Noise Estimation and Type Identification in Natural Scene and Medical Images using Deep Learning Approaches

Table 7

Performance of noise type identification for natural images and medical images.

	Gaussian	Motion	Poisson	Salt-and-pepper	Speckle	Average
(a) Performance of noise type identification for natural images^a
Precision	1.0	1.0	1.0	1.0	1.0	1.0
Recall	1,0	1.0	1.0	1.0	1,0	1.0
F1-score	1.0	1.0	1.0	1.0	1.0	1.0
Accuracy	1.0	1.0	1.0	1.0	1.0	1.0
(b) Performance of noise type identification for medical images^b
Precision	0.954	1.0	0.873	1.0	0.986	0.963
Recall	0.981	1.0	1.0	0.939	0.962	0.976
F1-score	0.967	1.0	0.932	0.965	0.974	0.977
Accuracy	0.955	1.0	0.873	1.0	0.986	0.963

^aThis shows the average precision, recall, F1-score, and accuracy is 1.0. ^bThis shows the average precision obtained is 0.963 and recall is 0.976. F1-score is 0.977 and accuracy is 0.963.