Fabric Defect Detection in Textile Manufacturing: A Survey of the State of the Art

Table 4

Traditional machine learning algorithms for fabric defect detection.

Author	Proposed method	Dataset	Evaluation
Wang et al. [63]	Multiview stereo vision (MVS) and bag-of-features (BOF), K-nearest neighbor (KNN) algorithm	Collected dataset	Detection success rate
Priyanka and Manish [69]	Artificial neural networks (ANN)	Collected dataset	Detection success rate
Bumrungkun [70]	Snake active contour and support vector machines	Collected dataset	Recognition accuracy detection success rate
Zhang et al. [71]	L0 gradient minimization (LGM) and the fuzzy c-means (FCM) method to detect various fabric defects with diverse textures	Images from the automation laboratory sample database of Hong Kong University, TILDA textile texture database, and Guang Dong Esquel Textiles	ACC, TPR, FPR, PPV, and IOU (intersection over union)