symmetry op• Data kinds: image2d × table → image2d
• Call: import fullseye as fs; fs.ledger.symmetry_difference_map(image, symmetry, exclusion_mask=None, detrend=True) (to call the implementation directly, import symmetry2d; symmetry2d.symmetry_difference_map(image, symmetry, exclusion_mask=None, detrend=True); from the registry, opsaoi.get("symmetry_difference_map"))
• GPU: none (CPU reference implementation only)
Returns a self-referenced difference map against an estimated reflection axis or rotation centre.
> The detailed description below is the original text — the summary and the headings are translated.
image : array-like, shape (H, W)
検査するグレー画像。
symmetry : dict
reflection_axis または rotational_symmetry の table。
exclusion_mask : array-like or None, default None
設計上の非対称を除外する H x W mask。True 部とその変換先をともに 0 にする。
detrend : bool, default True
True なら符号付き差から頑健な一次面を引き、線形な照明勾配を抑える。
numpy.ndarray
abs(image - transformed_image)。再標本化は線形補間で、最近傍は使わない。
定数入力、モデル種別不明、mask の形不一致は例外。自己参照なので欠陥は元位置と対称位置の対で現れ、軸上の欠陥や同じ欠陥が対称位置にもある場合は消える。一次面の除去は線形照明に限り、急な陰影や飽和は欠陥と区別できない。
• 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_symmetry_self_reference_inspection — py -3.11 examples/poc_symmetry_self_reference_inspection.py
image2d as input)flat_field_correct · register_image · tiled_map · center_from_symmetric_edges · reflection_axis · rotational_symmetry · symmetry_score
symmetry)center_from_symmetric_edges · reflection_axis · rotational_symmetry · symmetry_score
*Provenance: symmetry2d.py — AOI 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.