Discrete Generalized Inverted Exponential Distribution: Case Study Color Image Segmentation

Table 11

Comparison between developed method and other segmentation methods.

		DGIEMM	FSC	GMM	K-means		DGIEMM	FSC	GMM	K-means
I1	Accuracy	0.9951	0.9494	0.6259	0.6259	I4	0.9886	0.9086	0.9013	0.9515
	AR	0.9803	0.8068	0.9572	0.9134		0.9548	0.6679	0.6441	0.7422
	Hubert	0.9805	0.8078	0.8634	0.8886		0.9548	0.6679	0.6442	0.7141
	NMI	0.9574	0.7474	0.8373	0.8726		0.9208	0.6419	0.5919	0.6986
I2	Accuracy	0.9995	0.9880	0.8956	0.8956	I5	0.9998	0.9964	0.9899	0.5614
	AR	0.9978	0.9510	0.6224	0.6224		0.9993	0.9858	0.9600	0.0785
	Hubert	0.9979	0.9526	0.6260	0.6260		0.9993	0.9858	0.9601	0.0543
	NMI	0.9931	0.9076	0.5820	0.5820		0.9978	0.9691	0.9276	0.1884
I3	Accuracy	0.9913	0.9867	0.9280	0.9274	I6	0.9982	0.9928	0.8972	0.9198
	AR	0.9647	0.9468	0.7227	0.7206		0.9915	0.9666	0.6047	0.6251
	Hubert	0.9653	0.9476	0.7326	0.7306		0.9928	0.9716	0.6311	0.7240
	NMI	0.9306	0.8926	0.6554	0.6537		0.9762	0.9160	0.5463	0.6547