A Defect Detection Algorithm of Denim Fabric Based on Cascading Feature Extraction Architecture
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denimfabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extractionarchitecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the largedataset ImageNet and uses its portability to train the defect detection classifier and the defect recognitionclassifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layerwere retrained and adjusted from of these two training models on the high-definition fabric defect dataset. Thelast step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and otherfeature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show thatthe defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increasedby 1–3 percentage points.
Abstract
Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denimfabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extractionarchitecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the largedataset ImageNet and uses its portability to train the defect detection classifier and the defect recognitionclassifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layerwere retrained and adjusted from of these two training models on the high-definition fabric defect dataset. Thelast step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and otherfeature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show thatthe defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increasedby 1–3 percentage points.
참고문헌 (10)
- Y. Ding, "Fabric image defect detection based on fission particle filter algorithm", Textile Auxiliaries, 36(4), pp.60~64 (2019)
- S. Zhao, "Fabric defect detection algorithm based on two-stage deep transfer learning", Journal of Mechanical Engineering, 57(17), pp.86~97 (2021)
- Ning Lang, "Virtual-sample-based defect detection algorithm for aluminum tube surface", Measurement Science and Technology, 32(8), pp.085001~ (2021), IOP Publishing[DOI]
- Q. Xu, "Straw defect detection algorithm based on pruned YOLOv3", Proceedings of 20214th International Conference on Control and Computer Vision, pp.64~69 (2021)
- H. Y. Ngan, "Motif-based defect detection for patterned fabric", Pattern Recognition, 41(6), pp.1878~1894 (2008)
- Shuangbao Ma, "An Improved Defect Detection Algorithm of Jean Fabric Based on Optimized Gabor Filter", JIPS(Journal of Information Processing Systems), 16(5), pp.1008~1014 (2020), 한국정보처리학회[DOI]
- J. Luo, "Yarn-dyed fabric defect detection based on convolution neural network and transfer learning", Shanghai Textile Science & Technology, 47(6), pp.52~56 (2019)
- C. Li, "Fabric defect detection algorithm based on histogram of oriented gradient and low-rank decomposition", Journal of Textile Research, 38(3), pp.149~154 (2017)
- J. Zhou, "Unsupervised fabric defect segmentation using local texture feature", Journal of Textile Research, 37(12), pp.43~48 (2016)
- D. Yapi, "Automatic fabric defect detection using learning-based local textural distributions in the contourlet domain", IEEE Transactions on Automation Science and Engineering, 15(3), pp.1014~1026 (2018)