Figure 1
From: Quantification of arthritic bone degradation by analysis of 3D micro-computed tomography data
(a) Example of two CT slices (top row) segmented by the texture based approach (bottom row). The texture based approach was capable of identifying closely lying bones that are separated by tissue that is of higher intensity than the general background. (b) The filter bank used following Malik et al.32. The first 36 filters are Gabors with ϕ ∈ [0, π/2], θm ∈ [0, π/6, π/3, π/2, 2π/3, 5π/6], 
in all combinations. The last four are DoGs with paired standard deviations[σm, σn] ∈ {[0.075, 0.125], [0.125, 0.175], [0.175, 0.225], [0.225, 0.275]}.
