fullseye

Fullseye Dokumentationsindex

Language: 日本語 · English · 简体中文 · 繁體中文 · 한국어 · Deutsch

Präsentation auf der ViEW2026 (3.–4. Dezember 2026, Pacifico Yokohama) → ViEW2026-Seite (bewegte PoC-Ergebnisse, Viewer zum Ausprobieren im Browser, das Paper)

Hinweis: Übersetzt ist bisher nur diese Indexseite. Die einzelnen Dokumente, auf die sie verweist, liegen vorerst ausschließlich auf Japanisch vor.

Sechs Akte, ausschließlich echte Operator-Ausgaben: Kantenorientierung, Blob-Auswahl, Subpixel-Messung, SDF zu Mesh, LiDAR-Clustering, Objektiv-Defokus.

Fullseye (Arbeitsname imgevolve) ist ein Werkzeug auf HALCON-/HDevelop-Niveau: eine numpy-native Bibliothek von Bildverarbeitungs-Operatoren, dazu eine visuelle Pipeline-Entwurfsumgebung im Stil von HDevelop (Fullseye Studio) und eine ausführende Laufzeitumgebung (FullseyeEngine). Es umfasst rund 942 Operatoren (gezählt in der Registry), bietet für 981/2313 tatsächliche HALCON-Operatoren eine genuine (wirklich gleichwertige) Implementierung und deckt 48 Kategorien ab.

★ Selten für eine Bildverarbeitungsbibliothek, bringt Fullseye auch virtuelles optisches Design mit — dünne/dicke Linsen, Raytracing, Seidel-Aberrationen und PSF/MTF, dazu eine Damped-Least-Squares-Optimierung (Levenberg–Marquardt) der Linsenverordnung selbst (optimize_lens). Man kann das abbildende System entwerfen und sein Bild dann mit den obigen Operatoren prüfen — durchgängig, ein Unterscheidungsmerkmal für Halbleiter und Präzisionsmesstechnik.

Fangen Sie hier an → GETTING_STARTED.de.md (in 5 Minuten lauffähig)

Was es kann → CAPABILITIES.en.md (nach Vorhaben geordnet) / Was die PoCs gehärtet haben → HARDENING.en.md (gefunden, behoben, abgesichert)

Ergebnisse von echter Hardware und echten Daten gesucht. Fullseye wird ohne physische Messaufbauten entwickelt und deshalb gegen virtuelle optische Systeme und simulierte Referenzwerte validiert. Ergebnisse mit echter Hardware oder echten Daten sind sehr willkommen. Ihre Daten müssen Sie nicht teilen — reine Ergebnisberichte werden angenommen, und ein Validierungskit (python -m fullseye.validation_kit) gibt aus lokalen Daten nur aggregierte Zahlen aus. → Berichtsformular · Discussions › Show and tell · Bewertungsregeln (Englisch)

---

Wie geprüft wird

Keine dieser Zahlen ist von Hand geschrieben: tools/gen_trust_block.py erzeugt diesen Abschnitt aus Messdateien in docs/ (test_count.json, gate_inventory.json, maturity.json, op_count_history.json), und tests/test_trust_block.py schlägt fehl, wenn er davon abweicht. Jede Zahl trägt Version und Datum ihrer Messung.

22,110 Regressionstests — in 0.8.1 enthalten, Commit e720d52d02, am 2026-10-22 mit pytest --collect-only gezählt, mit allen optionalen Backends installiert (ohne sie werden die Tests der fehlenden Backends nicht gesammelt und die Zahl ist kleiner).

Was einen neu hinzugefügten Operator prüft

Pro Schicht wurde genau ein absichtlich defekter Operator eingefügt und die gesamte Testsuite ausgeführt; gezählt wurden die fehlschlagenden Tests (Mutation Probe). ✓ = ein Gate erkennt diesen Defekt, ✗ = noch keines.

• Messung ①: Commit e97e94bae2, 2026-10-11, Stand nach 0.6.0 (mit unveröffentlichten Änderungen).

Schicht	Messung	Verwaltungs-Gates	Verhaltens-Gates	wirft Ausnahme	NaN	falscher Typ	nicht deterministisch	ignoriert Parameter	keine Beschreibung	Beschreibung nur Englisch	akzeptiert leere Eingabe
2-D-Kern (ops.REGISTRY)	①	27	10	✓	✓	✓	✓	✗	✓	✓	✗
n-är	①	16	5	✓	✓	✓	✗	✗	✓	✓	✗
Farbe	①	28	10	✓	✓	✓	✓	✗	✓	✓	✗
typisiertes Register + tb_-Brücke	①	29	16	✓	✓	✓	✓	✓	✓	✓	✓
typisiertes Register (ohne Brücke)	①	17	5	✓	✓	✓	✓	✓	✓	✓	✓
3-D-Register	①	20	7	✓	✓	✓	✓	✓	✓	✓	✓
nur Fassade	①	1	1	✗	✗	✗	✗	✗	✓	✗	✗

Verwaltungs-Gates schlagen bei jedem neuen Operator an, auch bei einem korrekten, bis seine Notiz und sein Indexeintrag neu erzeugt sind. Verhaltens-Gates = die weiteren, verschiedenen Tests, die wegen der Art des Defekts fehlschlagen.

Nicht gemessen: plausible, aber falsche Werte (Abstand zur Grundwahrheit), Geschwindigkeit, betriebssystemspezifische Fehler, zwei Defekte zugleich. ✓ heißt, dass mindestens ein Test fehlschlug, nicht dass seine Meldung den Grund erklärt.

Verifikationsstufe

Die 97 Fähigkeiten, aufgeteilt nach Art der Prüfung (docs/maturity.json, von tools/gen_maturity.py aus dem aktuellen Stand (pyproject-Version 0.8.1) erzeugt; Stufen erklärt in MATURITY.md).

Stufe	Bedeutung	Fähigkeiten
research-prototype	implementiert; Tests oder ein laufendes Beispiel fehlen noch	0
verified-synthetic	automatisch gegen synthetische Grundwahrheit geprüft	79
validated-public-real-data	ein Beispiel mit öffentlichen Messdaten läuft in einem Gate	18
validated-hardware	an Hardware validiert (nur über angenommene externe Berichte)	0

Von 449 Beispielen werden 449 tatsächlich von einem Gate ausgeführt.

Operatorzahlen pro Version

Version	Datum	Index gesamt	davon typisiertes Register	HALCON	PoC	Regressionstests
0.1.0	2026-08-30	—	—	323	0	6,246
0.1.8	2026-09-05	—	—	323	0	11,518
0.1.9	2026-09-05	—	—	979	0	11,593
0.1.11	2026-09-15	918	0	979	121	13,178
0.2.0	2026-09-15	1,942	1,024	979	121	13,272
0.3.0	2026-10-03	2,590	1,639	980	187	16,675
0.4.0	2026-10-06	3,057	2,104	980	214	17,424
0.5.0	2026-10-06	3,078	2,125	980	217	17,489
0.6.0	2026-10-11	3,083	2,130	981	218	18,109
0.7.0	2026-10-18	3,354	2,401	982	248	19,935
0.8.0	2026-10-22	3,529	2,572	982	275	22,073
0.8.1	2026-10-22	3,531	2,572	982	275	22,110

• Der HALCON-Wert 323 für 0.1.0–0.1.8 ist der damals festgehaltene Wert; ab 0.1.9 beträgt er nach geänderter Zählung 979 (keine 656 neuen Implementierungen).
• 0.2.0 ist die erste Version, deren Index das typisierte Register enthält: 918 → 1,942 ist eine Änderung der Zählweise, keine neue Implementierung (das Register gab es ab 0.1.6, aber außerhalb des Index).

— = für diese Version nicht gemessen. Alle Versionen und Spaltendefinitionen: OP_COUNT_HISTORY.md (Japanisch/Englisch).

PoC-Serie — 283 reale Aufgaben mit Grundwahrheit

Jede hat eine geschlossene oder synthetische Grundwahrheit und ein Nullmodell. Fehlerarten werden getrennt gezählt. Vollständige Liste: examples/README.md.

