Language: 日本語 / English column in the table.
この表は手で書いていません。tools/gen_maturity.py が能力ノート・例の台帳・
門の実体・tests/ の中身から数えて出します。tests/test_maturity.py が
コミット済みの内容と生成物を突き合わせるので、古びると CI が落ちます。
This ledger is generated, not written. Each row’s status is derived from facts in the repository — which operators have tests, which linked examples an actual gate executes, and whether that example is driven by real measured data.
| 段 | 意味 | Meaning |
|---|---|---|
research-prototype |
実装はあるが、名指しの op に試験が揃っておらず、走る例も無い | Implemented, but not every named operator is exercised by a test and no linked example is executed by a gate. |
verified-synthetic |
真値を持つ合成データで自動検証済み(名指しの op 全部に試験があるか、走る例がある) | Automatically verified against ground truth that is synthesised or computed in closed form. |
validated-public-real-data |
公開された実写・実測データを使う例が、門で実際に走っている | At least one linked example that runs in CI is driven by real, publicly available measured data. |
validated-hardware |
実機センサ・装置で検証済み(★CI に実機は無い。外部の実機検証報告を保守者が受理し、昇格規則を満たしたときだけ出る) | Validated against physical sensors or instruments. CI has no hardware, so this is emitted only from accepted external reports that meet the promotion rules (docs/VALIDATION_CONTRIBUTING.en.md). |
★ validated-hardware は repo の中の事実からは出ません。 CI に実機センサが
無いからです。出る道は 1 本だけで、実機・実データを持つ人の検証報告を保守者が
受理して docs/validation_reports.json に記録し、昇格規則を満たしたときです。
データを外に出せない場合も、結果の数値だけで報告できます。
Fullseye is developed without physical measurement rigs, so CI can only verify against synthetic or computed ground truth. If you have real hardware or real data, your results can move a capability up this ladder — results-only reports (data kept private) count too: report form · how reports are judged · 日本語
| 能力 | Capability | 分類 | 段 | op(名指しの試験/全) | 例(走る門) |
|---|---|---|---|---|---|
| 位置を合わせて重ねる | Align and stack | 組み立てる | verified-synthetic |
4/4 | poc_astro_photometry synthetic → tests/test_poc_scripts_run.pypoc_registration_basin synthetic → tests/test_poc_scripts_run.py |
| 配列で方向を測り、距離と速度を分ける | Beamform for direction, separate range from velocity | 波と信号 | verified-synthetic |
4/4 | poc_multibeam_bathymetry synthetic → tests/test_poc_scripts_run.pypoc_bev_sensor_fusion synthetic → tests/test_poc_scripts_run.py |
| うなりは一つ(膜のモード・干渉縞・回折次数・印刷のモアレ・墨に落とす) | One beat (membrane modes, fringes, diffraction orders, print moire, and turning tone into ink) | 波と信号 | verified-synthetic |
12/12 | poc_beats_fringes_and_screens synthetic → tests/test_poc_scripts_run.py |
| 領域を切り出して、選んで、数える | Segment regions, select them, and count | 見つける | validated-public-real-data |
5/5 | poc_cell_counting synthetic → tests/test_poc_scripts_run.pypoc_particle_sizing synthetic → tests/test_poc_scripts_run.pypoc_real_coin_metrology real → tests/test_poc_scripts_run.pypoc_dense_bubble_count real → tests/test_poc_scripts_run.py |
| 平面ターゲットの多視点から内部行列 K を推定する(Zhang 法) | Estimate the camera intrinsic matrix K from multiple planar views (Zhang) | 測る | verified-synthetic |
4/4 | camera_intrinsics_calibration synthetic → tests/test_example_scripts_run.py |
| クロマティック共焦点変位センサ(硝材の分散 → 較正表 → 戻りスペクトル → 高さ・厚さ) | Chromatic confocal displacement sensor (glass dispersion, calibration table, return spectrum, height and thickness) | 光と色 | verified-synthetic |
6/6 | poc_chromatic_confocal synthetic → tests/test_poc_scripts_run.py |
| 色を測る(XYZ / Lab / 色差) | Measure colour (XYZ / Lab / colour difference) | 光と色 | verified-synthetic |
4/4 | poc_white_balance synthetic → tests/test_poc_scripts_run.pypoc_pigment_unmixing synthetic → tests/test_poc_scripts_run.py |
| 複素平面を「面」で見る(位相彩色・吸引域・脱出時間・翼まわりの流れ) | Seeing the complex plane as an area (domain colouring, basins, escape time, flow) | 測る | verified-synthetic |
