tf_steerable_filter — 2D `edges` op

• Data kinds: image → image

• Call: fullseye.apply(img, "tf_steerable_filter", a=0.5, b=0.5) (the 2-D model is one image plus two scalar knobs a,b∈[0,1])

tf_steerable_filter: 入力 → 出力

*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).*

Usage

steerable_filter: oriented first-derivative-of-Gaussian response.

The steerable G1 basis: the derivative of a Gaussian at orientation

`theta = a*pi is cos(theta)*Gx + sin(theta)*Gy` where Gx, Gy are the

x/y partial derivatives of the Gaussian-smoothed image. `b` sets the

Gaussian sigma. The signed response is mapped to [0,1] (0.5 = zero), so its

deviation from 0.5 peaks on edges whose gradient matches `theta`.

Detailed usage guide

• gallery2d_edges family guide

References (sample data, literature)

• 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 canonical algorithm (author, year) and its uses are named in the family usage guide above.

Try it in Studio

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.

tf_steerable_filter 0.40 0.50

▸ Load this pipeline · Load & run

Runnable examples (verified samples that actually call this op)

• gallery2d_edges — py -3.11 examples/gallery2d_edges.py

Ops the type connects to (they accept `image` as input)

identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter

Same category (`edges`)

sobel_mag · prewitt_mag · roberts_mag · dog · grad_dir · log · corner_response · sk_scharr

*Provenance: ops.py — 2D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

tf_steerable_filter — 2D edges op