CEU-Net: ensemble semantic segmentation of hyperspectral images using clustering

Journal of Big Data

Table 12 Detailed classification test results for the Indian Pines Dataset in terms of Precision, Recall, and F1-Score. Testing was done with PCA 30 CEU-Net no-patching with a 75%/25% Training/Testing split

Class Labels	Precision	Recall	f1-score	Support
Alfalfa	0.70	0.70	0.70	10
Corn Notill	0.93	0.80	0.86	378
Corn Mintill	0.90	0.87	0.89	223
Corn	0.65	0.86	0.74	51
Grass Pasture	0.94	0.93	0.94	120
Grass Trees	0.91	0.99	0.95	174
Grass Pasture M	0.92	1.00	0.96	11
Hay Windrowed	0.97	0.97	0.97	110
Oats	1.00	1.00	1.00	3
Soybean Notill	0.87	0.92	0.90	246
Soybean Mintill	0.90	0.92	0.91	605
Soybean Clean	0.85	0.89	0.87	158
Wheat	0.96	1.00	0.98	43
Woods	0.94	0.97	0.95	301
Buildings etc.	0.83	0.65	0.73	103
Stone Steel Towers	1.00	1.00	1.00	27
Accuracy			0.90	2563
Macro Average	0.89	0.91	0.90	2563
Weighted Average	0.90	0.90	0.90	2563