8/8 | poc_complex_plane_fields synthetic → tests/test_poc_scripts_run.py |
| 周期パターンが標本化格子で折り返す距離と、縞の上で狂う衝突時間を閉形式で測る(複眼・検査カメラ) | The distance at which a periodic pattern aliases on a sampling lattice, and the time-to-contact that stripes corrupt — in closed form (compound eyes and inspection cameras) | 測る | verified-synthetic |
8/8 | poc_zebra_stripes_fly_eye synthetic → tests/test_poc_scripts_run.py |
| 多重反射・多重散乱・反復を収束まで回す —— 収束した証拠と残りの誤差を返し、収束しなければ値を出さない | Run inter-reflections, multiple scattering and iterations to convergence — return the evidence and the remaining error, and no value when it did not converge | 光と色 | verified-synthetic |
6/6 | converge_tour synthetic → tests/test_example_scripts_run.py |
| 圃場の RGB から作物と雑草を色と肌理で分け、雑草の被度を宣言した境で段階にする(学習器なし) | Separating crop from weeds in field RGB by colour and texture, and grading weed cover at declared edges (no learned network) | 見つける | validated-public-real-data |
5/5 | poc_weed_rice_ratio real → tests/test_poc_scripts_run.py |
| X 線の 2 つのエネルギーで厚みと材質を分ける(デュアルエナジー / フォトンカウンティング: スペクトル → 窓 → 基底分解 → 実効 Z) | Separate thickness from material with two X-ray energies (dual-energy and photon-counting X-ray: spectrum, energy windows, basis decomposition, effective Z) | 見つける | verified-synthetic |
15/15 | poc_dual_energy_xray synthetic → tests/test_poc_scripts_run.py |
| カメラのデータシートの数を EMVA 1288 の手順で測り直し、カメラの中の前処理がその数をどれだけ動かすかを見る(Linear と General) | Re-measure a camera’s datasheet numbers with the EMVA 1288 procedure, and see how much in-camera processing moves them (Linear and General) | 測る | verified-synthetic |
13/13 | poc_emva1288_sensor synthetic → tests/test_poc_scripts_run.pypoc_emva1288_in_camera_processing synthetic → tests/test_poc_scripts_run.py |
| 本来まっすぐな線から歪み係数を推定する(plumb-line、チェッカー不要) | Estimate lens distortion coefficients from straight lines (plumb-line, no board) | 測る | verified-synthetic |
4/4 | estimate_lens_distortion synthetic → tests/test_example_scripts_run.py |
| 光ファイバとライトガイド(ガラスの分散 → LP モード → モード径 → 照明の効率) | Optical fibres and light guides (glass dispersion, LP modes, mode field diameter, illumination efficiency) | 光と色 | verified-synthetic |
7/7 | poc_fiber_light_guide synthetic → tests/test_poc_scripts_run.py |
| 結果を人が読める図にする | Turn results into figures people can read | 見せる | verified-synthetic |
3/3 | poc_colormap_readability synthetic → tests/test_poc_scripts_run.pypoc_dem_terrain synthetic → tests/test_poc_scripts_run.py |
| 画像の中の文字を、正しい文字列に合わせて直す | Fix the text inside an image against the string it should read | 見つける | verified-synthetic |
1/11 | fix_text_in_image synthetic → tests/test_example_scripts_run.pypoc_glyph_typo_detection synthetic → tests/test_poc_scripts_run.py |
| フーリエ・タイコグラフィ(LED の斜め照明の像の組 → 位相回復で高 NA の振幅と位相、収束しなければ拒否) | Fourier ptychography (oblique LED illumination, phase retrieval to a high-NA amplitude and phase, refused unless it converges) | 測る | verified-synthetic |
6/6 | poc_fourier_ptychography synthetic → tests/test_poc_scripts_run.py |
| 地球規模の座標に載せる(ECEF・高さの基準・局所 ENU) | Put measurements on the Earth (ECEF, height frames, local ENU) | 測る | validated-public-real-data |
8/8 | poc_geodetic_height_frames synthetic → tests/test_poc_scripts_run.pypoc_geodetic_benchmarks_real real → tests/test_poc_scripts_run.pydem_geodesy_tour synthetic → tests/test_example_scripts_run.py |
| 基準画像(ゴールデン)と比べて欠陥を測り、ロットごと判定する | Compare against a golden image — align, diff, count defects, judge the lot | 組み立てる | verified-synthetic |
7/7 | golden_compare synthetic → tests/test_example_scripts_run.py |
| 良品を並べて「いつもと違う」を言う(良品統計の変動モデル、誤検出率の宣言つき) | Flag what differs from aligned good samples (a per-pixel variation model with a declared false-alarm rate) | 見つける | validated-public-real-data |
