|
Author | Proposed method | Dataset | Evaluation |
|
Sulochan [25] | Multiscale wavelet features and fuzzy C-means clustering | Real and computer-simulated fabric images | Detection error rate |
|
Vermaak et al. [26] | Dual-tree complex wavelet transform (DTCWT) | TILDA dataset | Detection success rate |
|
Liu and Zheng [27] | The method based on information entropy and frequency domain saliency | Database created by the research associate of the industrial automation research laboratory | ACC, true positive rate(TPR), false positive rate(FPR), positive predictive value (PPV), negative predictive value (NPV), time, F-measure |
|
Di et al. [28] | L0 gradient minimization method and two-dimensional fractional Fourier transform (2D-FRFT) for obtaining the saliency map of the quaternion image | Dataset from automation laboratory fabric database of Hong Kong University | True positive (TP), false positive (FP), true negative (TN), and false negative (FN) |
|
Jing [29] | Gabor preprocessed golden image subtraction | Industrial automation laboratory at the University of Hong Kong and the TILD database | Detection success rate |
|
Mohammed and Alhamdani [30] | Fuzzy back propagation neural network (FBPNN) with Gabor features | Collected dataset | Detection success rate |
|
Yapi et al. [31] | Using learning-based local textural distributions in the contourlet domain | TILDA database | (TP, FP, TN, and FN) local precision (PL), local recall (RL), and local accuracy (ACCL) |
|