Research Article
A Composite Model of Wound Segmentation Based on Traditional Methods and Deep Neural Networks
Table 2
Results of different models.
| | Model | mIoU (%) | MaxIoU(%) | Precision (%) |
| | Preprocess-1.0 | 85.3262 | 85.8030 | 94.9430 |
| | Raw-1.0 | 84.4080 | 84.8738 | 93.5520 |
| | Preprocess-0.5 | 84.2682 | 84.6251 | 94.2579 |
| | Raw-0.5 | 83.0970 | 83.5808 | 92.3514 |
| | Preprocess-0.25 | 82.0241 | 82.4051 | 92.9335 |
| | Raw-0.25 | 80.9700 | 81.3167 | 90.8778 |
| | PreAndPost-1.0 | 85.8823 | 86.4018 | 94.6906 |
|
|
