The Prague Texture Segmentation Datagenerator and Benchmark

The Prague Texture Segmentation Datagenerator and Benchmark - Algorithms

optimized
for

The concise description of algorithms contains hyperlinks to further information (author, algorithms details, BIB entry, WWW external page).

The algorithm features are: f1 = classification (supervised segmentation), f2 = hiearchy result (manual selection), f3 = known number of regions, f4 = [reserved].

huangyuan's
EWT-FCNT

f1: 1
f2: 0
f3: 0
f4: 0

Yuan Huang, Fugen Zhou, Jérôme Gilles: Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation

List of uploaded results for 'EWT-FCNT' algorithm

benchmark	label version	CS	OS	US	ME	NE	O	C	CA	CO	CC	I	II	EA	MS	RM	CI	GCE	LCE	BCE	GBCE	BGM	SC	SSC	VD	L	AVI	NVI	NMI	M	ARI	JC	DC	FMI	WI	WII	NBDE
Colour [normal] CL	EWT-FCNT	98.45	0.00	0.00	0.37	0.46	0.93	1.05	97.67	98.78	98.81	1.22	0.25	98.76	98.17	0.24	98.78	2.23	1.68	2.88	2.33	98.78	97.69	97.67	1.21	97.86	1.02	3.33	96.32	0.74	97.61	96.31	98.09	98.09	98.14	98.04	0.60
#Colour [normal] CL	EWT-FCNT-NR	98.11	0.00	0.00	0.49	0.46	1.16	1.56	97.01	98.43	98.46	1.57	0.33	98.40	97.65	0.28	98.42	2.85	2.23	3.63	3.02	98.43	97.08	97.01	1.57	97.28	1.31	4.24	95.30	0.99	96.84	95.17	97.47	97.48	97.53	97.43	1.71