Feld	PoC und Befund
metrology (70)	poc_aoi_ct_traceability Matching Full 2-D Inspection to Sampled 3-D Inspection — A Grid Overlaps Itself poc_asbuilt_wall_deviation As-built wall deviation — the bounding box measures the room’s heading, not its size poc_battery_electrode_breathing Measuring electrode breathing in microns — sub-pixel is not enough poc_bone_trabecular_thickness Trabecular Thickness, Separation and Bone Volume Fraction — The Plate Model and the Direct Method Disagree on the Same Image poc_braid_homotopy_classes Sorting Multi-Robot Plans with the Same Starts and Goals by How They Wind — Counting Homotopy Classes with Space-Time Braids and Dynnikov Coordinates, 61 Planner Candidates in 26 Classes poc_bump_coplanarity Bump coplanarity versus substrate warpage — subtract too much and the real defect goes with it poc_cad_scan_deviation CAD-to-scan deviation inspection — the fit absorbs the defect and invents a dent poc_crack_width Concrete Crack Width Is Thinner Than a Pixel — Counting Width Versus Integrating Width poc_crack_width_timeseries Measuring the Growth, Not the Width — Rephotographing the Same Wall Changes What the Error Is poc_datacenter_thermal_field A 3-D Thermal Field from Sparse Sensors — The Grid’s Blind Spot Erases a Rack poc_diabolo_model_and_vision Transcribing a Diabolo Model from the Paper and Checking It, then Reading Axis, Spin and Tension from Synthetic Video — Eq. (1b) as Printed Is Dimensionally Wrong and Gives NaN at the Real Dimensions; Closed Forms, an Exact String and MuJoCo as the Truth poc_dic_strain Strain From Speckle Images (DIC) poc_dimensional_inspection Dimensional Inspection of a Machined Part — Bias and Scatter as Two Numbers poc_dose_uniformity_from_grinding How Long to Grind for a Uniform Dose — Content Uniformity from Particle Size by Closed Form and Monte Carlo, Inverted through Comminution Laws; the Low CV from Photos Was the Same 12 Images at Different Scales poc_fiber_orientation Fibre Orientation Distribution — Angles Repeat Every 180 Degrees, and a Naive Mean Is 90 Degrees Off poc_gear_tooth_metrology Gear Tooth Metrology — Eccentricity Is Order 1, Teeth Are Order z poc_geodetic_height_frames Coordinates Go Wrong by Tens of Metres While Still Looking Plausible poc_granular_heap_repose Measuring a Powder Heap from Images — Angle of Repose, Volume, Mass, Flowability and Discharge by Rules, with Closed Forms, Published Values and MuJoCo as the Truth poc_grating_interferometry Grating Interferometry — Fibre Orientation, Micro-Cracks and Pores That Absorption Cannot See, Read From the Fringe Amplitude (Dark Field) poc_gw_detector_pseudo_simulation A Pseudo-Simulation of a Gravitational-Wave Detector — Cavity Optics, the Quantum-Noise Budget and the Matched Filter in Closed Form, Scored on the Real GW150914 Data poc_industrial_oct Industrial OCT (optical coherence tomography) — Layer Thickness and Hidden Defects of Paints, Coatings and Multilayer Films, Seen in Depth by the FFT of One Spectral Interferogram poc_interferometry_step How Accurately a White-Light Interferometer Measures a Nanometre Step poc_interreflection_fringe_error Fringe Projection Misreads Even a White Groove - Separating the Interreflection, Predicting the Error Before Measuring, and Removing It with Micro Phase Shifting poc_knife_tactile_toughness Holding and Cutting with a Knife by Fingertip Visuotactile Sensing Alone — Toughness, Blade Contact Position and How Long a Handle Can Be Held, without a Wrist Force Sensor; the Existing Reader’s Torsion Over-read (+33 % at Half Slip) Fixed by a Numerical Partial-Slip Solution poc_laser_line_speckle_floor Speckle Sets the Error Floor of a Laser Sheet-of-Light - It Does Not Average Away, and the Estimator Ranking Flips poc_livestock_body_volume Weighing an Animal from Silhouettes — The Error You Can Buy Down, and the One You Cannot poc_metal_grain_size Metallographic Grain Size — The Planimetric and Intercept Methods Fall Off Different Cliffs poc_moire_alignment Moiré (beat fringe between periodic patterns) Alignment — Two Invisible 2 µm Gratings Overlaid Turn a 1 nm Shift into a Readable Fringe Phase poc_multibeam_bathymetry Why the Seafloor Smiles — Sound-Speed Error Remaining on Outer Beams After Nadir Calibration poc_particle_sizing Particle Size Distribution From Images — Merging and Edge Cuts Pull Opposite Ways and Cancel poc_peg_insertion_tactile Reading Peg-in-Hole Insertion through Two Fingertip Membranes — Contact Wrench, Whitney’s Contact States, Wall Friction and Wrist Stiffness from Shear Images; at the Wedging Boundary the Wrench Alone Is Blind poc_peg_symmetry_search Cutting a Peg’s Rotation Search to 1/n with Its Symmetry — Inserting Square, Hexagonal and Keyed Pegs Checked by Group Identities, Closed Forms and MuJoCo; Friction Shrinks the Hexagon’s Chamfer Window from 20.9° to 6.8° poc_phase_measuring_deflectometry Finding Micrometre Dents a Photograph Cannot Show, in the Mirror Image of a Fringe Screen — Phase-Measuring Deflectometry poc_photoelasticity Stress by Photoelasticity — Unwrapping Fails First at the Isotropic Point poc_pipe_wall_loss Pipe Wall Loss on the Unwrapped Map — The Axis You Choose Eats the Invert Corrosion poc_plateau_venue_lod2 The Venue Buildings and Asteroid Itokawa on One Ruler — Turning PLATEAU CityGML LOD2 into a Triangle Mesh poc_polish_wipe_measure Measuring Grinding, Polishing and Wiping from Images — Removed Depth, Wiped Band Width and Area Checked by Preston’s Law, Closed-Form Contact Pressure and MuJoCo; a Compliant Wrist Keeps the Band Even over a 2 mm Height Error while a Stiff Wrist Lifts Off and Leaves Gaps poc_powder_grinding_ae Measuring Mortar Grinding — D50 of the Size Distribution, Comminution Laws, Spread over Three Independent Runs and AE Band Power, against Published Laser-Diffraction Measurements; a Different D50 Definition Is a One-Bin, 12 % Bias poc_powder_scoop_pour Measuring Scooping and Pouring of Powder from Images — the Scooped Amount from Side-View Silhouettes, the Pour Rate from PIV (particle image velocimetry) Speed × a Boolean-Model Line Density, within 5 % of MuJoCo’s Ball Counts and Line Crossings poc_pxrd_phase_peel Peeling Phases One at a Time off a 2-D Powder X-ray Diffraction Image — Calibration, Azimuthal Integration, NNLS and the Unknown Phase in the Residual; References from the NIST SRM 640g Certificate and COD CIFs, with the Shared-Model Leak Measured by Deliberate Mismatch poc_real_coin_metrology Counting and Measuring Real Coins — A Correct Answer Is Not a Safe One poc_robust_profile_filter Deep Scratches Dent the Mean Line — How Much Contamination Robust Gaussian and Spline Filters Survive poc_rover_slip_risk_path Predicting Wheel Slip with Uncertainty on Real Martian Terrain and Planning a Path that Avoids the Slip Risk — Bekker / Wong–Reece and CVaR on a HiRISE DTM; outside the Data a Gaussian Process Calls a Stuck Slope ‘Slip 0.29’ poc_scan_to_bim_asbuilt As-built deviation of a room — the compromise pose is handed to the innocent element poc_screw_thread_metrology Pitch, Flank Angle and Pitch Diameter From a Thread Silhouette — Tilt Shows Up With Opposite Signs on the Two Flanks poc_sem_tem_same_particle Measuring the Same Particles in Scanning and Transmission Images — Which Is Right, 52 nm or 48 nm? poc_sem_wafer_defect_edge_bias How Much the Bright SEM Edge Inflates a Dimension — the Shape Matches but the Area Grows poc_settlement_significance Did It Settle, or Did We Just Scan It Again — What Changes When You Cut at the Detection Limit poc_shape_from_polarization Measuring Black-Gloss and Glass from Polarisation - No Shading, but the Polarisation Remembers the Slope poc_simcal_telecentric Calibrating an Imaging Model on a Real Telecentric Image — the Scale Matches the Paper, the Entrance Pupil Is Only ‘Farther than 1 m’ poc_star_astrometry To What Fraction of a Pixel Can a Star Be Located, and Where Is the Cliff? poc_stockpile_volume Stockpile Inventory — The Answer Is Fixed by the Ground Nobody Measured poc_strain_history Strain History in a Creep Test — Cumulative or Direct? poc_structure_4d_deterioration Re-surveying a structure year by year — when the vantage moves, decay appears to advance poc_surface_roughness How Far Sa / Sq / Sz Survive Sampling and Cutoff poc_swarm_obstacle_from_flow A Swarm That Flows Like a Fluid Senses an Invisible Obstacle from the Disturbance of Its Velocity Field Alone — Reading the Impact Point and the Obstacle Outline by Tracking and PIV (particle image velocimetry) on Overhead Video, from Upstream Before Contact, and Saying Nothing When There Is No Obstacle poc_tacdome_large_deformation Gating Large-Deformation Contact of a Soft Dome Fingertip Pressed on a Flat Object with a Scaling Law and an Exact Continuum Solution — As Printed, the Linear Coefficient of Eq. (3) Makes the Force of a Cylinder Negative; 2n/(1+n) Is Derived from the Paper’s Own Model poc_tacscalib_sphere_lut Calibrating a Vision-Based Tactile Sensor’s Illumination on Real Calibration Spheres, with a Gradient LUT as the Second Implementation — the Ball Radius and Hand-Marked Circles as the Truth poc_tacsim_elastic_membrane A Vision-Based Tactile Sensor (Elastic Membrane + Camera), Synthesised and Inverted — Hertz Contact and Photometric Stereo in Closed Form as the Gate, Force Read from a Pressed Sphere poc_tacsim_marker_shear Reading the Shear Field, Stick/Slip and Tangential Force from a Tactile Sensor’s Marker Array — Cattaneo–Mindlin in Closed Form and Finite-Element Nodal Displacements as the Gate poc_tactile_dipole_torque Reading In-Grasp Tilt and Torsion Torque from a Tactile Sensor’s Marker Field with a ‘Tactile Dipole’ — Gauss’s Law Becoming an Identity in the Half-Space as the Gate poc_telecentric_metrology Telecentric Lenses for Dimensional Metrology — Move Only the Stop of the Same Lens and the Height-Dependent Magnification Disappears poc_tem_ctf_thon_rings A Virtual Transmission Electron Microscope — Thon Rings (CTF rings in a TEM power spectrum) Move with Focus, Fine Detail Reverses, and Defocus Is Read from Real Micrographs poc_thermal_radiometry A Thermal Image Is Not a Temperature Image — Emissivity, Reflection, and an Uncertainty That Does Not Add poc_tree_ring_dendro Counting tree rings and extracting the width series — ring count and width correlation fail separately poc_virtual_sem_kv_cd_bse A Virtual SEM — Fire Electrons One by One into the Solid, and the Image and the Measured Line Width Change with the Voltage (Scored against Measured Data) poc_water_level River Stage From an Oblique Photo — Ignoring Perspective Bends the Row-Number Error Into an Arc poc_weld_bead_profile Weld Bead From a Laser-Triangulation Profile — The Sin of Writing 0 Where Nothing Was Measured poc_weld_bead_scan_angle Light-section scanning of a weld bead — resolution and occlusion share one knob poc_wound_area_tracking Wound Area Over Time — Calibration Error Enters the Area Squared
imgmetrics (47)	poc_agv_fleet A Warehouse That Does Not Jam When Vehicles Run Late — A Correct Plan Alone Still Stops an AGV Fleet poc_air_hockey_intercept Tracking, Predicting and Returning an Air-Hockey Puck with a Five-Bar Linkage — No Learning, Closed Forms and an External Simulator as the Gates poc_am_thermal_to_ct Metal-AM Thermography and X-ray CT — Separate Experiments poc_ball_bounce Measuring a Table-Tennis Ball the Way the Pioneers Did — Multi-Camera Tracking, Triangulation, Trajectory Prediction, Bounce and Spin, Scored by Theorems on a Table with Ground Truth poc_car_parking How a Car Turns Shortest — Dubins and Reeds–Shepp in Closed Form, and Hybrid A* Parallel Parking on an Occupancy Grid poc_carla_bridge One Scene, Two Worlds — Scoring a Photoreal Simulator’s Depth Against a Closed-Form Truth, Side by Side with Our Own World poc_connectome_across_decades How Much Does a Hand-Traced Wiring Diagram from 40 Years Ago Overlap Today’s Adult Worms? — The Era Difference Next to the Individual Difference poc_connectome_across_worms How Much of the Wiring Do Two Genetically Identical Worms Share? — Counting the Connections Present in All 8 Worms of a Developmental Series poc_connectome_lr_symmetry Is the Worm’s Wiring Bilaterally Symmetric? — The L/R-Swap Jaccard (set-overlap coefficient), Bracketed by a Closed Form and a Degree-Preserving Null poc_driving_commonroad Driving Our Own Driver Through Someone Else’s Scenario and Submitting to Someone Else’s Judge — CommonRoad Public Scenarios and TUM’s Official Checker poc_driving_crossing Level Crossings and Right of Way — Stop and Look, Never Enter During the Alarm or Into a Blocked Exit, Yield to the Wider Road poc_driving_decisions Decision Scenes — Mirrors, Predicting Amber from the Pedestrian Light, Giving Way to an Ambulance, Waiting for a Bus poc_driving_endless_map An Endless Map — Tiles Made Around the Car, Far Tiles Dropped, 50 km Without a Break poc_driving_humanoids Humanoids on the Crosswalk — Keep the Car’s Physics Exact, Draw the Walkers Cheaply poc_driving_japan_town Building a Real Japanese Town in Our Own World and Driving It — Roads from OpenStreetMap, Buildings from PLATEAU, Japanese Furniture and Rules poc_driving_lateral Lateral Motion — Slowing Before a Bend, Staying in the Lane, Keeping