isc_match — CODEMATCH `match` op

• Data kinds: image2d × image2d → table

• Call: import fullseye as fs; fs.ledger.isc_match(image, template, direction='h', flat_thresh=0.01, min_valid=32) -> 'dict' (to call the implementation directly, import codematch; codematch.isc_match(image, template, direction='h', flat_thresh=0.01, min_valid=32) -> 'dict'; from the registry, opscodematch.get("isc_match"))

Usage

Increment sign correlation (ISC): returns the position where the largest fraction of increment signs agree.

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

r = (1/n) Σ [b_image == b_template](n は増分の数)。乱れた位置での期待値は 0.5、同じものなら 1 に近い。direction="h" は論文どおり行に沿った増分、"hv" は縦の増分も足す 2 次元の拡張。

狭義単調増加の明るさの変換(ガンマ・ゲイン・オフセット・任意の単調な表)で score_map は 1 ビットも変わらない。

テンプレートの増分のうち |Δ| > flat_thresh のものが min_valid に満たなければ ValueError(平坦なテンプレートは符号が雑音で決まり、位置を決めない)。既定の 0.01 は [0, 1] の明るさで 8 ビットの約 2.5 階調 —— これより小さい増分の符号は撮像の雑音と同じ桁で決まる。この判定はテンプレートだけを見るので、上の不変性を壊さない。拒否までの余裕は refusal_margin。

Detailed usage guide

• robust_code_matching 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.

Runnable examples (verified samples that actually call this op)

• poc_code_matching_breakdown — py -3.11 examples/poc_code_matching_breakdown.py

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

—

Same category (`match`)

ocm_match · scc_match

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

isc_match — CODEMATCH match op