10/10 | poc_good_sample_variation_model real → tests/test_poc_scripts_run.pyanomaly_eval_metrics synthetic → tests/test_example_scripts_run.py |
| 格子干渉計(タルボ・ロー)で透過・微分位相・暗視野の 3 像を分ける | Grating interferometry (Talbot / Talbot-Lau): transmission, differential phase and dark field from one phase-stepping scan | 測る | validated-public-real-data |
8/8 | poc_grating_interferometry real → tests/test_poc_scripts_run.py |
| 回折格子の分光器と顕微鏡の照明系(帯域の幅・smile / keystone・ケーラー / クリティカル・同軸のハーフミラー) | Grating spectrometer and microscope illumination (bandwidth, smile and keystone, Koehler and critical illumination, coaxial half mirror) | 光と色 | verified-synthetic |
8/8 | poc_spectrometer_illumination synthetic → tests/test_poc_scripts_run.py |
| 干渉計の共振器・量子雑音の予算・色つき雑音の中の既知波形を閉形式で設計する(重力波望遠鏡の式を検査装置の干渉計・振動計・AE に) | Cavity optics, the quantum-noise budget and a known waveform in coloured noise, in closed form (the gravitational-wave detector’s equations for inspection interferometers, vibrometers and AE) | 波と信号 | validated-public-real-data |
12/12 | poc_gw_detector_pseudo_simulation real → tests/test_poc_scripts_run.py |
| 照明の円錐と観察の NA で、鏡面の小さな傾きを出す・消す(球冠の交わり → 傾きの帯 → 打痕・傷・梨地) | Illumination cone versus imaging NA on specular parts (cap intersection, slope bands, dents, scratches and satin) | 光と色 | verified-synthetic |
5/5 | poc_illumination_cone_vs_na synthetic → tests/test_poc_scripts_run.py |
| 工業用 OCT(干渉スペクトル → k 線形化 → 分散補償 → A / B スキャン → 群屈折率で層厚) | Industrial OCT (spectral interferogram, k-linearisation, dispersion compensation, A/B-scans, layer thickness via the group index) | 測る | validated-public-real-data |
12/13 | poc_industrial_oct real → tests/test_poc_scripts_run.py |
| 円形部品の内径を mm まで測る | Inner diameter of a round part, all the way to millimetres | 測る | validated-public-real-data |
4/4 | example_inner_diameter_mm synthetic → tests/test_example_scripts_run.pypoc_dimensional_inspection synthetic → tests/test_poc_scripts_run.pypoc_real_coin_metrology real → tests/test_poc_scripts_run.py |
| 既知の良品/不良品セットで検査レシピと仕様を配備前に検定し、余裕を測る | Validate a recipe and spec on known good/bad sets before deployment, and measure the margins | 組み立てる | verified-synthetic |
4/4 | inspection_fixture synthetic → tests/test_example_scripts_run.py |
| フォルダを一括検査し、仕様で判定し、集計・SPC・レポート・監査ログまで出す | Inspect a folder in one call — batch, judge against a spec, aggregate, SPC, report, audit log | 組み立てる | verified-synthetic |
8/8 | inspection_workflow synthetic → tests/test_example_scripts_run.py |
| 結果を、触って見られる 1 枚の HTML にする(タブ・バッジ・3-D・動画・多言語) | Turn results into one self-contained page you can touch (tabs, badges, 3-D, video, languages) | 見せる | verified-synthetic |
7/7 | interactive_poc_viewer synthetic → tests/test_example_scripts_run.pyinteractive_anim3d_viewer synthetic → tests/test_example_scripts_run.py |
| 凹んだ部品の相互反射を、測光の真値を保ったまま収束まで数える(3-D の形態係数・漸進ラジオシティ・検査用の多重反射描画) | Count interreflection in concave parts to convergence without losing the photometric truth (3-D view factors, progressive radiosity, an inspection render with bounces) | 光と色 | verified-synthetic |
7/7 | poc_pocket_interreflection synthetic → tests/test_poc_scripts_run.py |
| 地の色を知らずに線と領域を描く(反転色) | Draw lines and regions without knowing the background colour | 見せる | verified-synthetic |
3/3 | annotate_paper_tour synthetic → tests/test_example_scripts_run.py |
| 間接 ToF(位相方式)の多周波アンラップと壊れ方(折り返し・多重反射・縁の混合・高調波・背景光) | Indirect time-of-flight (phase-based): multi-frequency unwrapping and how it breaks (wrapping, multipath, flying pixels, harmonics, ambient light) | 測る | verified-synthetic |
8/8 | poc_itof_multifreq synthetic → tests/test_poc_scripts_run.py |