Left to Turn Left, Off-Tracking poc_driving_longitudinal Giving the Car Inertia and Slopes — Stopping Just Before the Line with Reaction and Braking Distance, and a Hill Start Without Rolling Back poc_driving_pass Overtaking and What You Cannot See — Wait for Sight Distance, Return Once in the Mirror, Do Not Obstruct the Ring, and Why Curve Mirrors Make Cars Look Far poc_driving_school The Driving School Opens — Cars and Signals on a Regulation Loop Course, Seen by LiDAR (laser ranging) and Camera, Scored by Theorems and Identities poc_driving_town Assembling One Town — Auto-Joining Driving-School Elements, Driving Through from Entry to Exit, and Scoring Every Stop Line on the Way poc_driving_traffic Moving Traffic and Blind Spots — a Child Behind a Parked Car, Meeting Oncoming Traffic, a Bus Stop, Bad Drivers poc_driving_weather Sun and Weather — When the Morning Sun Hides the Signal, How Fast You May Drive in Fog, Wet Roads and Headlamps at Night poc_em_split_merge_score Scoring Neuron Segmentations from Electron Microscopy — Over-Splitting and Over-Merging as Two Separate Numbers poc_em_wiring_errors Where Segmentation Errors Break the Wiring Diagram — Pixel Scores Overweight Splits and Underweight Merges poc_food_cutting_measure Measuring Food Cutting from Images — Knife Tracking, Slice Thickness, Cut-Surface Roughness and Cutting Force from Wrist Deflection, with Closed Forms and MuJoCo as the Truth poc_iqa_fsim_gmsd_vif Perceptual Indices FSIM (feature similarity index) / FSIMc (colour extension of FSIM) / GMSD (gradient-similarity deviation) / VIF Matched to Four Digits Against an External Truth — TID2013’s Three Author-Value Files and the Published Rank-Correlation Tables poc_iqa_tid2013 Measuring Image-Quality Metrics Against a Public Ground Truth — TID2013’s 3,000 Images × 971 Observers and the Authors’ Published Values as the Gate poc_kendama Kendama the Way the Pioneers Did It — A True-to-Shape Kendama Filmed by Two Cameras, the Ball’s Flight Predicted from Images Alone and Caught in the Big, Small and Base Cups poc_mt_hidden_fault Every Sensor Reads Normal, Yet the Machine Is Failing — How Much the MT Method Recovers from Univariate 3σ poc_peg_failure_recovery Detecting and Recovering Peg-Insertion Failures with a Rule Table — Whitney’s Contact States Instead of a VLM, MuJoCo as the Truth poc_pegsim_insertion Peg-in-Hole with a Compliant Wrist — Whitney’s Quasi-Static Geometry as the Gate, a Wrist Camera to Centre the Peg, MuJoCo Contacts to Check It poc_physarum_maze Slime-Mould Tubes Solve the Maze — Thickening and Thinning Alone Converge to the Shortest Path, Bracketed by a Theorem and Dijkstra poc_physarum_transport Slime Mould Solves Optimal Transport — Make the Source and Sink Mass Distributions and the Same Tube Dynamics Converge to the Earth Mover’s Distance poc_residue_crt Angles and Shifts No Single Phase Can Pin Down, Fixed by Bundling Phases of Different Periods — the Chinese Remainder Theorem in Images poc_segmentation_gauntlet The Segmentation Gauntlet — Ten Methods Across Six Worlds With Ground Truth, and Which Measure Is Blind to Which Failure poc_skeleton_run_length_vs_voi Run Length Forgives No Small Merge — ERL and VOI Weigh the Same Error Differently poc_spc Is the Process in Control, and Is It Capable? — Statistical Process Control from Closed-Form Alone poc_swc_tree_truth Grading Skeleton Measurement on Real Trees — NeuroMorpho SWC as Ground Truth, and What Projection Breaks poc_table_tennis_bounce Filming a Bouncing Table-Tennis Ball with a High-Speed Camera and Reading Restitution and Friction — Checked Against Published Values poc_table_tennis_rally_loop Reading Errors End the Table-Tennis Rally — How Much Noise and Latency Move the Landing Point, in Closed Form Before the Shot poc_table_tennis_spin Filming a Spinning Table-Tennis Ball and Reading Its Spin Two Ways — From the Curve and From the Markings poc_text_region_truth Where Is the Text, Without a Recogniser — Grading a Stroke-Width Detector on Text We Drew Ourselves poc_ttc_rss Time to Collision and Safe Distance — Optical-Flow τ and the RSS Closed Forms, Scored by the Driving-School World’s Truth poc_world_terrain Widening the World — Closed-Form Terrain, World-Space Materials and Procedural Trees and Pedestrians Win the Focus of Expansion Back from Flow poc_worm_core_persists The Worm Brain’s Core Is There from Birth — Counting the Cells That Stay in the Deepest Shell Across 8 Developmental Stages poc_worm_neurites_grow How Much Do a Worm’s Neurites Grow from Birth to Adulthood? — Measuring Eight Animals’ Skeletons with the Tree Ops and Setting the Result Beside the Paper poc_worm_synapses_vs_neurites Do Synapses Grow in Proportion to Neurites? — Shape Growth and Wiring Growth Set Side by Side, Cell by Cell, in Eight Worms
optics_sensing (34)	poc_chromatic_confocal Chromatic Confocal Displacement Sensor — A Rainbow Ruler from Glass Dispersion, Reading Height from the Colour that Comes Back poc_dual_energy_xray Bone and Glass in Meat, Separated by Material with Two X-ray Energies (Dual-Energy and Photon-Counting X-ray) poc_fiber_light_guide Optical Fibres and Light Guides — From the Material Table’s Fused Silica to Modes, Dispersion, Mode Field and Illumination Efficiency poc_fourier_ptychography Fourier Ptychography — 20x-Equivalent Resolution and Phase from a 4x Objective’s Wide Field, by Iterative Phase Retrieval poc_hyperspectral_foreign_matter Sorting Look-Alike Foreign Matter with Hyperspectral NIR — Two Real Datasets (Plastic Flakes, Foreign Objects on Pork Belly) and a Material-Table Simulation of the Failure Modes poc_itof_multifreq Indirect Time of Flight, Multi-Frequency — Higher Frequencies Measure Finer, but Wrapping, Multipath, Flying Pixels and Harmonics Break It poc_lens_file_roundtrip Reading a Lens Design File (.zmx), Analysing It, Fixing It and Writing It Back — Scored Against Two Other Readers and a Round Trip poc_lens_global_search Glass Substitution and Multi-Start Search — Scored Against the Thin-Achromat Closed Form and the Third-Order Best-Form Bending poc_lens_merit_operands Designing a Triplet from a Table of Requirements — A Merit Function with Edge-Thickness, Centre-Thickness and Air-Gap Bounds, Scored Against Closed Forms and an Independent Implementation poc_lens_solves_afocal Keeping a Design’s Relations as Solves — A Double-Gauss Type Whose Focus and F-Number Follow the Stop, Afocal Telescopes, a Curved Image Surface and Odd Aspheres poc_lens_tolerancing Budgeting Lens Manufacturing Tolerances through MTF (modulation transfer function), Yield, and Compensator Travel poc_lockin_imaging Per-Pixel Quadrature Demodulation (Lock-in) — Ring-Illumination Normals, Coded-Light Daylighting and Lock-in Thermography, Scored Against Closed Forms and the Rice Phase Distribution poc_material_optical_library A Material Optical-Property Library — 86 Glasses, Crystals, Semiconductors, Metals, Liquids and Plastics in One Table, Scored on Catalogue Values and a Second Implementation poc_mueller_dofp_observability A Four-Angle Polarization Camera Leaves Seven Mueller (4-by-4 polarization-transfer matrix) Dimensions Unseen poc_nir_silicon_transmission Near-Infrared Inspection Through a Silicon Wafer — Choosing the LED Wavelength from the Source × Wafer × Sensor Integral poc_noncoaxial_optics Non-Coaxial Optics — a Coaxial-Illumination Beamsplitter Paints a False Defect on a Mirror-Like Part, Removed by a Coating or a Wedge; Fold Mirrors Shrink the Machine poc_omni360_inspection Measurable Omnidirectional Inspection, Stereo Display and Moving Viewports poc_optics_drawings Optical Drawings Straight from the Calculation — Lens Layouts, Vision-Setup Drawings and ISO 10110 Element Drawings as SVG / DXF, Scored by Reading the Written Files Back poc_photograph_through_prescription Photographing a 3-D Scene Through the Actual Lens Prescription — Depth of Field, Cat’s-Eye Bokeh, Corner Illumination, Colour Fringes and Ghosts, Scored Against Closed Forms, Existing Ops and an Independent Trace poc_pixel_shift Pixel-Shift Imaging — Shift the Sensor One Pixel and False Colour Vanishes, Half a Pixel and Aliasing Vanishes; the MTF (modulation transfer function) Does Not Rise poc_plenoptic_camera A Prescription-Based Plenoptic Camera poc_pocket_interreflection Counting Interreflection in a Machined Pocket to Convergence — The Direct-Light Model Fits with Albedo 1.32, the Converged Model Returns the Truth poc_simcal_pixel_shift Calibrating Pixel-Shift Offsets and Pixel Aperture from the Images — Where Only Stripes Are Seen, the Shift Is Fixed in One Direction Only poc_simcal_thin_film Calibrating a Thin-Film Model to Real Images — and Giving No Number to What the Data Do Not Determine poc_slanted_edge_sfr_limits Slanted-Edge SFR Misreads MTF50 (spatial frequency at 50% MTF) Through Gamma as Well as Edge Angle poc_spectrometer_illumination Spectrometer and Illumination Trains — Where the Bandwidth Comes From, and Whether the Lamp Shows in the Field poc_tdi_linescan TDI (time-delay integration) Line Scan and Line-Scan Lenses — Stages Reveal the Defects, a Sync Error Smears Them, and a C-Mount Lens Loses the Ends of a Long Sensor poc_thin_film_reflectometry Thin-Film Thickness by Spectral Reflectometry — Scored on Public Measured Data, then Fringes, Interference Colours, FFT versus Model Fit and Thickness Maps poc_tof_camera Indirect and Direct Time of Flight on One 3-D Scene — Multipath, Mixed Pixels, Pile-up and Volume Error poc_water_inspection_images How Water Looks in Inspection Images — Pool-Floor Caustics, a Bottle from the Side, a Wet Plate and a Hull Under Water, Scored Against Closed Forms and Second Methods poc_water_transparent_media Water and Transparent Media — Ocean Waves, Surface Refraction, Colour Under Water and the Caustic of a Bottle, Scored Against Closed Forms, Published Values and Second Implementations poc_wavefront_aberration_limits The Marechal Approximation Breaks at Different RMS Errors for Different Aberration Shapes poc_zmx_public_verify Verifying Public .zmx Prescriptions Independently and Scoring Them as Inspection Lenses poc_zoom_configurations A Zoom Lens as Differences of One Prescription — Scored Against the Two-Thin-Lens Closed Form and a Round Trip Through the Design File’s Multi-Configuration Table
analysis (20)	poc_attention_identities Every Speedup Is the Same Arithmetic Regrouped: Scoring Attention with Identities poc_beats_fringes_and_screens One Beat — A Two-Slit Fringe and a Print Moire (beat fringe between periodic patterns) Are the Same Mathematics poc_calipers_under_illusion Auditing the Instrument with Illusions - Where a Caliper Fails, and Why poc_complex_plane_fields Seeing the Complex Plane as an Area — When the Picture Proves the Theorem poc_connectome_motor_bottleneck Motor Quantisation — Where the Command Dimension Collapses Between Brain and Muscle (the Fly’s Neck and an RL Policy’s Joints on One Scale) poc_em_branch_territory Branch Territories — Handing Every Voxel Its Nearest Branch, Not Just Its Distance, Makes Per-Branch Volume and Radius Countable poc_endless_zoom_and_turning_solids Endless Zooms and Turning Solids: Making the Return Itself the Ground Truth poc_four_dimensions_by_three_d_tools Scoring Four-Dimensional Claims with Ordinary Three-Dimensional Operators poc_geodetic_benchmarks_real There Are Two Kinds of Height, for Real — Putting a Height-Frame Mix-Up Under a Detector with 523 Published Survey Marks poc_gravitational_lens_invariants Scoring Gravitational-Lens Images with Ordinary Industrial Measurement Operators poc_illusions_and_perpetual_drawing Scoring Endlessly Generated Pictures with Identities, Not with the Eye poc_measurement_system_analysis How Much of That Number Is Your Measuring - Gauge R&R (gauge repeatability and reproducibility) and Measurement Uncertainty poc_microns_brain_wave The MICrONS Brain Wave — How Much of the Measured Response Does the Wiring Explain in 1 mm^3 of Visual Cortex poc_one_stroke_epicycles A Photograph as One Line, Drawn by Rotating Circles — Tone, Stipple, Tour, Fourier Series, G-code poc_periodic_video_boundary Testing the Periodic Boundary of Temporal Operators with a Seamless Loop poc_pod_lighting The Resolution Formula Does Not Tell You What You Will Find - Probability of Detection per Lighting (MIL-HDBK-1823A) poc_theorems_as_pictures Theorems as Gates — Apollonian Gaskets, Ford Circles, Geodesic Domes, Phyllotaxis, IFS, Space-Filling Curves poc_vanishing_detail_and_morphing_area The Exact Distance at Which Detail Vanishes, and the Area of a Changing Shape poc_what_a_picture_cannot_check What a Picture Cannot Check — Scoring Dynamical Systems and Minimal Surfaces by Identity and Definition poc_zernike_aberrations Scoring an Aberration as a Picture: Zernike Polynomials (orthogonal aberration polynomials on a circular pupil) and the Point Spread Function
