tactile op• Data kinds: image → image
• Call: fullseye.apply(img, "tac_shear_field", a=0.5, b=0.5) (the 2-D model is one image plus two scalar knobs a,b∈[0,1])
*The figure is the real output on a synthetic 128×128 input. Left: input, right: output (a non-image return value is shown as the value itself).*
In-plane shear proxy from the 2-D structure tensor (Foerstner / Bigun-Granlund orientation coherence). The tensor `J = G_sigma(grad v * grad v^T) has eigenvalues l1 >= l2, and the coherence (l1-l2)/(l1+l2) = sqrt((J11-J22)^2 + 4*J12^2) / (J11+J22) is 1 where the gel texture is stretched into a single dominant orientation (as it is under tangential/shear load) and 0 where it is isotropic. The result is additionally weighted by the tensor trace (gradient energy) so that texture-free, un-contacted gel stays dark instead of amplifying noise orientation. a = tensor integration sigma (0.6..4.6), b` = output gain (0.5..2.5). Output clipped to [0,1], HxW; a constant frame has zero gradient energy and yields an all-zero shear field.
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
The program below has been verified to run (same input as the figure). In Studio's help this block becomes buttons that load and run it on the spot.
tac_shear_field 0.50 0.50
▸ Load this pipeline · Load & run
• sim2real_and_alife — py -3.11 examples/sim2real_and_alife.py
image as input)identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter
tactile)tac_contact_mask · tac_height_from_shading · tac_surface_normal · tac_pressure_proxy
*Provenance: ops.py — 2D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.