Table 7.
Comparing the classification efficiency of the proposed classifier with existing ones.
| Methods | Accuracy (%) | Precision (%) | Recall (%) | F1 score (%) |
|---|---|---|---|---|
| C-GAN DenseNet (Abbas et al., 2021) | 97.11 | 97 | 97 | 97 |
| CNN with transfer learning (Ahmad et al., 2021) | 99.69 | DNA | 99.40 | 99.62 |
| DCGAN-GoogleNet (Wu et al., 2020) | 94.33 | DNA | DNA | DNA |
| IBSA-Net (Zhang et al., 2023) | 99.4 | 98.9 | 99.3 | 99.1 |
| BotanicX-AI (Bhandari et al., 2023) | 98.28 | DNA | DNA | DNA |
| T-LSTM with an attention mechanism | 99.98 | 99.76 | 99.89 | 99.82 |
*DNA, Data not available.