suspect op• Data kinds: labels2d × image2d → table
• Call: import fullseye as fs; fs.ledger.seg_boundary_membrane_gap(labels, membrane, tau: 'float' = 0.2, min_len: 'int' = 60, normalize: 'bool' = True, ignore_zero: 'bool' = True) -> 'dict' (to call the implementation directly, import emproof; emproof.seg_boundary_membrane_gap(labels, membrane, tau: 'float' = 0.2, min_len: 'int' = 60, normalize: 'bool' = True, ignore_zero: 'bool' = True) -> 'dict'; from the registry, opsemproof.get("seg_boundary_membrane_gap"))
> This operator's description has not been translated yet. The original text follows as it is.
分断の疑い: 隣接する 2 ラベルの境界画素のうち、膜応答が `tau` 未満の割合。隣接対ごとに 1 行。
細胞の境目には必ず膜(暗い線)がある。膜が無いのにラベルが変わる境界は、1 細胞を 2 つに切った
分断の跡(`seg_inject_split` の直線はまさにこれ)。4 近傍で異ラベルが接する画素を数え、境界の膜応答は
両側の強い方をとる。CREMI sample A の試作で人工分断 vs 他: AUC 0.99(tau 0.2、境界長 ≥ 60)。
列: `label_a / label_b(a < b)/ length / gap_fraction / membrane_mean`(gap_fraction 降順)。
`min_len` px 未満の短い境界は数えない(数画素の接触は膜の有無を言えない)。
>>> table = seg_boundary_membrane_gap(labels, seg_membrane_response(raw))
>>> table["label_a"][0], table["label_b"][0], table["gap_fraction"][0] # いちばん怪しい対
• 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.
• poc_em_second_opinion — py -3.11 examples/poc_em_second_opinion.py
table as input)—
suspect)*Provenance: emproof.py — EMPROOF 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.