CNN-based fabric defect detection system on loom fabric inspection

Abstract

Fabric defect detection is generally performed based on human visual inspection. This method is not effective and it has various difficulties such as eye delusion and labor cost. To deal with these problems, machine learning, and computer vision-based intelligent systems have been developed. In this paper, a novel real-time fabric defect detection system is proposed. The proposed industrial vision system has been operated in real-time on a loom. Firstly, two fabric databases are constructed by using real fabric images and defective patch capture (DPC) algorithm. Thanks to the novel developed fast Fourier transform-based DPC algorithm, defective texture areas become visible and defect-free areas are suppressed, even on complex denim fabric textures. Secondly, an appropriate convolution neural networks (CNN) model integrated negative mining is determined. However, traditional feature extraction and classification approaches are also used to compare classification performances of deep models and traditional models. Experimental results show that our proposed CNN model integrated negative mining can classify the defected images with high accuracy. Also, the proposed CNN model has been tested in real-time on a loom, and it achieves 100% detection accuracy.