Table 8.

Summarizes the metrics used for assessing the performance of different tasks performed by an ML/DL model.

Image enhancement	PSNR		SSIM		MSE		MAXERR		L2rat
Segmentation	Intersection over Union (IOU)			Dice Coefficient		Pixel accuracy
Classification	Sensitivity	Specificity	Accuracy	Precision		F1-score		AUC-ROC Curve
Fairness	Demographic Parity	Equalized odds	Degree of bias	Disparate impact	Predictive Rate Parity	Equal opportunity	Treatment Equality	Individual Fairness	Counterfactual fairness
Image captioning	BLEU		METEOR		ROGUE-L		CIDEr	SPICE