Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 2 Texture features at half resolution

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

TA Method Greylevel RGB HSI
COM Sum of Squares G_ Sum of Squares I _ Inverse Difference Moment
  Sum Entropy R_ Sum of Squares S_ Sum of Squares
  Sum Variance G_ Sum Entropy I _ Correlation
RLM Vertical greylevel non-uniformity G_45° greylevel non-uniformity I _Vertical Long Run Emphasis
  Horizontal greylevel non-uniformity G_ Horizontal greylevel non-uniformity I _ Vertical Fraction
  45° greylevel non-uniformity G_135°greylevel non-uniformity I _ Vertical Run length non-uniformity
WT E 3 G_E 3 I _E 3
  E 1 G_E 3 I _E 3
  E 3 G_E 4 I _E 2
  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 half 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).