| レーザー光切断の誤差の床はスペックルが決める(コヒーレント結像・スペックルの統計・三角測量の不確かさ) | Speckle sets the error floor of laser sheet-of-light (coherent imaging, speckle statistics and triangulation uncertainty) | 測る | verified-synthetic |
6/6 | poc_laser_line_speckle_floor synthetic → tests/test_poc_scripts_run.py |
| レンズの歪みを画像ごと補正する(たる型・糸巻き型・接線) | Correct lens distortion over a whole image (barrel, pincushion, tangential) | 形にする | verified-synthetic |
4/4 | lens_undistort synthetic → tests/test_example_scripts_run.py |
| 光学設計ファイル(.zmx の逐次処方を読む・書く・分類する) | Lens design files (read, write and triage sequential .zmx prescriptions) | 光と色 | verified-synthetic |
4/4 | poc_lens_file_roundtrip synthetic → tests/test_poc_scripts_run.py |
| レンズの製造公差を、MTF と歩留まりで決める | Budget lens manufacturing tolerances by MTF and yield | 組み立てる | verified-synthetic |
8/8 | poc_lens_tolerancing synthetic → tests/test_poc_scripts_run.py |
| 凹みの相互反射で縞投影と ToF が外れる量を、撮る前に予測する(大域光輸送・直接と大域の分離・マイクロ位相シフト) | Predict how far interreflection in concave parts throws fringe projection and ToF off, before measuring (global light transport, direct/global separation, micro phase shifting) | 測る | verified-synthetic |
11/11 | poc_interreflection_fringe_error synthetic → tests/test_poc_scripts_run.py |
| 画素ごとの直交復調(ロックイン・時間相関イメージセンサ → 振幅・位相・直流、リング照明の法線・符号化照明の分離・熱波) | Per-pixel lock-in demodulation (time-correlation imaging: amplitude, phase and DC; ring-light normals, coded-light separation, thermal waves) | 測る | verified-synthetic |
9/9 | poc_lockin_imaging synthetic → tests/test_poc_scripts_run.py |
| 材料の光学物性を 1 つの表で引く(硝材・結晶・半導体・金属・液体・プラスチック 86 種、一次文献の係数と数表、硝材カタログの取り込み口) | One table of material optical constants (86 glasses, crystals, semiconductors, metals, liquids and plastics from primary literature, with a glass-catalogue importer) | 光と色 | validated-public-real-data |
15/16 | poc_material_optical_library real → tests/test_poc_scripts_run.py |
| その数字のうち、いくつが測り方のものか(ゲージ R&R と測定の不確かさ) | How much of that number is your measuring, not your process (gauge R&R and measurement uncertainty) | 測る | verified-synthetic |
11/11 | poc_measurement_system_analysis synthetic → tests/test_poc_scripts_run.py |
| モアレで位置合わせ(ピッチの僅かに違う 2 枚の格子 → 縞の位相 → nm のずれ、差動と Talbot ギャップ) | Moiré alignment (two gratings of slightly different pitch, fringe phase, nanometre shift, differential pairs and the Talbot gap) | 測る | verified-synthetic |
8/8 | poc_moire_alignment synthetic → tests/test_poc_scripts_run.py |
| 近赤外のハイパースペクトルで見た目が同じ異物を選別する(材料表の吸収帯 → 散乱層の反射 → InGaAs の帯域ごとの電子数) | Sorting look-alike foreign matter with NIR hyperspectral imaging (material absorption bands, scattering-layer reflectance, InGaAs band electrons) | 光と色 | validated-public-real-data |
6/8 | poc_hyperspectral_foreign_matter real → tests/test_poc_scripts_run.py |
| 非共軸の光学系(折り返しミラー・半透鏡・傾いた平板・シャインプルーフ・ゴースト) | Non-coaxial optics (fold mirrors, beamsplitters, tilted plates, Scheimpflug and ghosts) | 光と色 | verified-synthetic |
14/14 | poc_noncoaxial_optics synthetic → tests/test_poc_scripts_run.py |
| OCR の前処理(傾き補正・局所 2 値化・行の切り出し) | OCR pre-processing (deskew, local binarisation, line extraction) | 見つける | verified-synthetic |
2/4 | gallery2d_segmentation synthetic → tests/test_example_scripts_run.pypoc_matrix_code_reading synthetic → tests/test_poc_scripts_run.pygallery2d_region synthetic → tests/test_example_scripts_run.py |
| 写真を 1 本の線にする(点描 → 巡回路 → 回る円) | Turn a photograph into a single line (stipple, tour, rotating circles) | 描く | validated-public-real-data |
9/9 | poc_one_stroke_epicycles real → tests/test_poc_scripts_run.py |
| 光の反射・屈折・干渉を計算する | Compute reflection, refraction and interference | 光と色 | verified-synthetic |
