Spectral-Spatial Hyperspectral Image Classification Based on Homogeneous Minimum Spanning Forest

Table 2

Information classes, number of training samples, and classification accuracy for SalinasA.

	No. of samples	No. of training samples	SVM	SVM-MSF	MC-MSF	RD-MSF	MSWMF-MSF	MSMMSF	Proposed Methods
									HMSF	HKNN-MSF-MV	F–HKNN-MSF-MV MSF
Brocoli_green_weeds_1	391	6	99.49	100	100	100	98.47	100	100	100	100
Corn_senesced; _green_weeds	1343	6	97.69	95.9	92.03	93.22	99.48	98.98	99.93	99.7	99.48
Lettuce_romaine_4wk	616	6	93.67	97.73	94.97	95.62	98.86	98.78	90.42	90.58	100
Lettuce_romaine_5wk	1525	6	99.93	100	100	100	99.28	100	99.8	100	100
Lettuce_romaine_6wk	647	6	99.11	99.55	100	100	98.22	100	100	100	100
Lettuce_romaine_7wk	799	6	96.62	100	100	100	99.12	100	99.25	99.75	99.87
AA (%)	—	—	97.75	98.86	97.83	98.14	98.9	99.62	98.23	98.33	99.89
OA (%)	—	—	96.69	98.65	97.42	97.79	97.63	99.48	98.71	98.8	99.85
Kappa coefficient (%)	—	—	96.33	98.04	96.82	97.36	97.11	99.4	98.38	98.5	99.81