A Fast Recognition Method for Space Targets in ISAR Images Based on Local and Global Structural Fusion Features with Lower Dimensions

Table 7

Average classification accuracy of 8 fusion features with different dimensions in the 5 times 10-fold cross validation.

	T1_ LBP	T2_ LBP	T3_ LBP	T4_ LBP	T5_ LBP	T6_ LBP	T7_ LBP	T8_ LBP
3	0.887	0.953	0.956	0.922	0.935	0.916	0.864	0.801
6	0.951	0.968	0.963	0.955	0.963	0.976	0.971	0.948
9	0.972	0.970	0.956	0.981	0.982	0.983	0.980	0.960
12	0.975	0.982	0.949	0.983	0.982	0.982	0.979	0.965
15	0.970	0.985	0.967	0.989	0.989	0.988	0.987	0.967
18	0.987	0.986	0.968	0.994	0.986	0.986	0.991	0.966
21	0.991	0.988	0.982	0.991	0.986	0.986	0.990	0.974
24	0.993	0.988	0.990	0.991	0.987	0.988	0.994	0.972
27	0.994	0.994	0.988	0.990	0.992	0.991	0.993	0.971
30	0.994	0.989	0.990	0.987	0.988	0.995	0.995	0.972
33	0.993	0.988	0.991	0.992	0.990	0.991	0.995	0.986
36	0.992	0.993	0.990	0.989	0.988	0.994	0.996	0.978
39	0.996	0.989	0.990	0.986	0.991	0.989	0.993	0.980
42	0.994	0.991	0.990	0.989	0.991	0.989	0.994	0.980
45	0.993	0.991	0.990	0.990	0.992	0.990	0.993	0.982