Texture Classification Using Scattering Statistical and Cooccurrence Features

Table 4

Results of texture classification using scattering transform, ridgelet transform, and wavelet transform for 129 VisTex images (with 2580 image regions, Dataset-4).

Dataset-4	Feature vectors
	F1	F2	F3	R1 [8]	R2 [8]	R3 [8]	W1	W2	W3
Mean success rate (%)	85.81	73.99	85.23	72.79	71.40	86.16	81.40	76.36	81.43
Number of image regions correctly classified	2214	1909	2199	1878	1842	2223	2100	1969	2101

F1 = SSFs (mean and standard deviation); F2 = SCFs (cluster prominence, cluster shade, contrast, and local homogeneity); F3 = F1 + F2; R1 = RSFs (mean and standard deviation); R2 = RCFs (cluster prominence, cluster shade, contrast, and local homogeneity); R3 = R1 + R2; W1 = WSFs (mean and standard deviation); W2 = WCFs (cluster prominence, cluster shade, contrast, and local homogeneity); W3 = W1 + W2.