Defect detection is a core process of filtering unqualified products. By using Machine Learning or Deep Learning, we can train the model to detect the defect on fabric surface automatically. A fabric defect corresponds to a flaw on the manufactured fabric surface. In particular, fabric defects result from processes such as machine defects, faulty yarns, machine spoils and extreme stretching, etc.
Detecting defects is an integral part of any manufacturing process. Most works still utilize traditional image processing algorithms to detect defects owing to the complexity and variety of products and manufacturing environments. In this paper, we propose an approach based on deep learning which uses CNN for extraction of discriminative features. It can detect different defects without using any defect samples during training.
Fabric defect detection plays an important role in ensuring quality control in the textile manufacturing industry. This study introduces a fabric defect detection method based on a convolutional neural network (CNN) to improve accuracy and time efficiency. For detection accuracy, the CNN is constructed to obtain different scales of feature maps, which enhance the representation of tiny scale fabric defects. A faster defect locating method is designed with pre-known size information obtained by clustering analysis to reduce the computation time. An experiment is carried out for illustrating that the accuracy of CNN for each defect reaches over 92%,
and the frames per second (FPS) is more than 29. Further analysis results demonstrate that the proposed CNN can accurately detect the fabric defects with a tiny scale, and the speed of detection can reach 30 m/min to satisfy the industrial requirements.
The automatic textile fabric defect detection technology based on computer vision has attracted great attention. With the development of new object detection algorithms, computational capabilities, and sensor technology, computer-vision based textile defect detection techniques will continue to evolve at a high speed. The creation of innovative technologies could make low-cost, reliable flaw detection an actuality for the textile industry.
In the future, the few-shot learning method will be used in CNN to lower the demand for fabric images, which will use less data to train useful detection model. In addition, the more complicated fabrics and different structures of CNN will be investigated in further research to extend the types of fabrics we can detect.
Textile_Defect_Detection Ⓒ2022 By Pallavi-star2002