4/4 | glass_and_mirror_optics synthetic → tests/test_example_scripts_run.pyappearance_structural_colour synthetic → tests/test_example_scripts_run.py |
| 光学系の図面(レンズ断面図・撮像系の設置図・単レンズの製作図を SVG / DXF で) | Optical drawings (lens layouts, vision-setup drawings and ISO 10110 element drawings as SVG / DXF) | 描く | verified-synthetic |
8/8 | poc_optics_drawings synthetic → tests/test_poc_scripts_run.py |
| 良品だけから学んで外れたパッチを指す(古典特徴の「位置ごとの正規分布」と「記憶バンク」、再現率を保証する運用点) | Flag patches that leave what good samples look like (classical features, a normal distribution per position or a memory bank, and a recall-guaranteeing operating point) | 見つける | validated-public-real-data |
12/12 | poc_patch_anomaly real → tests/test_poc_scripts_run.pyanomaly_eval_metrics synthetic → tests/test_example_scripts_run.py |
| 1-D 信号の周期欠陥を見つける | Periodic defects in a 1-D signal | 波と信号 | verified-synthetic |
5/5 | poc_web_roll_periodicity synthetic → tests/test_poc_scripts_run.pypoc_rail_corrugation synthetic → tests/test_poc_scripts_run.pypoc_bearing_diagnosis synthetic → tests/test_poc_scripts_run.py |
| 光沢面の µm の凹みを縞の鏡像で測る(位相計測デフレクトメトリ: 縞 → 位相 → 傾き → 曲率) | Find micrometre dents on glossy surfaces from the mirror image of a fringe screen (phase-measuring deflectometry) | 測る | verified-synthetic |
6/6 | poc_phase_measuring_deflectometry synthetic → tests/test_poc_scripts_run.py |
| 光弾性で応力を測る(応力場 → 縞 → 偏光像 → 位相差と主軸) | Measure stress by photoelasticity (stress field, fringes, polarisation images, retardation and axis) | 測る | verified-synthetic |
13/13 | poc_photoelasticity synthetic → tests/test_poc_scripts_run.py |
| 処方どおりのレンズ越しに 3 次元の場面を撮る(被写界深度・猫の目のボケ・隅の光量・色収差・ゴースト) | Photographing a 3-D scene through the actual lens prescription (depth of field, cat’s-eye bokeh, corner illumination, colour fringes, ghosts) | 描く | verified-synthetic |
8/8 | poc_photograph_through_prescription synthetic → tests/test_poc_scripts_run.py |
| 目が嘘をつく絵を作って、測る側を採点する(錯視・無限描画・循環動画) | Pictures that carry their own ground truth (illusions, endless drawing, seamless loops) | 描く | verified-synthetic |
15/16 | poc_illusions_and_perpetual_drawing synthetic → tests/test_poc_scripts_run.py |
| ピクセルシフト撮像(1 画素シフトで全色、半画素シフトで折り返しを消す、壊れる条件まで) | Pixel-shift imaging (full colour from 1-pixel shifts, no aliasing from half-pixel shifts, and where it breaks) | 光と色 | verified-synthetic |
6/6 | poc_pixel_shift synthetic → tests/test_poc_scripts_run.py |
| PL 像で細い溝が見えなくなる理由を、キャリア拡散の PSF と欠陥の種類で切り分ける(Si ウェハ・太陽電池の PL/EL 検査) | Why a thin groove disappears in a PL image — the carrier-diffusion PSF and the kind of defect decide the visibility (PL/EL inspection of wafers and solar cells) | 見つける | validated-public-real-data |
4/4 | poc_si_wafer_pl_defect_visibility real → tests/test_poc_scripts_run.py |
| 3-D 点群から平面度を出す | Flatness of a surface from a 3-D point cloud | 測る | verified-synthetic |
4/4 | geometry_metrology synthetic → examples3d.py (suite runs a smoke subset)poc_bump_coplanarity synthetic → tests/test_poc_scripts_run.pypoc_scan_to_bim_asbuilt synthetic → tests/test_poc_scripts_run.py |
| 処方から撮るプレノプティックカメラ | Prescription-based plenoptic camera | 描く | verified-synthetic |
6/6 | poc_plenoptic_camera synthetic → tests/test_poc_scripts_run.py |
| 点群をそのまま色の絵にする | Draw a point cloud as a colour picture | 見せる | validated-public-real-data |
3/3 | points_render_basics synthetic → examples3d.py (suite runs a smoke subset)poc_flybrain_pointcloud real → tests/test_poc_scripts_run.py |
| 小さな点状の目標を見つけて、副画素で位置を出す | Find small point-like targets and locate them below the pixel | 見つける | verified-synthetic |
4/4 | poc_search_sweep_width synthetic → tests/test_poc_scripts_run.pypoc_astro_photometry synthetic → tests/test_poc_scripts_run.py |
