A novel segmentation method for uneven lighting image with noise injection based on non-local spatial information and intuitionistic fuzzy entropy

EURASIP Journal on Advances in Signal Processing

Table 1 Missclassfication rate (ME) obtained by the eight methods on images corrupted by addictive noise

ME	Gaussian noise	Bernsen’s method	Niblack’s method	Sauvola’s method	Bradley’s method	Chou’s method	Valizadeh’s method	Wei’s method	2D Otsu	FCM_NLS	2D WFPE	Our method
Rice	0.010	0.1718	0.3497	0.2225	0.3537	0.3502	0.2064	0.3307	0.0884	0.0462	0.0686	0.0284
Fingerprint	0.002	0.1386	0.1707	0.1758	0.1417	0.1751	0.1394	0.1023	0.2359	0.2091	0.3645	0.0644
Mouse	0.010	0.2897	0.2818	0.2341	0.2421	0.2852	0.2929	0.4277	0.5326	0.5184	0.5982	0.0471
Block	0.015	0.3246	0.5262	0.4734	0.4685	0.5254	0.5007	0.4637	0.1497	0.0815	0.1708	0.0089
License-plate	0.015	0.1348	0.2552	0.2264	0.2817	0.2549	0.2526	0.2042	0.0523	0.0487	0.0414	0.0258
Coin	0.010	0.2229	0.3704	0.3164	0.3540	0.3154	0.2813	0.3096	0.1925	0.2000	0.2017	0.1167