segment op• 数据种类:voxel → labels
• 调用: import fullseye as fs; fs.ledger.vol_watershed(vol, markers, mask=None)(要直接调用实现,import volops; volops.vol_watershed(vol, markers, mask=None);从台账取用则 ops3d.get("vol_watershed"))
标记控制的 3-D 分水岭分割(可选 —— scikit-image)。
> 以下的详细说明为原文 —— 摘要与标题已翻译。
Floods the volume from the labelled *markers* (an int volume, `0` = unset),
optionally restricted to *mask*. Delegates to
`skimage.segmentation.watershed` — treat *vol* as a landscape (e.g. a
gradient magnitude, or the negated distance transform for splitting touching
blobs). Returns an `int32 (D, H, W)` label volume.
Raises `ImportError with a clear pip install scikit-image` message when
the optional dependency is absent; the rest of this module needs only
numpy + scipy.
• 示例数据目录(下载 URL / 许可证) —— 2-D 用 skimage.data(BSD/公有领域)加合成图,3-D 给出真实数据源(Stanford/PDS 等)的下载 URL。
• 算子来历与参考文献 —— 该算子族所依据的研究/方法出处。
• molecule_atom_count — py -3.11 examples_3d/molecule_atom_count.py
labels 作为输入)fuse_to_voxel · vol_region_props
segment)region_growing · euclidean_cluster · plane_segmentation
*Provenance: volops.py — 3D 算子登记表。本条目由 tools/opdocs.py md 自动生成(请勿手工编辑)。*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.