| 偏光 4 方向で鏡面反射を除く(誘電体と金属で分ける) | Remove specular reflection from a four-angle polariser sweep (dielectrics vs metals) | 光と色 | verified-synthetic |
4/4 | example_polarization_metal synthetic → tests/test_example_scripts_run.pypoc_polarization_specular synthetic → tests/test_poc_scripts_run.pyspecular_photometric synthetic → tests/test_example_scripts_run.py |
| 偏光カメラの生フレームを Stokes・DoLP・Mueller に読む | Read a polarisation camera’s raw frame into Stokes, DoLP and Mueller | 光と色 | verified-synthetic |
10/10 | polarization_camera_pipeline synthetic → tests/test_example_scripts_run.pypoc_polarization_specular synthetic → tests/test_poc_scripts_run.py |
| どの大きさなら見つかるか(検出確率 POD と a90/95、MIL-HDBK-1823A) | Which flaw size will you actually find (probability of detection and a90/95, MIL-HDBK-1823A) | 測る | verified-synthetic |
7/7 | poc_pod_lighting synthetic → tests/test_poc_scripts_run.py |
| Bayer の生フレームを、段ごとに説明できる式で表示画像にする | Turn a Bayer raw frame into a display image, one explainable stage at a time | 光と色 | verified-synthetic |
13/14 | raw_to_display_isp synthetic → tests/test_example_scripts_run.py |
| 同じ入力の検証・近傍探索・変換核を一度だけ計算する | Reuse validation, neighbourhoods and transform kernels | 組み立てる | verified-synthetic |
8/9 | perf_pointcloud_descriptors synthetic → tests/test_example_scripts_run.pyperf_monogenic_metrics synthetic → tests/test_example_scripts_run.pyperf_prepared_volume_probe synthetic → tests/test_example_scripts_run.pyperf_polarization_analyze synthetic → tests/test_example_scripts_run.pyperf_hankel_plan_and_piv_stream synthetic → tests/test_example_scripts_run.py |
| 照明むら・ハイライト・遮蔽に強いテンプレート照合(明るさの変化の向きを符号にして比べ、決まらないテンプレートは拒否する) | Template matching that survives uneven light, highlights and occlusion (compare the direction of brightness change as codes, and refuse templates that cannot fix a position) | 見つける | validated-public-real-data |
5/6 | poc_code_matching_breakdown real → tests/test_poc_scripts_run.py |
| 傷や突起に引きずられない平均線を引く(ロバストなガウス回帰・スプラインフィルタ、断面と面) | A mean line that deep scratches and spikes cannot drag (robust Gaussian-regression and spline filters, for profiles and surfaces) | 測る | verified-synthetic |
4/4 | poc_robust_profile_filter synthetic → tests/test_poc_scripts_run.pyexample_robust_profile_filter synthetic → tests/test_example_scripts_run.py |
| ハイブリッド接合のボイドを、超音波のエコーの明るさでなく位相で見つける(走査型音響顕微鏡の C スキャン・周波数の取引・POD) | Find hybrid-bond voids by the phase of the ultrasonic echo, not its brightness (scanning acoustic microscope C-scans, the frequency trade-off, POD) | 見つける | verified-synthetic |
7/7 | poc_sam_hybrid_bonding_voids synthetic → tests/test_poc_scripts_run.py |
| 微細スクラッチを見つけて、幅を測る | Detect fine scratches and measure their width | 測る | verified-synthetic |
4/4 | example_scratch_width synthetic → tests/test_example_scripts_run.pypoc_crack_width synthetic → tests/test_poc_scripts_run.pypoc_solar_el_inspection synthetic → tests/test_poc_scripts_run.py |
| SEM の明るい縁が寸法をどれだけ太らせるかを、真値つきで測る | Measure how much the bright SEM edge inflates a dimension, with ground truth | 測る | validated-public-real-data |
6/6 | poc_sem_wafer_defect_edge_bias real → tests/test_poc_scripts_run.py |
| 同じ粒子を走査像と透過像で測り、二つの寸法偏りを比べる | Measure the same particles in scanning and transmission images and compare both size biases | 測る | verified-synthetic |
9/9 | poc_sem_tem_same_particle synthetic → tests/test_poc_scripts_run.py |
| 逐次光学設計の指標(理想レンズ面 → 囲みエネルギー → 子午/球欠 MTF → スルーフォーカス MTF) | Sequential lens-design metrics (ideal lens surface, encircled energy, tangential / sagittal MTF, through-focus MTF) | 測る | verified-synthetic |
