xcv_grabcut — 2D `segmentation` op

• Data kinds: image → region

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

xcv_grabcut: 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

Automatic foreground/background separation via GrabCut (iterative graph cut).

> The detailed description below is the original text — the summary and the headings are translated.

画像中央 70%×70%の固定矩形を「たぶん前景」の初期領域として与え、

色分布の GMM とグラフカットで前景/背景を反復的に分離する

(`cv2.GC_INIT_WITH_RECT`)。「確実な前景」と「たぶん前景」の画素を

合わせて前景 region として返す。

`a` が反復回数を 2〜5 回の範囲で振る(多いほど収束するが遅い)。

`b` は未使用。矩形が画像中央固定のため、被写体が縁に寄っている

画像では抽出に失敗しやすい。

Detailed usage guide

• gallery2d_segmentation 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.

xcv_grabcut 0.50 0.50

▸ Load this pipeline · Load & run

Runnable examples (verified samples that actually call this op)

• gallery2d_segmentation — py -3.11 examples/gallery2d_segmentation.py

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

identity · reg_erode · reg_dilate · reg_open · reg_close · fill_holes · select_largest · remove_small

Same category (`segmentation`)

threshold · otsu · canny · adaptive_gauss_thresh · sk_otsu · sk_li · sk_yen · sk_sauvola

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

xcv_grabcut — 2D segmentation op