diagnostics (10)	poc_bearing_diagnosis Seven-Level SNR Sweep on Synthetic Bearing Signals — Raw versus Envelope Detection Rates poc_cold_chain_excursion The Cold-Chain Temperature Record — Where You Taped the Logger Is the Verdict poc_fabric_defect Defects Buried in a Periodic Background — What a Pooled ROC (true-positive versus false-positive curve) Hides poc_machine_condition_fusion Fusing thermal, vibration and geometry for machine health — three sensors, one fact poc_prnu_camera_fingerprint Camera Fingerprints (PRNU): Which Camera Took This? — The Fingerprint Grows With Frame Count and Dies at the Save Button poc_pv_thermal_survey Drone Thermography of a PV Plant — You Think You Are Measuring Temperature Difference, but You Are Measuring Wind and Viewing Angle poc_solar_el_inspection Power loss from solar-cell EL images — dark is not the same as inactive poc_solder_fillet_aoi Solder fillet AOI — three ring lights are a 3-level tilt quantiser, and 70 % of the fillet height sits in the dark poc_thermography_ndt Depth of a Subsurface Defect by Pulsed Thermography poc_weld_radiograph_porosity Porosity in Weld Radiographs — Closing With the Share of Images Misgraded by One Class
segmentation (9)	poc_active_contours Active Contours and Level Sets — Checking With Closed Forms How a Contour Shrinks, Enters a Concavity and Stops at an Edge poc_cell_counting Counting Overlapping Cells — Count, Over-Segmentation and Under-Segmentation as Three Numbers poc_dense_bubble_count Counting Dense Bubbles — When the Overlap Is Too Deep to Decide, Return an Interval Instead of a Count poc_graph_hierarchy_segmentation Graph, Hierarchical and Threshold Segmentation — Max Flow = Min Cut, Ultrametrics, and Turning a Knob From Coarse to Fine poc_leaf_disease_area Leaf disease severity — colour axes survive the lighting; the grade is decided by the leaf mask and the edge convention poc_mri_bias_field MRI Bias Field and Tissue Area — Grey and White Matter Fail in Opposite Directions, and the Sum Hides It poc_timelapse_growth A Growth Time-Lapse as Space-Time Connected Components poc_vegetation_cover Counting Crop Green — Ground Truth as Per-Pixel Leaf Area Fraction poc_weed_rice_ratio Weedy-Rice Cover — Supervised Linear Discrimination without Deep Learning
geometry (7)	poc_dfm_thickness_overhang Manufacturability from geometry alone — faces that sit on the threshold flip when you smooth them poc_mesh_quality_repair Repair the mesh, then measure — the defect count clears, the quantity does not poc_pallet_load_utilization Pallet load utilization — one number gives voids and overhang the same value poc_panorama_drift Chain the Neighbours Together and You Cannot Get Back Where You Started poc_print_warpage_risk Warpage lives in the layer history — averaging the area throws the placement away poc_symmetry_restoration Restoring what is missing by symmetry — the plane you assume is the lie you get poc_xyt_event_surface The Arrival-Time Surface as an Isosurface in (x, y, t)
imaging quality (6)	poc_colormap_readability Pseudo-colour changes what the reader decides — counting edges that are not there poc_emva1288_in_camera_processing In-Camera Processing Makes Datasheet Numbers Lie Plausibly - Denoising Adds 83 % to the Quantum Efficiency, the Standard’s Check Misses It, Noise Correlation Catches It poc_emva1288_sensor Measuring a Camera Without Buying One — Recovering Quantum Efficiency, Gain and Dark Noise from a Planted Sensor with the EMVA 1288 (image-sensor characterization standard) Procedure poc_moire_screen Can Display-Inspection Moire (beat fringe between periodic patterns) Be Told From Real Non-Uniformity? poc_veiling_glare Veiling Glare Breaks Contrast Measurement — MTF (modulation transfer function) Passes While Black Level Fails poc_zebra_stripes_fly_eye A Fly’s Eye Closing In on Stripes — Do Zebra Stripes Really Spoil a Compound Eye’s Sense of Distance, and Would a Fibonacci Eye Do Better?
photometry (6)	poc_allsky_cloud_cover All-Sky Cloud Cover — Counting Pixels Is Biased by Position poc_astro_photometry How Many Frames for What Photometric Precision? poc_exoplanet_transit Exoplanet transit from aperture photometry — depth and duration fail separately poc_nuclei_ploidy Ploidy From Integrated Nuclear Intensity — Area Cannot Separate It poc_real_sky_photometry Planting Known Stars in a Real Deep Field — Contamination Lies About the Measurement and the Confidence in the Same Direction poc_solar_limb_darkening Where Is the Edge of a Limb-Darkened Disc? The 50 % Rule Reads the Radius Small
separation (6)	poc_colocalization_crosstalk Colocalization lies under bleed-through — Pearson and Manders break in different places poc_pigment_unmixing Peeling Layers With Many Wavelengths — Underdrawing, Ground, Glaze and Fading, Truth in Hand poc_polarization_specular Stripping Specular Reflection With Polarisation — Truth From the Fresnel Equations poc_real_stain_unmix Separating a Real Immunostain by Colour — The Watchdog Was Blind to Exactly the Error It Should Catch poc_recycling_sorting Sorting mixed waste by material — what a preprocessor can erase is decided by algebra poc_sea_ice_concentration Sea-Ice Concentration — The Answer Depends on How Mixed Pixels Are Counted
calibration (5)	poc_camera_calibration A Reprojection Error of 0.05 px Guarantees Nothing poc_fly_optomotor_steering Holding a Course with a Fly’s Optic Lobe Alone — From the Lamina to the Steering, Without Learning poc_public_camera_heading Where Is the Public Camera Looking — The Orientation of a Fixed Camera Whose Only Published Fact Is Its Position, from the Picture Itself poc_public_camera_heading_real Where Is the Public Camera Looking, for Real — Hunting the Sun in 807 Road Cameras, Fixing the Heading from One Sunset and Checking It Against the Road poc_thermal_drift_metrology How Much Camera Thermal Drift Costs a Dimensional Measurement
detection (5)	poc_good_sample_variation_model Flagging What Differs from Aligned Good Samples — a Variation Model with a Declared False-Alarm Rate, and Where Real Images Break It poc_patch_anomaly Anomaly Detection from Good Samples Only — Classical Patch Features, a Per-Position Distribution Against a Memory Bank on One Yard-Stick, Down to a Recall-Guaranteeing Threshold poc_real_defect_floor How Faint a Defect Can Still Be Found — Planting a Known Truth in a Real Background poc_search_sweep_width Sweep Width — One Number Measured from Aerial Images Decides Whether the Search Works poc_si_wafer_pl_defect_visibility Why a Thin Groove Vanishes in a PL Image — a Longer Diffusion Length Hides Only Shadow Grooves, and Makes Sink Grooves Stand Out
registration (5)	poc_change_detection_misreg Change detection under misregistration — false positives are edge bands, with a cliff poc_print_registration Print Misregistration from the Sheet — A Halftone Is a Lattice, So the Answer Is Not Unique poc_registration_basin The Convergence Basin of Point-Cloud Registration — How Far Off Can the Initial Pose Be? poc_reproducible_icp Registration That Does Not Move by a Single Bit When the Points Are Shuffled — FP64 Reductions by the Ozaki Scheme, with the Error Falling in Steps under a Guaranteed Bound; Slow on the CPU, and GPU Speed Is Left to cuBLAS Emulation poc_template_tracking Template Tracking Drifts Quietly Before It Ever Loses the Target
visualization (5)	poc_eye_to_brain What the Compound Eye Sees, and Where the Brain Answers — Trace an Ommatidium and the Response Travels the Wiring poc_flybrain_pointcloud Drawing the Male Fly Brain as 126,104 Cell Bodies — A New Point-Cloud Renderer, Scored Against Four Answers from Outside the Picture poc_live4d Living Tissue in 3D+t Without a Generator — Magnify, Flow, Interpolate, Height, All Against Truth poc_malecns_activity_wave Watching a Pulse Travel the Wiring on the 3-D Fly Brain — Connectome vs Degree-Preserving Shuffle poc_video_cube A Clip as a Space-Time Cube — What Passed Where, and When, in One Solid
motion (4)	poc_particle_tracking Particle Tracking as a (row, column, time) Volume — Mislinks Come in Two Directions poc_river_surface_velocity River Surface Velocity — Separating a Discharge Proxy from Actual Discharge poc_traffic_counting Counting in (x, y, t) — Vehicles Passed, Occlusion, and One Constant: L/V poc_warehouse_flow Where the Warehouse Dwell Came From — Count Waiting Without Its Kind and Everything Is Just Congestion
inspection (4)	poc_em_second_opinion A Second Opinion for EM Connectome Proofreading — Membranes Belong Only on Label Boundaries poc_illumination_cone_vs_na Illumination Cone versus Imaging NA — Change Only the Opening of the Light Cone and the Same Dent, Scratch and Satin Patch Vanish or Appear poc_print_layer_inspection Print Layer Inspection — Closing the Shape → Layer → Path → Image Loop and Catching Planted Defects by the Numbers poc_sam_hybrid_bonding_voids Find Hybrid-Bond Voids by Echo Phase, Not Brightness - Small Voids Hide in the Amplitude Image and Light Up Inverted in the Phase Image
tomography_3d (4)	poc_battery_ct_degradation Battery cell degradation by CT — the swelling shows outside, the cause stays inside poc_battery_electrode_tortuosity Electrode tortuosity from CT — the rule of thumb only sees porosity poc_ct_void_morphology Collapsing joint voids into one number — what the number drops is the shape that matters poc_die_tilt_tsv_overlay Die tilt and TSV overlay from one CT — tilt fakes rotation too
depth (3)	poc_focus_stacking Focus Stacking — The All-in-Focus Image and the Depth Map Are Different Things poc_lightfield_depth Depth From a Light Field — A Light Field of Known Depth, Confronted With Its Nulls poc_real_stereo_depth Measuring on a Real Stereo Photograph — Three Stumbles Synthesis Never Produces
forensics (3)	poc_forensics_roc Forgery Detection as an ROC (true-positive versus false-positive curve) — Not the One Image Found, but Detection at a Fixed False-Positive Rate poc_fresco_craquelure Craquelure networks — of three indicators, only junction degree breaks under imaging conditions poc_video_physics_consistency Physical Consistency of Footage — Ballistic or Thrusted, and Was the Clock Stretched?
perception_templates (3)	poc_bev_sensor_fusion Fusing two sensors into a bird’s-eye grid — a calibration that passes in pixels turns into metres at range poc_code_matching_breakdown Matching on the Direction of Brightness Change — NCC Falls at 10 % Occlusion, Code Matching Holds to Over 60 % poc_safety_clearance Human-machine clearance — swap the body for a point, and the hazard vanishes with it
restoration (3)	poc_camera_shake_deblur How Much Camera Shake Can Be Undone — Make the Kernel, Apply It, Invert It, Compare poc_dehazing Removing Haze — Ground Truth From the Scattering Model, Transmission and Airlight Scored Apart poc_real_deblur_honesty Deblurring a Real Photograph — Three Rulers, Three Different Winners
terrain (3)	poc_crop_phenotyping Crop leaf area from above — folded by projection before it is ever hidden poc_dem_terrain Measuring Terrain — Slope, Flow and Insolation Against Closed Forms poc_lidar_terrain_change Earthwork on a slope — align first and the scar gets shallower
decoding (2)	poc_barcode_1d Where a 1-D Barcode Stops Reading — Counting Misreads and Unreadables Separately poc_matrix_code_reading Reading a Binary Matrix Code — Geometry Always Dies First
morphology (2)	poc_bilateral_asymmetry Measuring Bilateral Asymmetry — The Symmetry Plane Gets Dragged by the Deformation poc_vessel_network Extracting a Vessel Network — Spurs, Overestimated Radii Near Branches, and a Fragile Exponent
optics (2)	poc_compound_eye The Fly’s Compound Eye Is a Light-Field Sensor — Neural Superposition Pays Only Up to the Knee poc_fly_vision The Fly’s Visual Front End as a Chain of Operators — Turning and Walking Through a Synthetic Sky, What Can and Cannot Be Read
ranging (2)	poc_dtof_ranging Ranging by Counting Photons — How Many for How Many Millimetres? poc_leak_localization Digging Where the Sound Says — A Clean Correlation Still Digs in the Wrong Place
shape_descriptors (2)	poc_real_texture_invariance Rotating Real Textures — Rotation Invariance Holds Only Where It Is Not Needed poc_rotation_invariance_audit Which Quantities Really Survive a Rotation — Auditing Invariance on a Real Coin
signal_processing (2)	poc_rail_corrugation Measuring Rail with a Chord — At the Wavelengths Where the Transfer Function Is Zero, Any Amplitude Reads Zero poc_web_roll_periodicity Naming the Damaged Roller from a Period — You Run Out of Evidence Before You Reach the Cliff
verification (2)	poc_glyph_typo_detection Finding and Fixing Wrong Characters Without Recognising Them — the Threshold Comes from Typeface Spread poc_larval_connectome_reservoir A Larval Connectome as a Reservoir Reads Digits — and the Wiring Is Not What Does It
vibration (2)	poc_beam_modal_video Modal identification from video — frequency survives to the end, damping lies first poc_motion_magnification Micro-Vibration of a Structure From Video — Does Motion Magnification Help You Measure?
colour (1)	poc_white_balance Colour Constancy (White Balance) — No Method Works, Only Conditions Do
rectification (1)	poc_document_scan Straightening a Hand-Held Document Photo — Keystone Correction and Shadow Removal Against Ground Truth
space (1)	poc_star_tracker How One Star Image Reveals Satellite Attitude
tomography (1)	poc_ct_fidelity Where CT Reconstruction Starts to Break as Projections Are Removed
super-resolution (1)	poc_superresolution_limits Does Super-Resolution Add Information? Downsample With the Truth in Hand, Restore, Count