32/32 | optical_design_metrics synthetic → tests/test_example_scripts_run.pypoc_zoom_configurations synthetic → tests/test_poc_scripts_run.pypoc_lens_global_search synthetic → tests/test_poc_scripts_run.pypoc_lens_merit_operands synthetic → tests/test_poc_scripts_run.pypoc_lens_solves_afocal synthetic → tests/test_poc_scripts_run.py |
| 黒光沢とガラスの形を偏光で測る(偏光からの形状復元・曖昧さの集合・屈折率の推定) | Measure the shape of black-glossy and glass parts from polarisation (shape from polarisation, the ambiguity set, refractive index) | 測る | verified-synthetic |
8/8 | poc_shape_from_polarization synthetic → tests/test_poc_scripts_run.py |
| 実物の画像から物理モデルの係数を合わせる(sim-to-real 較正)—— 画像が決めない係数には数を出さず、決まる組み合わせと理由を返す | Fit a physical model’s coefficients to real images (sim-to-real calibration) — no number for a coefficient the images do not determine, the determined combination and the reason instead | 測る | verified-synthetic |
10/10 | simcal_tour synthetic → tests/test_example_scripts_run.pysimcal_checks_tour synthetic → tests/test_example_scripts_run.py |
| 光源 × 対象 × センサの分光の鎖(Planck・CIE A・LED・フィルタ・Si の QE、曲線の積と積分) | The spectral chain source × object × sensor (Planck, CIE A, LEDs, filters, Si QE, curve products and integrals) | 光と色 | verified-synthetic |
9/9 | poc_nir_silicon_transmission synthetic → tests/test_poc_scripts_run.py |
| 画像から寸法をサブピクセルで測る | Measure dimensions from an image, below the pixel | 測る | verified-synthetic |
4/4 | poc_dimensional_inspection synthetic → tests/test_poc_scripts_run.pypoc_screw_thread_metrology synthetic → tests/test_poc_scripts_run.pypoc_calipers_under_illusion synthetic → tests/test_poc_scripts_run.py |
| 表面の凹凸欠陥を、照明の設計から検出まで | Surface relief defects, from lighting design to detection | 見つける | verified-synthetic |
5/5 | illumination_design_demo synthetic → tests/test_example_scripts_run.pyphotometric_stereo synthetic → examples3d.py (suite runs a smoke subset)poc_bump_coplanarity synthetic → tests/test_poc_scripts_run.py |
| TDI ラインスキャンとラインスキャン用レンズ(段数と SNR → 同期ずれの MTF → 像高ごとの照度と MTF) | TDI line-scan cameras and line-scan lenses (stages and SNR, synchronisation MTF, illumination and MTF across the image height) | 光と色 | verified-synthetic |
6/6 | poc_tdi_linescan synthetic → tests/test_poc_scripts_run.py |
| テレセントリックレンズと寸法計測(主光線の傾き → 高さで変わる倍率 → ケラレとぼけ) | Telecentric lenses for dimensional metrology (chief-ray angle, magnification versus height, vignetting and blur) | 測る | verified-synthetic |
7/7 | poc_telecentric_metrology synthetic → tests/test_poc_scripts_run.py |
| 仮想の透過電子顕微鏡(電子の波長 → CTF → 位相コントラストの像 → Thon リングから焦点外れを推定 → 補正) | A virtual transmission electron microscope (electron wavelength, CTF, phase-contrast images, defocus from Thon rings, correction) | 測る | validated-public-real-data |
11/11 | poc_tem_ctf_thon_rings real → tests/test_poc_scripts_run.py |
| 位置決め(テンプレート照合で測定線を追従させる) | Locate a part by template matching and move the measurement model with it | 見つける | verified-synthetic |
4/4 | poc_template_tracking synthetic → tests/test_poc_scripts_run.pygallery2d_contour_measure synthetic → tests/test_example_scripts_run.pypoc_search_sweep_width synthetic → tests/test_poc_scripts_run.py |
| 地形の傾き・水の流れ・見通しを測る | Slope, flow and line of sight on a terrain | 測る | verified-synthetic |
4/4 | poc_dem_terrain synthetic → tests/test_poc_scripts_run.pydem_terrain_analysis_tour synthetic → tests/test_example_scripts_run.py |
| 画像の上に、文字と表を置きたい場所へ置く | Put text and tables exactly where you want them on an image | 見せる | verified-synthetic |
6/6 | annotate_paper_tour synthetic → tests/test_example_scripts_run.py |
| 定理が門になる図(アポロニウス・フォード・測地ドーム・葉序・IFS・空間充填曲線) | Theorems as pictures (Apollonian, Ford, geodesic dome, phyllotaxis, IFS, space-filling curves) | 描く | verified-synthetic |
9/9 | poc_theorems_as_pictures synthetic → tests/test_poc_scripts_run.py |
