Table 10.
Methods and results used in studies with Figshare dataset
| References | Feature extraction | Model | Accuracy (%) |
|---|---|---|---|
| Cheng et al. [18] | Bag of words | SVM | 91.28% |
| Cheng et al. [19] | Local features using Fisher Vector | SVM | 94.68% |
| Abir et al. [20] | GLCM | PNN | 83.33% |
| Deepak and Ameer [21] | GoogleNet | SVM | 97.10% |
| Afshar et al. [22] | Capsule networks (CapsNet) | − | 86.56% |
| Swati et al. [23] | Fine-tune VGG19 | − | 94.80% |
| Arı et al. [24] | AlexNet and VGG16 | ELM | 97.64% |
| Kaplan et al. [11] | nLBP ve LBP | KNN | 95.56% |
| Belaid and Loudini [25] | VGG16 | Softmax | 96.5% |
| Kaur and Gandhi [26] | Fine-tuned AlexNet | − | 96.95% |
| Rehman et al. [27] | VGG16 | Softmax | 98.69% |
| Deepak and Ameer [6] | CNN | SVM | 95.82% |
| Bodapati et al. [28] | Xception and InceptionResNetV2 | Softmax | 95.23% |
| Sadad et al. [29] | NASNet | Softmax | 99.6% |
| Oksuz et al. [30] | ResNet18+ShallowNet | SVM | 97.25% |
| Ayadi et al. [31] | DSURF and HoG | SVM | 90.27% |
| MTAP model | CNN | Softmax | 99.69% |