Einen Operator finden

3,629 Operator-Notizen (Aufrufform, Typvertrag, HALCON-Pendant, Literatur, Provenienz) und 69 Familien-Leitfäden. Einstiegspunkte nach Dimension:

Gemessene Abdeckung: evolvierbare Ops 942/942, typisiertes Ledger 2652/2664, Fassade fullseye.<name> 724/1514 — die Fassade ist erst zur Hälfte abgedeckt.

Gemessener Inhalt: von 3629 Notizen verweisen 3595 auf mindestens ein lauffähiges Beispiel (34 ohne), 3428 haben einen Nutzungsabschnitt ab 120 Zeichen (201 nur eine Zeile). Die Struktur (Aufrufform, Typen, anschließbare Ops) haben alle 3629.

Dimension	Ops	Einstieg
2d	959	INDEX
drive	717	INDEX
optics	483	INDEX · guide
3d	376	INDEX
math	114	INDEX · guide
segmentation	59	INDEX · guide
annotate	51	INDEX · guide
oned	49	INDEX
gfx2d	44	INDEX
generative	42	INDEX · guide
imgmetrics	42	INDEX · guide
reprconv	42	INDEX
spc	41	INDEX
tomography	32	INDEX
piv	29	INDEX · guide
conngraph	28	INDEX · guide
acoustics	27	INDEX · guide
dem	25	INDEX · guide
printpath	23	INDEX · guide
flyvision	22	INDEX · guide
calib	21	INDEX · guide
graph	20	INDEX
specular	20	INDEX · guide
quat	19	INDEX · guide
multivar	18	INDEX · guide
lightfield	17	INDEX · guide
measure1d	17	INDEX · guide
photon	17	INDEX · guide
imgforensics	16	INDEX
shape2d	16	INDEX · guide
shapestat	16	INDEX · guide
videostream	16	INDEX · guide
astrostack	14	INDEX
emproof	14	INDEX · guide
fileio	14	INDEX
live4d	14	INDEX · guide
profile	12	INDEX · guide
blob	11	INDEX · guide
colortransport	11	INDEX
volcolor	11	INDEX
llmcore	10	INDEX · guide
simcal	10	INDEX · guide
vx	10	INDEX · guide
geocam	9	INDEX · guide
interferometry	9	INDEX · guide
motionmag	9	INDEX · guide
roughness	9	INDEX · guide
rangedoppler	8	INDEX · guide
codematch	6	INDEX · guide
converge	6	INDEX · guide
videocube	6	INDEX · guide
residue	5	INDEX
cadmap	4	INDEX
aoi	3	INDEX · guide
fit	3	INDEX
text	3	INDEX

Nach Namen suchen mit py -3.11 imgevolve.py ops --search edge; die vollständige Tabelle ist OP_CATALOG.md, der dimensionsübergreifende Einstieg ops/INDEX.md.

Abruf durch KI-Assistenten: der maschinenlesbare Index ist OP_INDEX.json, die Anleitung steht in AI_RAG_GUIDE.md.

Benutzung (für Anwender — zuerst diese vier)

Dokument	Inhalt
GETTING_STARTED.de.md	In 5 Minuten loslegen: Installation → erste Pipeline → Ausführung aus Studio, CLI oder Code → Ergebnis ansehen
INSTALL.de.md	Vollständige Anleitung zur Einrichtung: Voraussetzungen, pip install -e . und die Wahl der passenden Extras, Installer für Windows/Linux, Minimalaufbau und Einbettung, Fehlerbehebung
STUDIO_GUIDE.de.md	Vollständiger Leitfaden zu Fullseye Studio: die drei Panels, Operator-Browser, schrittweise Ausführung, Regler, Inspector, Perception-Panel, Befehlspalette, Tastenkürzel, Export
ENGINE.de.md	FullseyeEngine (Entwurf → Ausführung): sämtliche Methoden, Verwendung aus Python, das CLI-Kommando run, Aufruf aus anderen Projekten

---

Operator- / API-Referenz

Dokument	Inhalt
OPERATORS.md	Katalog aller 897 Operatoren (48 Kategorien, nach sort gegliedert, mit den entsprechenden APIs von HALCON/OpenCV/scikit-image/MATLAB)
EXAMPLES.md	Beispielcode je Operator, samt dem äquivalenten Aufruf in anderen Bibliotheken
OP_INDEX.json	Maschinenlesbarer Operatorindex (neu erzeugen mit imgevolve.py index)
ADDING_OPS.md	Wie man einen neuen Operator hinzufügt (Evolution, Codegen, Katalog und Index ziehen automatisch nach)
../examples/README.md	Lauffähige Ende-zu-Ende-Beispielskripte

Perception-Stack (Robotik / Vision)

Dokument	Inhalt
PERCEPTION.md	Einseitige Referenz zum Perception-Stack (stereo / terrain / detect / registration / pose / flow / motion)
PERCEPTION_REALDATA.md	Messungen an realen Videoclips (Video-I/O und ehrlich ausgewiesene Messwerte)

HALCON-Parität / Abdeckung (ehrliche Offenlegung, honest disclosure)

Dokument	Inhalt
HALCON_PARITY.md	Stand der genuine (wirklich gleichwertigen) Implementierungen (981/2313) — ob ein Operator tatsächlich dasselbe leistet und nicht bloß denselben Namen trägt
HALCON_COVERAGE.md	Abdeckung, gemessen durch tatsächliches Scrapen der offiziellen Referenz (v2605)
LIB_COVERAGE.md	Bibliotheksübergreifende Abdeckung (Aufnahme markanter Operatoren jenseits von HALCON)
PARITY_CROSSBACKEND.md	Parität, belegt durch die Übereinstimmung unabhängiger Implementierungen (scipy/cv2/skimage) über die Backends hinweg