| 薄膜の膜厚を分光反射率で測る(転送行列 → 干渉色 → FFT・モデルあてはめ・膜厚マップ) | Thin-film thickness by spectral reflectometry (transfer matrix, interference colour, FFT, model fit, thickness maps) | 光と色 | validated-public-real-data |
5/5 | poc_thin_film_reflectometry real → tests/test_poc_scripts_run.py |
| 同じ3次元場面を間接ToFと直接ToFで測る | Measuring one 3-D scene with indirect and direct time of flight | 測る | verified-synthetic |
14/14 | poc_tof_camera synthetic → tests/test_poc_scripts_run.py |
| 投影から断面を再構成する(CT) | Reconstruct slices from projections (CT) | 形にする | verified-synthetic |
3/4 | poc_ct_fidelity synthetic → tests/test_poc_scripts_run.pypoc_ct_void_morphology synthetic → tests/test_poc_scripts_run.py |
| op の返り値(型付き)を JSON に出し、bit そのままで戻す | Write typed op results as JSON and read them back bit-for-bit | 組み立てる | verified-synthetic |
11/11 | typed_results_json synthetic → tests/test_example_scripts_run.py |
| op の返り値(型付き)を Markdown で読める形にし、JSON を埋め込んで戻す | Render typed op results as Markdown, with an exact JSON block to read back | 組み立てる | verified-synthetic |
4/4 | typed_results_markdown synthetic → tests/test_example_scripts_run.py |
| 振動と音から異常を診断する | Diagnose faults from vibration and sound | 波と信号 | verified-synthetic |
5/5 | poc_bearing_diagnosis synthetic → tests/test_poc_scripts_run.pypoc_rail_corrugation synthetic → tests/test_poc_scripts_run.py |
| 仮想 SEM —— 電子と固体の相互作用をモンテカルロで解き、加速電圧・検出器・帯電で像と線幅がどう変わるかを実測値で採点しながら見る | A virtual SEM — solve the electron-solid interaction by Monte Carlo and see, scored against measured data, how voltage, detector and charging change the image and the measured line width | 測る | verified-synthetic |
9/9 | poc_virtual_sem_kv_cd_bse synthetic → tests/test_poc_scripts_run.py |
| シルエットから立体を彫り出す(視体積交差) | Carve a solid out of silhouettes (visual hull) | 形にする | verified-synthetic |
4/4 | space_carving synthetic → examples3d.py (suite runs a smoke subset)poc_livestock_body_volume synthetic → tests/test_poc_scripts_run.py |
| 3-D スキャンから体積・土量を出す | Turn a 3-D scan into a volume | 測る | verified-synthetic |
4/4 | poc_stockpile_volume synthetic → tests/test_poc_scripts_run.pypoc_lidar_terrain_change synthetic → tests/test_poc_scripts_run.py |
| 水が検査画像にどう写るか(プールの底のコースティクス・瓶の側面像と液面・濡れた面・船体の水中画像) | How water looks in inspection images (caustics on a pool floor, a bottle seen from the side with its fill line, a wet surface, a hull seen through water) | 光と色 | verified-synthetic |
7/7 | poc_water_inspection_images synthetic → tests/test_poc_scripts_run.py |
| 水と透明媒質(海の波・水面のフレネルと屈折・水中の色と散乱・瓶のレンズ作用) | Water and transparent media (ocean waves, Fresnel and refraction at the surface, colour and scattering under water, a bottle as a lens) | 光と色 | verified-synthetic |
10/10 | poc_water_transparent_media synthetic → tests/test_poc_scripts_run.py |
| 絵では確かめられないもの(積分器の次数・リアプノフ指数・分岐・相関次元・極小曲面) | What a picture cannot check (integrator order, Lyapunov spectrum, bifurcations, correlation dimension, minimal surfaces) | 測る | verified-synthetic |
11/11 | poc_what_a_picture_cannot_check synthetic → tests/test_poc_scripts_run.py |
| 型付きの検査結果を Excel(.xlsx)レポートに書き出す | Write typed inspection results to an Excel (.xlsx) report | 組み立てる | verified-synthetic |
4/4 | xlsx_report synthetic → tests/test_example_scripts_run.py |
記録した報告はまだ 0 件です(docs/validation_reports.json は空)。
No external report has been recorded yet.
| 件数 | |
|---|---|
| 2-D 台帳の例 | 449 |
tests/test_poc_scripts_run.py が走らせる |
283 |
tests/test_example_scripts_run.py が走らせる |
166 |
| どの門も走らせていない | 0 |
走らせない門は、実行時の壊れに盲目です。2026-09-06 に PoC 側で穴が見つかり
(31 本のうち 4 本が exit 1 のまま放置)、2026-09-09 に同じ穴が 1 つ内側で
再演していたことが分かりました —— 門を作ったのに、対象を数え直さなかったので
poc_* 以外の 83 件が外に残り、そのうち 2 件が落ちていました。
どちらの門も PYTHONPATH を渡さずに走らせます(利用者と同じ条件)。
機械可読版は maturity.json。