create_ncc_model — MV `detect` op

• Data kinds: image2d → table

• Call: import fullseye as fs; fs.ledger.create_ncc_model(template) -> 'dict' (to call the implementation directly, import matching; matching.create_ncc_model(template) -> 'dict'; from the registry, opsmv.get("create_ncc_model"))

• HALCON equivalent: create_ncc_model (the HALCON reference is a useful guide to its meaning and parameters)

• GPU: none (CPU reference implementation only)

Usage

Prepare an NCC model (a normalized template).

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

Args:

template: 2次元の有限値テンプレート。呼び出し元と独立した

float64 コピーを保持する。

Returns:

中心化・単位ノルム化済みテンプレートと準備時の template_scale、整数の template_scale_exp を持つモデル。最大絶対値の2進指数が -500 未満または 500 超、すなわち 2**-500 未満または 2**501 以上のとき、有限な正の 2のべき乗で拡大縮小して norm を計算する。有限の非定数テンプレートは倍率によらず自己一致が 1（誤差 1e-12 以下）になり、1e-200 と 1e200 の混在も含む。最大値と最小値が等しい定数テンプレートは constant=True、norm=0、t0n が全ゼロとなり、すべての窓にスコア0を返す。

空の入力(template が 0 要素)は ValueError。

Raises:

FsValueError: template が NaN または無限大を含む場合。

Detailed usage guide

• machine_vision_classics 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)

• machine_vision_tour — py -3.11 examples/machine_vision_tour.py

• poc_real_stereo_multiscanline — py -3.11 examples/poc_real_stereo_multiscanline.py

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

map_image · rectify_to_world_plane · change_radial_distortion_image · find_ncc_models · run_bg_esti · give_bg_esti · update_bg_esti · classify_class_gmm

Same category (`detect`)

points_lepetit · find_ncc_models

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

create_ncc_model — MV detect op