Qualität / Provenienz / Reproduktion

Dokument	Inhalt
ACCURACY_BENCH.md	Ständige Genauigkeitstabelle: evolvierter Champion gegen Null-Baseline (Holdout)
CHAIN_FUZZ.en.md	Der Chain-Fuzzer — eine dritte Schicht der Qualitätssicherung, die zu Ketten verbundene Operatoren durchrüttelt (Diffusion → Konvergenz → minimale Reproduktion)
EVOLUTION_ENVIRONMENT.en.md	Entwicklungsumgebung für evolutionäre Algorithmen (Diffusion → Kontraktion → Promotion; das Counterfactual-Utility-Gate und die Brücke zwischen den beiden Operatoruniversen)
PROVENANCE.md	Provenienz: der Nachweis, dass alles auf Basis veröffentlichter Algorithmen selbst gebaut wurde
REFERENCES.md	Die Literatur, die jeden einzelnen Operator belegt
REPRODUCE.md	Wie sich die Zahlen reproduzieren lassen: seed-gesteuert und deterministisch
STATUS.md	Wo das Projekt steht und was geplant ist (plan_ref)

Release Notes / Design

Dokument	Inhalt
V13.md	v13 = Praxistauglichkeit + projektübergreifendes Packaging + Perception-Stack
V14.md	v14 = Perception-Stack fertiggestellt (Motion + Härtung)
STUDIO_UX.md	Absicht und Hintergrund der UX- und Design-Verbesserungen an Fullseye Studio

---

Schnellbefehle

py -3.11 -m pip install -e ".[opencv,gui]"     # Installation (Bild-I/O + Studio)
py -3.11 studio.py                              # Fullseye Studio starten (= fullseye-studio)
py -3.11 imgevolve.py ops --search edge         # Operatoren suchen (= fullseye ops --search edge)
py -3.11 imgevolve.py apply gauss_filter in.png out.png --a 0.6
py -3.11 imgevolve.py run pipeline.json in.png --out result.png
py -3.11 imgevolve.py coverage                  # ehrliche Abdeckungszahlen

Aus Python heraus:

import fullseye, numpy as np
out = fullseye.run_pipeline(frame, ["gaussian", "sobel_amp", "otsu"])
eng = fullseye.FullseyeEngine.load("pipeline.json"); result = eng.run(frame)

---

Echte Ausgaben klassischer 2-D-Bildverarbeitungsoperatoren

Echte Ausgaben des Physical-AI- und Sensor-Suites

Dokumentkarte — alle 303

Die vollständige Karte, damit kein Dokument vom Index aus unerreichbar ist (die 3,629 Operator-Notizen und 69 Familien-Leitfäden unter docs/ops/ über den Operator-Abschnitt oben; Artikel über articles/). Die Texte sind überwiegend japanisch.

Getting started(12)

Dokument	Inhalt
GETTING_STARTED.md	Erste Schritte (in 5 Minuten startklar) → GETTING_STARTED.de.md · Original (ja)
INSTALL.md	Installations- und Einrichtungshandbuch → INSTALL.de.md · Original (ja)
STUDIO_GUIDE.md	Vollständiger Leitfaden zu Fullseye Studio → STUDIO_GUIDE.de.md · Original (ja)
STUDIO_UX.md	Fullseye Studio — UX & design pass (v15)
EXAMPLES.md	imgevolve — sample code (cross-library recipes)
EXAMPLES_3D.md	Fullseye 3-D ビジョン — 事例ギャラリー(EXAMPLES_3D) (ja)
GALLERY.md	Fullseye Gallery → GALLERY.en.md · Original (ja)
REPRODUCE.md	Reproducing the numbers
CONSUMER_APPLICATIONS.md	Fullseye — per-project applications (honest, 2026-08-15)
3DGS_USAGE.md	Fullseye 3DGS – Anwendung (ein einziger Befehl) → 3DGS_USAGE.de.md · Original (ja)
TERRAIN_WALK.md	Walking a Character Over Terrain (sim-native, no GPU required) → TERRAIN_WALK.en.md · Original (ja)
GSPLAT_NATIVE_WINDOWS.md	Building native gsplat on Windows (RTX 5090 / torch cu128) — a proven procedure → GSPLAT_NATIVE_WINDOWS.en.md · Original (ja)

Operator reference(9)

Dokument	Inhalt
OPERATORS.md	imgevolve — cross-library operator catalog
OP_CATALOG.md	Fullseye Operator Catalog — AI capability ledger
OP_COMBINATION_MATRIX.md	fullseye 3D op × op Combination Matrix (prioritized by feasibility × differentiation) → OP_COMBINATION_MATRIX.en.md · Original (ja)
CONVERSION_MATRIX.md	型変換の行列 ―― 穴と不具合の点検 (ja)
CONNECTIVITY.md	Fullseye connectivity — devices, cameras & industrial protocols
MATCH_3D_MATRIX.md	fullseye 3D Vision Toolkit (for Physical AI, differentiating from HALCON/OpenCV) → MATCH_3D_MATRIX.en.md · Original (ja)
GENERAL_ALGORITHMS.md	Allgemeine Algorithmen implementierbar machen — algo-c Kompatibilitäts-Roadmap → GENERAL_ALGORITHMS.de.md · Original (ja)
ADDING_OPS.md	Adding an operator
WAVE0_STABLE_SLOTS.md	Wave-0: stable op slots + name-pinned champions

Retrieval for AI assistants(1)

Dokument	Inhalt
AI_RAG_GUIDE.md	Fullseye als RAG eines KI-Assistenten nutzen (für Claude Code) → AI_RAG_GUIDE.de.md · Original (ja)

Literature layer (manufacturing, driving and optical-metrology knowledge → ops)(9)

Dokument	Inhalt
literature/INDEX.md	文献層 —— RAD コーパスからの、op に繋がる来歴つき要約 (ja)
literature/mech_design.md	文献層: メカ設計(機械設計) (ja)
literature/mechatronics_parts.md	文献層: メカトロ部品(アクチュエータ・センサ・電気部品) (ja)
literature/manufacturing_processes.md	文献層: 製造工程(あらゆる製造技術の開発に) (ja)
literature/driving_simulation.md	文献層: 運転のシミュレーションと評価 (ja)
literature/sensor_simulation.md	文献層: センサーの模擬(カメラ・LiDAR・レーダー) (ja)
literature/optical_metrology.md	文献層: 光学計測と外観検査の信頼性(厳選) (ja)
literature/OSS_LANDSCAPE.md	既存 OSS の地図 —— すでにある道具と、Fullseye との繋ぎ方 (ja)
literature/oss_landscape_notes.md	OSS landscape notes (verified 2026-09-21)

Perception and sensors(7)

Dokument	Inhalt
PERCEPTION.md	Fullseye perception stack — one-page reference
PERCEPTION_PHYSICAL_AI.md	Physical-AI perception pipeline (fullseye / imgevolve, v18.3, 2026-08-15)
PERCEPTION_REALDATA.md	v15 — perception stack on real footage (video I/O + honest field measurements)
SENSOR_PLAYBOOK.md	Fullseye Sensor Playbook — センサー種別ごとの推奨 op パイプライン (ja)
HIGHSPEED_VISION.md	高速ビジョン(1ms 視覚フィードバック)を物理シミュ上でやる — 計画 (ja)
SAMPLE_IMAGE_REFERENCES.md	Sample images — provenance, source papers & public repositories
BBB_SENSING.md	BBB sensing — 複眼光場 × コネクトーム(研究方向) (ja)

HALCON correspondence(6)

Dokument	Inhalt
HALCON_PARITY.md	HALCON parity — what imgevolve genuinely DOES (not just names)
HALCON_COVERAGE.md	HALCON operator coverage (measured vs the real reference)
HALCON_COVERAGE_HONEST.md	HALCON Coverage — the honest denominator (updated 2026-08-18) → HALCON_COVERAGE_HONEST.en.md · Original (ja)
HDEVELOP_FIDELITY.md	Fullseye Studio — HDevelop Fidelity Spec (North Star) → HDEVELOP_FIDELITY.en.md · Original (ja)
HDEVELOP_DEV_OPS.md	HDevelop dev_* operator family — the UI/display control surface (Studio north star) → HDEVELOP_DEV_OPS.en.md · Original (ja)
LIB_COVERAGE.md	Multi-library coverage (imgevolve is not HALCON-only)

Fullseye Script(3)

Dokument	Inhalt
FSCRIPT_DECISION.md	Fullseye Script / Runtime — 要件定義と基本設計(確定案) (ja)
FSCRIPT_LANGUAGE.md	Fullseye Script — Language / Runtime / Watch IDE Design Specification (North Star) → FSCRIPT_LANGUAGE.en.md · Original (ja)
FSCRIPT_MEASUREMENTS.md	Fullseye Runtime — 実測記録 (2026-08-15) (ja)

Quality and honesty(13)

Dokument	Inhalt
KNOWN_ISSUES.md	Known Issues — 調べた欠陥の記録(2026-08-30 開始、最終の節は §52 = 2026-09-26) (ja)
STATUS.md	imgevolve — status / plan (plan_ref)
ACCURACY_BENCH.md	Accuracy benchmark — champion vs null (holdout)
BENCH_VS_OPENCV.md	imgevolve GPU op vs OpenCV (CPU) throughput benchmark → BENCH_VS_OPENCV.en.md · Original (ja)
PARITY_CROSSBACKEND.md	Cross-backend parity — independent implementations agree at the tested points
CHAIN_FUZZ.md	Chain Fuzzer (chain fuzz) — a third quality-assurance layer that shakes ops by wiring them into chains → CHAIN_FUZZ.en.md · Original (ja)
PROVENANCE.md	Provenance
OP_COUNT_HISTORY.md	op の数の推移(版ごと) / Operator counts by version (ja)
REFERENCES.md	imgevolve — operator research provenance
AUDIT_2026_08_12.md	imgevolve implementation audit — 2026-08-12
RELEASE_CHECKLIST.md	リリース手順書 — 同じ間違いを繰り返さないための門 (ja)
I18N.md	Fullseye の多言語対応 — 全体設計 / Internationalisation design (ja)
VALIDATION_CONTRIBUTING.md	Reporting validation on real hardware or real data → VALIDATION_CONTRIBUTING.en.md · Original (ja)

Performance and GPU(4)

Dokument	Inhalt
GPU_ACCEL_PLAN.md	op の GPU 化ロードマップ(E2E の本丸) (ja)
GPU_OPTIMIZATION_PATTERNS.md	GPU Optimization Design-Pattern Catalog (for RTX 5090 / Blackwell sm_120) → GPU_OPTIMIZATION_PATTERNS.en.md · Original (ja)
design/FAST_TWINS.md	CPU 高速 twin(fast.py)— 実装記録と実測(2026-09-03) (ja)
design/PERF_MEMORY_VIDEO_SURVEY.md	op の高速化・省メモリ化・動画処理 — 実測にもとづく調査報告(2026-09-03) (ja)

Design and architecture(7)

