Data Augmentation on Defect Detection of Sanitary Ceramics

In this paper, we propose four offline data augmentation methods to improve the performance of convolutional neural network(CNN) on defect detection of sanitary ceramics. In recent years, based on big data, deep learning has begun to become a popular way for sanitary ceramics defect detection. Comparing with traditional vision inspection system, deep learning method is more robust and convenient without manual design of feature extraction. As a data-driven detection way, data plays a vital roll, however, sometimes we could not obtain a high-quality and large dataset. Consequently, we consider data augmentation to improve the quality of original dataset. Here, we use image generation, image mosaic, image fusion and image rotation mosaic. According to the experiment results, with these methods, the enhanced datasets perform well compared with the original one.