Table 5.
The quantitative examination of various segmentation strategies utilizing the (The satisfactory values are featured in strong face).
| Index | Image | Applied algorithm | Count of the clusters |
|||
|---|---|---|---|---|---|---|
| 3 | 5 | 7 | 9 | |||
| Davies–Bouldin | Average (310 images) |
Efficient GA [97] | 2.057389792 | 2.341342543 | 2.631067668 | 2.182999317 |
| Adaptive PSO [96] | 1.466742939 | 2.262712553 | 2.300312783 | 1.649374921 | ||
| Beam-ACO [95] | 1.49016067 | 1.906178838 | 2.109355593 | 1.852796881 | ||
| MCS method [98] | 2.125579881 | 2.355334741 | 1.756786889 | 1.832064307 | ||
| HHO method [99] | 1.615224562 | 1.702627053 | 2.204451965 | 2.647738311 | ||
| GWO approach [100] | 1.835247126 | 1.767716428 | 2.946051439 | 2.722753129 | ||
| Whale optimization [101] | 1.767607021 | 2.528863859 | 2.803699012 | 2.316640263 | ||
| Chimp optimization [102] | 2.415340941 | 2.350907067 | 2.433318413 | 2.553789173 | ||
| Neural network based segmentation [103] | 1.606792734 | 1.693970454 | 1.542606235 | 2.297489919 | ||
| SUFEMO (Proposed) | 1.421301735 | 1.812008792 | 1.687189337 | 1.502481616 | ||
| Xie–Beni Index | Average (310 images) |
Efficient GA [97] | 1.624786762 | 1.709276519 | 2.207538007 | 2.649905004 |
| adaptive PSO [96] | 1.849336068 | 1.786084272 | 2.948651807 | 2.735604899 | ||
| Beam-ACO [95] | 1.784413031 | 2.534017353 | 2.806131272 | 2.335561186 | ||
| MCS method [98] | 2.435244805 | 2.353755926 | 2.446036152 | 2.554270162 | ||
| HHO method [99] | 2.038041 | 2.334152 | 2.612432 | 2.9165278 | ||
| GWO approach [100] | 1.448495 | 2.246186 | 2.295493 | 2.631099 | ||
| Whale optimization [101] | 1.475947 | 1.904366 | 2.105878 | 2.833088 | ||
| Chimp optimization [102] | 2.107597 | 2.351055 | 2.754129 | 2.819813 | ||
| Neural network based segmentation [103] | 1.61375 | 1.683281 | 2.044525 | 2.595974 | ||
| SUFEMO (Proposed) | 1.628119075 | 1.697662119 | 2.246409944 | 2.310486157 | ||
| Dunn index | Average (310 images) |
efficient GA [97] | 1.326722693 | 2.295283281 | 2.334360301 | 2.013982282 |
| Adaptive PSO [96] | 1.517242172 | 1.803836769 | 1.405798931 | 1.331685373 | ||
| Beam-ACO [95] | 1.458856701 | 1.438020506 | 2.154291777 | 2.655296748 | ||
| MCS method [98] | 1.906901194 | 1.853224645 | 2.831798973 | 3.028592536 | ||
| HHO method [99] | 1.230797 | 1.306074 | 2.353937 | 2.016582 | ||
| GWO approach [100] | 1.726747 | 1.815292 | 1.9218 | 2.244343 | ||
| Whale optimization [101] | 1.459989 | 1.552861 | 2.455488 | 2.763597 | ||
| Chimp optimization [102] | 2.122828 | 1.66564 | 2.44328 | 2.732422 | ||
| Neural network based segmentation [103] | 2.546459 | 2.504361 | 2.362737 | 2.28769 | ||
| SUFEMO (Proposed) | 2.584698504 | 2.588595748 | 2.350004016 | 2.868974087 | ||
| index | Average (300 images) |
Efficient GA [97] | 0.48298906 | 1.855825929 | 1.935245603 | 1.513778012 |
| Adaptive PSO [96] | 2.199301495 | 2.028453938 | 2.538635827 | 2.158815625 | ||
| Beam-ACO [95] | 1.442986088 | 2.053681742 | 1.724977482 | 1.834309177 | ||
| MCS method [98] | 2.749255434 | 2.711009201 | 3.993628751 | 2.967283554 | ||
| HHO method [99] | 2.486583 | 2.864695 | 2.941107 | 1.92769 | ||
| GWO approach [100] | 2.517785 | 2.947065 | 2.855919 | 2.859128 | ||
| Whale optimization [101] | 2.954762 | 2.367244 | 2.728644 | 2.449435 | ||
| Chimp optimization [102] | 2.766324 | 2.521449 | 3.011658 | 2.969639 | ||
| Neural network based segmentation [103] | 2.849432 | 3.157295 | 3.77819 | 2.936146 | ||
| SUFEMO (Proposed) | 2.830809221 | 3.142069236 | 3.790172244 | 2.993016698 | ||