Dokument	Inhalt
ENGINE.md	FullseyeEngine — Laufzeitumgebung zur Ausführung entworfener Pipelines → ENGINE.de.md · Original (ja)
EVOLUTION_ENVIRONMENT.md	Evolutionary Algorithm Development Environment — Expand, Contract, Promote → EVOLUTION_ENVIRONMENT.en.md · Original (ja)
INTEGRATION.md	Depending on Fullseye from another project (stability contract)
UNIFIED_API_REQUIREMENTS.md	Fullseye Unified Interface — Requirements Specification (v0.1, 2026-08-18) → UNIFIED_API_REQUIREMENTS.en.md · Original (ja)
design/TRIZ_DESIGN_PATTERN_MATRIX.md	TRIZ 40 発明原理 × ソフトウェア設計パターン × コンテナ型 — 構造選択マトリクス(fullseye) (ja)
EVIS_VISION_OSS_GAP.md	evis Vision Components — OSS/ROS2 Gap Analysis (2026-08-17) → EVIS_VISION_OSS_GAP.en.md · Original (ja)
INDUSTRY_SIGNALS.md	業界シグナル — 展示会・アワードを op 発想の恒常的な入力にする (ja)

Working notes and plans (historical; numbers are as of their date)(12)

Dokument	Inhalt
V13.md	v13 — production hardening, cross-project packaging, perception stack
V14.md	v14 — perception-stack completion: motion + robustness
SESSION_SUMMARY.md	Session Summary (auto-generated)
SESSION_2026_08_14.md	Session 2026-08-14 — Data-format expansion + Studio UI review
STUDIO_REVIEW_2026_08_14.md	Fullseye Studio — verified UI review (2026-08-14)
NEXT_SESSION.md	次セッション引き継ぎ — 高速化・省メモリ・動画 + 解像度管理 + 図注(2026-09-03 午前〜) (ja)
NEXT_OPS_PLAN_2026-08-31.md	次期 op 拡張計画(2026-08-31 調査、v0.1.4 リリース直後) (ja)
PLAN_0_1_9.md	0.1.9 → 0.1.10 の作業計画 (ja)
ARTICLE_INTEGRATION_TODO.md	記事への反映待ち(2026-09-02、可視化ウィング作業から) (ja)
ARTICLE_RESTRUCTURE_PLAN.md	Qiita 記事の章構成 組み替え計画(2026-09-02 起票 / 同日 実施済み = commit 32e47171) (ja)
ARTICLE_GPU_SHAPEMATCH.md	記事材料: 形状マッチングを GPU に載せる —— 勾配方向スコアの conv2d 定式化 (ja)
FULLSEYE_OP_ARTICLE_SPEC.md	Fullseye op カタログ画像・専用記事 仕様書(第 2 陣企画書) (ja)

Other(220)

