contour op• Data kinds: image2d × mask → table
• Call: import fullseye as fs; fs.ledger.chan_vese_energy(image, phi, *, mu: 'float' = 0.1, nu: 'float' = 0.0, lambda1: 'float' = 1.0, lambda2: 'float' = 1.0, eps: 'float' = 1.0, eta: 'float' = 0.1) -> 'Dict[str, float]' (to call the implementation directly, import segcontour; segcontour.chan_vese_energy(image, phi, *, mu: 'float' = 0.1, nu: 'float' = 0.0, lambda1: 'float' = 1.0, lambda2: 'float' = 1.0, eps: 'float' = 1.0, eta: 'float' = 0.1) -> 'Dict[str, float]'; from the registry, opssegmentation.get("chan_vese_energy"))
Chan–Vese 2001 energy F = μ Length + ν Area(inside) + λ1 ∫_in |I − c1|² + λ2 ∫_out |I − c2|² (two-phase) (chan_vese_energy).
> The detailed description below is the original text — the summary and the headings are translated.
`phi` は φ(内側 φ < 0)か bool のマスク(符号付き距離に直す)。正則化: 内側の重み H_ε(−φ)(論文の arctan 版)、
長さ = Σ δ_ε(φ) |Dφ|_η(前進差分、|Dφ|_η = √(D_x² + D_y² + η²))。c1 / c2 = 内 / 外の H_ε で重みづけた平均(式 (6)(7))。
同じマスクの「鋭い」版(`energy_sharp`)も返す: 長さ = 4 近傍で内外が変わる辺の数、内外は φ < 0 で 0/1。
返り値: `energy、length、area、fit_inside / fit_outside、c1 / c2`(H_ε で重みづけた平均 ——
ε = 1 の arctan は裾が長いので 2 値の画像でも 0/1 から離れる)、`energy_sharp、perimeter_sharp`、
`c1_sharp / c2_sharp`(φ < 0 の内外の平均)。
• halcon_segmentation family guide
• active_contours_and_level_sets — 変分・動的輪郭とレベルセット — どの輪郭がどこで止まり、何を保証するか
• 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.
• (none yet)
table as input)contour)snake_evolve · gvf_field · chan_vese_evolve · morph_chan_vese · morph_geodesic_ac · edge_stop_g · level_set_reinit · drle_evolve
*Provenance: segcontour.py — SEGMENTATION 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.