ABSTRACT
Defect detection to control the quality of fabrics is one of the key tasks in the production process of fabrics. Although significant progress has been made in the research of fabric defect detection, while traditional methods are still difficult to cope with complex and variable defect shapes. In order to solve these problems, this paper proposes an adaptive fabric defect detection method based on DenseNet-SSD algorithm to improve the performance of fabric defect detection. This method uses the DenseNet network to replace the backbone network VGG16 in the SSD algorithm, which strengthens the transfer between feature maps, alleviates the problem of gradient disappearance and reduces the number of network parameters. Compared with SSD, it improves network detection accuracy and real-time performance. The accuracy in the test set is 78.6mAP and the detection speed is 61FPS.
- Ngan, H., Pang, G., and Yung, N. 2011. Automated fabric defect detection-A review. Image and Vision Computing. 29, 7(Jun. 2011), 442--458. DOI=https://doi.org/10.1016/j.imavis.2011.02.002.Google ScholarDigital Library
- Castellini, C., Francini, F., Longobardi, G., and et al. 1996. On-line textile quality control using optical Fourier transforms. Optics and Lasers in Engineering. 24, 1 (Jan. 1996), 19--32. DOI=https://doi.org/10.1016/0143-8166(95)00044-o.Google ScholarCross Ref
- Mak, K. L., and Peng, P. 2008. An automated inspection system for textile fabrics based on Gabor filters. Robotics and Computer-Integrated Manufacturing. 24, 3 (Jun.2008), 359--369. DOI=https://doi.org/10.1016/j.rcim.2007.02.019.Google ScholarDigital Library
- Lan, Y. J., and Zhong, S. C. 2015. Defect detection of eyelet fabric using adaptive image segmentation based on region growing method. Journal of Mechanical & Electrical Engineering. 32, 11 (Nov. 2015), 1513--1518. DOI=10.3969/j.issn.1001-4551.2015.11.024.Google Scholar
- Zhao, Z. Y., Ye, L., Sang, H. S., and et al. 2019. Application of deep learning in fabric defect detection. Foreign Electronic Measurement Technology. 38, 8 (Aug. 2019), 110--116. DOI=10.19652/j.cnki.femt.1901468.Google Scholar
- Wu, Z. Y., Zhuo, Y., Li, J., and et al. 2018. A Fast Monochromatic Fabric Defect Fast Detection Method Based on Convolution Neural Network. Journal of Computer-Aided & Computer Graphics. 30, 12 (Dec. 2018), 2262--2270. DOI=10.3724/SP.J.1089.2018.17173.Google Scholar
- Zhou, J., Jing J. F., Zhang, H. H., and et al. 2020. Real-time Defect Detection Method of Fabric Based on S-YOLOV3. Laser & Optoelectronics Progress. (July 13, 2020), 1--14.Google Scholar
- Liu, W., Anguelov, D., Erhan, D., and et al. 2016. SSD: Single Shot MultiBox Detector. In Proceedings of the 14th European Conference on Computer Vision (The Amsterdam, The Netherlands, October 08-16, 2016). 21--37. DOI=https://doi.org/10.1007/978-3-319-46448-0_2.Google Scholar
- Huang, G., Liu, Z., Laurens, V. D. M., and et al. 2017. Densely Connected Convolutional Networks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (The Hawaii, The America, July 21-26, 2017). IEEE Computer Society, Washington, DC, USA. DOI=https://doi.org/10.1109/cvpr.2017.243.Google Scholar
Index Terms
- Research on Fabric Defect Detection Based on Deep Fusion DenseNet-SSD Network
Recommendations
Fabric defect detection algorithm based on YOLOv3 Transfer learning
ICFEICT 2021: International Conference on Frontiers of Electronics, Information and Computation TechnologiesFabric defect detection is an important part of controlling the quality of fabrics. Aiming at the low accuracy of manual detection methods and the difficulty of manual feature extraction in traditional machine learning methods, a transfer learning ...
Fabric Defects Detection based on SSD
ICGSP '18: Proceedings of the 2nd International Conference on Graphics and Signal ProcessingIn this paper, Fabric defect detection is a challenging task because of the complex texture. Deep learning technology provide a promising solution. As a kind of deep learning object detection model. Single Shot Multibox Detector(SSD)achieves good ...
Real-time Fabric Defect Detection based on Lightweight Convolutional Neural Network
ICCPR '19: Proceedings of the 2019 8th International Conference on Computing and Pattern RecognitionFabric defect detection is an important link for quality control in a textile factory. Deep convolutional neural network (CNN) has made great progress in the field of target detection, and has proven applicable in fabric defect detection. However, the ...
Comments