Dokument	Inhalt
3DGS_USAGE.de.md	Fullseye 3DGS – Anwendung (ein einziger Befehl)
3DGS_USAGE.en.md	Fullseye 3DGS — how to use it (one command)
3DGS_USAGE.ko.md	Fullseye 3DGS — 사용법(명령어 한 줄)
3DGS_USAGE.tw.md	Fullseye 3DGS —— 使用方法（一行指令） (tw)
3DGS_USAGE.zh.md	Fullseye 3DGS —— 使用方法（单条命令） (zh)
AI_RAG_GUIDE.de.md	Fullseye als RAG eines KI-Assistenten nutzen (für Claude Code)
AI_RAG_GUIDE.en.md	Using Fullseye as an AI assistant’s RAG (for Claude Code)
AI_RAG_GUIDE.hi.md	Fullseye को AI assistant के RAG के रूप में इस्तेमाल करना (Claude Code के लिए)
AI_RAG_GUIDE.ko.md	Fullseye를 AI 어시스턴트의 RAG로 사용하는 방법(Claude Code용)
AI_RAG_GUIDE.tw.md	將 Fullseye 用作 AI 助理 RAG 的方法（針對 Claude Code） (tw)
AI_RAG_GUIDE.zh.md	将 Fullseye 用作 AI 助手 RAG 的方法（面向 Claude Code） (zh)
BENCH_VS_OPENCV.en.md	imgevolve GPU op vs OpenCV (CPU) throughput benchmark
CAPABILITIES.en.md	What Fullseye can do
CAPABILITIES.md	What Fullseye can do → CAPABILITIES.en.md · Original (ja)
CHAIN_FUZZ.en.md	Chain Fuzzer (chain fuzz) — a third quality-assurance layer that shakes ops by wiring them into chains
DESIGN_NOTES.de.md	Fullseye-Entwurfsnotizen (aus den ★-Kommentaren im Quellcode erzeugt)
DESIGN_NOTES.en.md	Fullseye design notes (generated from the ★ comments in the source)
DESIGN_NOTES.ko.md	Fullseye 설계 판단 모음(소스의 ★ 주석에서 생성)
DESIGN_NOTES.md	Fullseye-Entwurfsnotizen (aus den ★-Kommentaren im Quellcode erzeugt) → DESIGN_NOTES.de.md · Original (ja)
DESIGN_NOTES.tw.md	Fullseye 設計判斷集（由原始碼中的 ★ 註解產生） (tw)
DESIGN_NOTES.zh.md	Fullseye 设计判断集（由源码中的 ★ 注释生成） (zh)
DEVICE_GUIDE.md	CPU / GPU の選び方 (ja)
ENGINE.de.md	FullseyeEngine — Laufzeitumgebung zur Ausführung entworfener Pipelines
ENGINE.en.md	FullseyeEngine — the runtime that executes a pipeline you designed
ENGINE.ko.md	FullseyeEngine — 설계한 파이프라인을 실행하는 런타임
ENGINE.tw.md	FullseyeEngine — 執行已設計管線的執行環境 (tw)
ENGINE.zh.md	FullseyeEngine — 运行已设计管道的运行时 (zh)
EVIS_VISION_OSS_GAP.en.md	evis Vision Components — OSS/ROS2 Gap Analysis (2026-08-17)
EVOLUTION_ENVIRONMENT.en.md	Evolutionary Algorithm Development Environment — Expand, Contract, Promote
FILE_FORMATS.md	Fullseye のファイル形式棚卸し (ja)
FSCRIPT_LANGUAGE.en.md	Fullseye Script — Language / Runtime / Watch IDE Design Specification (North Star)
GALLERY.en.md	Fullseye Gallery
GENERAL_ALGORITHMS.de.md	Allgemeine Algorithmen implementierbar machen — algo-c Kompatibilitäts-Roadmap
GENERAL_ALGORITHMS.en.md	Making general algorithms implementable — the algo-c support roadmap
GENERAL_ALGORITHMS.ko.md	범용 알고리즘을 구현 가능하게 만들기 — algo-c 대응 로드맵
GENERAL_ALGORITHMS.tw.md	讓通用演算法也能實作 — algo-c 對應路線圖 (tw)
GENERAL_ALGORITHMS.zh.md	让通用算法也能实现 — algo-c 对应路线图 (zh)
GETTING_STARTED.de.md	Erste Schritte (in 5 Minuten startklar)
GETTING_STARTED.en.md	Getting started (running in 5 minutes)
GETTING_STARTED.hi.md	शुरुआत करें (5 मिनट में चालू)
GETTING_STARTED.ko.md	시작하기 (5분 만에 실행하기)
GETTING_STARTED.tw.md	快速上手（5 分鐘跑起來） (tw)
GETTING_STARTED.zh.md	快速上手（5 分钟运行起来） (zh)
GPU_OPTIMIZATION_PATTERNS.en.md	GPU Optimization Design-Pattern Catalog (for RTX 5090 / Blackwell sm_120)
GSPLAT_NATIVE_WINDOWS.en.md	Building native gsplat on Windows (RTX 5090 / torch cu128) — a proven procedure
HALCON_COVERAGE_HONEST.en.md	HALCON Coverage — the honest denominator (updated 2026-08-18)
HARDENING.en.md	What the PoCs hardened — found, fixed, and gated
HARDENING.md	What the PoCs hardened — found, fixed, and gated → HARDENING.en.md · Original (ja)
HDEVELOP_DEV_OPS.en.md	HDevelop dev_* operator family — the UI/display control surface (Studio north star)
HDEVELOP_FIDELITY.en.md	Fullseye Studio — HDevelop Fidelity Spec (North Star)
I18N_PLAN.md	完全な多言語化 — 計画と現在地 (ja)
INSTALL.de.md	Installations- und Einrichtungshandbuch
INSTALL.en.md	Installation / Environment Setup — Complete Guide
INSTALL.hi.md	Installation / Environment Setup — पूरी गाइड
INSTALL.ko.md	설치 / 환경 구축 완전 가이드
INSTALL.tw.md	安裝 / 環境建置完整指南 (tw)
INSTALL.zh.md	安装 / 环境搭建完全指南 (zh)
MATCH_3D_MATRIX.en.md	fullseye 3D Vision Toolkit (for Physical AI, differentiating from HALCON/OpenCV)
MATURITY.md	成熟度台帳(Maturity) (ja)
MCP.md	Fullseye を MCP(Model Context Protocol)から使う (ja)
NAN_INPUT_AUDIT.md	非有限入力監査 (ja)
OP_COMBINATION_MATRIX.en.md	fullseye 3D op × op Combination Matrix (prioritized by feasibility × differentiation)
PIPELINE_SHAPES.md	Typed DAG execution
SAMPLE_IMAGE_REFERENCES.en.md	Sample images — provenance, source papers & public repositories
STUDIO_GUIDE.de.md	Vollständiger Leitfaden zu Fullseye Studio
STUDIO_GUIDE.en.md	The complete guide to Fullseye Studio
STUDIO_GUIDE.hi.md	Fullseye Studio की पूरी गाइड
STUDIO_GUIDE.ko.md	Fullseye Studio 완전 가이드
STUDIO_GUIDE.tw.md	Fullseye Studio 完全指南 (tw)
STUDIO_GUIDE.zh.md	Fullseye Studio 完全指南 (zh)
TERRAIN_WALK.en.md	Walking a Character Over Terrain (sim-native, no GPU required)
UNIFIED_API_REQUIREMENTS.en.md	Fullseye Unified Interface — Requirements Specification (v0.1, 2026-08-18)
VALIDATION_CONTRIBUTING.en.md	Reporting validation on real hardware or real data
capabilities/align-and-stack.md	id: align-and-stack
capabilities/beamforming-and-range-doppler.md	id: beamforming-and-range-doppler
capabilities/beats-fringes-and-screens.md	id: beats-fringes-and-screens
capabilities/blob-and-region.md	id: blob-and-region
capabilities/camera-intrinsics-calibration.md	id: camera-intrinsics-calibration
capabilities/chromatic-confocal-sensor.md	id: chromatic-confocal-sensor
capabilities/colour-and-delta-e.md	id: colour-and-delta-e
capabilities/complex-plane-fields.md	id: complex-plane-fields
capabilities/compound-eye-aliasing-and-ttc.md	id: compound-eye-aliasing-and-ttc
capabilities/convergent-forward-models.md	id: convergent-forward-models
capabilities/crop-weed-cover-grade.md	id: crop-weed-cover-grade
capabilities/dual-energy-xray-material-discrimination.md	id: dual-energy-xray-material-discrimination
capabilities/emva1288-camera-datasheets.md	id: emva1288-camera-datasheets
capabilities/estimate-lens-distortion.md	id: estimate-lens-distortion
capabilities/fiber-and-light-guide.md	id: fiber-and-light-guide
capabilities/figures-and-annotation.md	id: figures-and-annotation
capabilities/fix-text-in-images.md	id: fix-text-in-images
capabilities/fourier-ptychography.md	id: fourier-ptychography
capabilities/geodetic-frames.md	id: geodetic-frames
capabilities/golden-compare.md	id: golden-compare
capabilities/good-sample-variation-model.md	id: good-sample-variation-model
capabilities/grating-interferometry.md	id: grating-interferometry
capabilities/grating-spectrometer-and-illumination.md	id: grating-spectrometer-and-illumination
capabilities/gw-interferometer-quantum-noise-and-matched-filter.md	id: gw-interferometer-quantum-noise-and-matched-filter
capabilities/illumination-cone-vs-na.md	id: illumination-cone-vs-na
capabilities/industrial-oct.md	id: industrial-oct
capabilities/inner-diameter-in-mm.md	id: inner-diameter-in-mm
capabilities/inspection-fixture.md	id: inspection-fixture
capabilities/inspection-workflow.md	id: inspection-workflow
capabilities/interactive-poc-viewer.md	id: interactive-poc-viewer
capabilities/interreflection-to-convergence.md	id: interreflection-to-convergence
capabilities/inverted-colour-overlays.md	id: inverted-colour-overlays
capabilities/itof-multifreq.md	id: itof-multifreq
capabilities/laser-speckle-floor.md	id: laser-speckle-floor
capabilities/lens-distortion-correction.md	id: lens-distortion-correction
capabilities/lens-prescription-files.md	id: lens-prescription-files
capabilities/lens-tolerancing.md	id: lens-tolerancing
capabilities/light-transport.md	id: light-transport
capabilities/lockin-demodulation.md	id: lockin-demodulation
capabilities/material-optical-property-library.md	id: material-optical-property-library
capabilities/measurement-system-and-uncertainty.md	id: measurement-system-and-uncertainty
capabilities/moire-alignment.md	id: moire-alignment
capabilities/nir-hyperspectral-sorting.md	id: nir-hyperspectral-sorting
capabilities/noncoaxial-optics.md	id: noncoaxial-optics
capabilities/ocr-preprocessing.md	id: ocr-preprocessing
capabilities/one-stroke-drawing.md	id: one-stroke-drawing
capabilities/optics-and-materials.md	id: optics-and-materials
capabilities/optics-drawings.md	id: optics-drawings
capabilities/patch-feature-anomaly-detection.md	id: patch-feature-anomaly-detection
capabilities/periodic-defects-in-1d-signals.md	id: periodic-defects-in-1d-signals
capabilities/phase-measuring-deflectometry.md	id: phase-measuring-deflectometry
capabilities/photoelasticity.md	id: photoelasticity
capabilities/photograph-through-prescription.md	id: photograph-through-prescription
capabilities/pictures-that-carry-their-own-truth.md	id: pictures-that-carry-their-own-truth
capabilities/pixel-shift-imaging.md	id: pixel-shift-imaging
capabilities/pl-carrier-diffusion-visibility.md	id: pl-carrier-diffusion-visibility
capabilities/planarity-from-point-cloud.md	id: planarity-from-point-cloud
capabilities/plenoptic-camera.md	id: plenoptic-camera
capabilities/point-cloud-to-picture.md	id: point-cloud-to-picture
capabilities/point-target-detection.md	id: point-target-detection
capabilities/polarisation-specular-removal.md	id: polarisation-specular-removal
capabilities/polarization-imaging.md	id: polarization-imaging
capabilities/probability-of-detection.md	id: probability-of-detection
capabilities/raw-to-display-isp.md	id: raw-to-display-isp
capabilities/reuse-computation-results.md	id: reuse-computation-results
capabilities/robust-code-matching.md	id: robust-code-matching
capabilities/robust-gaussian-spline-profile-filter.md	id: robust-gaussian-spline-profile-filter
capabilities/sam-bond-voids.md	id: sam-bond-voids
capabilities/scratch-detection-and-width.md	id: scratch-detection-and-width
capabilities/sem-edge-effect-metrology.md	id: sem-edge-effect-metrology
capabilities/sem-tem-same-particle.md	id: sem-tem-same-particle
capabilities/sequential-lens-design-metrics.md	id: sequential-lens-design-metrics
capabilities/shape-from-polarization.md	id: shape-from-polarization
capabilities/sim-to-real-calibration.md	id: sim-to-real-calibration
capabilities/spectral-radiometry-chain.md	id: spectral-radiometry-chain
capabilities/subpixel-2d-metrology.md	id: subpixel-2d-metrology
capabilities/surface-defects-with-lighting.md	id: surface-defects-with-lighting
capabilities/tdi-linescan-and-lens.md	id: tdi-linescan-and-lens
capabilities/telecentric-metrology.md	id: telecentric-metrology
capabilities/tem-phase-contrast-and-ctf.md	id: tem-phase-contrast-and-ctf
capabilities/template-alignment.md	id: template-alignment
capabilities/terrain-and-visibility.md	id: terrain-and-visibility
capabilities/text-and-tables-on-images.md	id: text-and-tables-on-images
capabilities/theorems-as-pictures.md	id: theorems-as-pictures
capabilities/thin-film-reflectometry.md	id: thin-film-reflectometry
capabilities/tof-camera.md	id: tof-camera
capabilities/tomography-reconstruction.md	id: tomography-reconstruction
capabilities/typed-results-as-json.md	id: typed-results-as-json
capabilities/typed-results-as-markdown.md	id: typed-results-as-markdown
capabilities/vibration-and-acoustics.md	id: vibration-and-acoustics
capabilities/virtual-sem-monte-carlo.md	id: virtual-sem-monte-carlo
capabilities/visual-hull-from-silhouettes.md	id: visual-hull-from-silhouettes
capabilities/volume-from-3d-scan.md	id: volume-from-3d-scan
capabilities/water-inspection-images.md	id: water-inspection-images
capabilities/water-transparent-media.md	id: water-transparent-media
capabilities/what-a-picture-cannot-check.md	id: what-a-picture-cannot-check
capabilities/xlsx-report.md	id: xlsx-report
hardening/carve-look-at-unreachable-and-silent.md	id: carve-look-at-unreachable-and-silent
hardening/cli-help-and-subcommands-broke-in-the-wheel.md	id: cli-help-and-subcommands-broke-in-the-wheel
hardening/compactness-saturated-at-one.md	id: compactness-saturated-at-one
hardening/dem-viewshed-self-occlusion.md	id: dem-viewshed-self-occlusion
hardening/dimensional-features-were-normalised.md	id: dimensional-features-were-normalised
hardening/ecef-to-geodetic-returned-latitude-180.md	id: ecef-to-geodetic-returned-latitude-180
hardening/empty-and-tiny-inputs-raised-raw-library-errors.md	id: empty-and-tiny-inputs-raised-raw-library-errors
hardening/empty-name-resolved-and-narrow-floats-not-upcast.md	id: empty-name-resolved-and-narrow-floats-not-upcast
hardening/engine-load-on-an-instance-was-silently-ignored.md	id: engine-load-on-an-instance-was-silently-ignored
hardening/features-saturated-at-one.md	id: features-saturated-at-one
hardening/frame-align-inlier-ratio-is-not-confidence.md	id: frame-align-inlier-ratio-is-not-confidence
hardening/functional-gate-did-not-know-the-match-sort.md	id: functional-gate-did-not-know-the-match-sort
hardening/halcon-named-shape-factors.md	id: halcon-named-shape-factors
hardening/image-io-dropped-write-failures-and-crushed-16-bit.md	id: image-io-dropped-write-failures-and-crushed-16-bit
hardening/inputs-without-a-conversion-were-not-refused.md	id: inputs-without-a-conversion-were-not-refused
hardening/itk-threshold-ops-returned-the-dark-side.md	id: itk-threshold-ops-returned-the-dark-side
hardening/ledger-evicted-silently-and-studio-help-aborted.md	id: ledger-evicted-silently-and-studio-help-aborted
hardening/ledger-lookups-returned-empty-for-unknown-names.md	id: ledger-lookups-returned-empty-for-unknown-names
hardening/mcp-facade-layer-listed-classes-as-ops.md	id: mcp-facade-layer-listed-classes-as-ops
hardening/moment-invariants-two-families-same-name.md	id: moment-invariants-two-families-same-name
hardening/nary-ops-unlisted-and-knobs-unstated.md	id: nary-ops-unlisted-and-knobs-unstated
hardening/no-gate-knew-what-dimension-a-feature-has.md	id: no-gate-knew-what-dimension-a-feature-has
hardening/noise-sigma-mad-collapses-on-quantised-data.md	id: noise-sigma-mad-collapses-on-quantised-data
hardening/nonfinite-output-was-sanitized-silently.md	id: nonfinite-output-was-sanitized-silently
hardening/op-find-blind-to-japanese-queries.md	id: op-find-blind-to-japanese-queries
hardening/otsu-threshold-at-the-bin-midpoint.md	id: otsu-threshold-at-the-bin-midpoint
hardening/pfm-default-wrote-8-bit-values-into-a-float-format.md	id: pfm-default-wrote-8-bit-values-into-a-float-format
hardening/pose-helpers-could-not-take-their-own-matrix.md	id: pose-helpers-could-not-take-their-own-matrix
hardening/refract-one-way-reference.md	id: refract-one-way-reference
hardening/run-pipeline-stage-forms-fail-obscurely.md	id: run-pipeline-stage-forms-fail-obscurely
hardening/stage-forms-read-differently-by-four-entry-points.md	id: stage-forms-read-differently-by-four-entry-points
hardening/strict-mode-only-covered-some-of-the-guards.md	id: strict-mode-only-covered-some-of-the-guards
hardening/studio-run-key-ignored-unapplied-edits.md	id: studio-run-key-ignored-unapplied-edits
hardening/table-sort-mixes-rows-and-spec-dicts.md	id: table-sort-mixes-rows-and-spec-dicts
hardening/unknown-operator-hides-missing-backend.md	id: unknown-operator-hides-missing-backend
hardening/wrappers-were-scalars-and-hints-were-raw-type-errors.md	id: wrappers-were-scalars-and-hints-were-raw-type-errors
literature/convergent_numerics_light_transport.md	文献層: 収束型数値計算と光輸送(厳選) (ja)
literature/electron_microscopy.md	文献層: 電子顕微鏡の撮像と計測(厳選) (ja)
literature/industrial_optical_sensing.md	文献層: 工業用光学センシング(厳選) (ja)
literature/sensitivity_uq_calibration.md	文献層: 感度解析・不確かさ定量化・較正(厳選) (ja)
view2026/about.md	Fullseye
view2026/de/index.md	Fullseye — ViEW2026
view2026/en/about.md	Fullseye
view2026/en/index.md	Fullseye — ViEW2026
view2026/fr/index.md	Fullseye — ViEW2026
view2026/hi/index.md	Fullseye — ViEW2026
view2026/index.md	Fullseye — ViEW2026
view2026/ko/index.md	Fullseye — ViEW2026
view2026/tw/index.md	Fullseye — ViEW2026
view2026/zh/index.md	Fullseye — ViEW2026

This site is open source. Improve this page.