Skip to main content


Table 3 Texture features at quarter resolution

From: Optimizing automated characterization of liver fibrosis histological images by investigating color spaces at different resolutions

TA Method Greylevel RGB HSI
COM Sum Entropy G-Sum Entropy I _ Contrast
  Sum Variance G-Sum of Squares I _ Correlation
  Sum of Squares G-Sum Variance I _ Inverse Difference Moment
RLM Horizontal greylevel non-uniformity G_45° greylevel non-uniformity I _ Inverse Difference Moment
  Vertical greylevel non-uniformity G_ Horizontal greylevel non-uniformity I _ Vertical Run length non-uniformity
  45° greylevel non-uniformity G_ Vertical greylevel non-uniformity I _ Vertical Long Run Emphasis
WT E 3 G_E 2 I _E 2
  E 2 G_E 1 S_E 2
  E 1 G_E 3 I _E 1
  1. The texture features (parameters with the highest F-Coefficient) that discriminate between the C and F groups on greylevel-, RGB-, and HSI- schemes at quarter resolution images, using TA methods:COM, RLM, and WT.
  2. R_: Red, G_: Green, and B_: Blue channels. H_: Hue, S_: Saturation, and I _: Intensity. E s Energy calculated from the wavelets using various scales (s).