|
| Author | Dataset | Performance evaluation criteria | Proposed model and purpose |
|
| Ismail et al. [43] | 50 original and 50 fake fabric samples, total 100 fabric samples are tested which consist of Arsenal, Manchester United, Italia, Chelsea, and Liverpool brand | Magnitude and phase graph are used to compare the results of test samples with the original sample | Proposed fast Fourier transformation (FFT) to investigate the originality of the sport jersey fabric and inspect Fourier transformation spectrum to detect the authenticity of the fabric |
| Hu et al. [44] | Two groups, c1r1 and c1r3, from the TILDA textile dataset have been used | False-positive rate (FPR), true-positive rate (TPR), and accuracy (Acc) | Proposed an unsupervised method that combines discrete Fourier transform (DFT) and discrete wavelet transform (DWT) |
| Sakhare et al. [45] | The database that includes four types of defects: missing warp, missing weft, hole, and tom out are used | The percentage accuracy has been used | Proposed two domain techniques: spatial and spectral for the detection and classification of defects |
| Zhang et al. [46] | Not explicitly mentioned | Similarity measure has been used to recognize the defective and defect-free units | Presented a method based on frequency domain filtering, similarity measurement, and distance matching function for the detection of defects in yarn-dyed fabric |
|
