for rare defects has significantly improved. The detection accuracy of the concave and smoke stains types of defects has increased by 1.2% and 3.9% respectively.