Self-Transfer Learning Network for Multicolor Fabric Defect Detection

This paper presented a self-transfer learning network (STLN) for multicolor fabric defect detection. Deep neural networks were adopted to detect defects in objects with complex backgrounds such as multicolored fabrics. It is noteworthy that the more disturbances there are on the object surface, the more difficult it is to optimize the network and the more training samples will be required. At the same time, the distinct difference in different types of multi-colored fabrics makes model difficult to apply data information. To this end, the STLN in this paper, consisting of a dataset expansion module, a dataset filtering module, a feature extraction module, a defect detection module, and a category discrimination module, used only limited raw data without the help of external data, and expanded the training set by mining the features of the raw data to better optimize the network. It is experimentally demonstrated that the STLN can achieve higher accuracy compared to deep neural networks for detecting defects of multicolor fabrics with insufficient target data.