cutting_scene — DRIVE `cutting` op

• Data kinds: any → table

• Call: import fullseye as fs; fs.ledger.cutting_scene(kind: 'str' = 'face', px_per_mm: 'float | None' = None, **overrides) -> 'dict' (to call the implementation directly, import cutting; cutting.cutting_scene(kind: 'str' = 'face', px_per_mm: 'float | None' = None, **overrides) -> 'dict'; from the registry, opsdrive.get("cutting_scene"))

Usage

Parameters (dict) of the synthetic scene. kind="face" = face view (camera along the normal of the blade face), "edge" = view along the cutting edge.

Front view: the blade is longer than the food, and the straight edge line is visible to the left and right of the food. Within the food's width it is hidden by the food. Keys are food_xc / food_w / food_h (food centre, width, height), blade_len / blade_h / tip_slant (edge length, blade height, slanted part at the tip). Edge-on view: the blade appears as a thin band, and the distance between the flat face of the single-bevel blade and the food's end face is the slice thickness. Keys are food_top, blade_tb (spine thickness), blade_hb (height of the single-bevel cutting edge), blade_h.

Changing px_per_mm scales the pixel dimensions H / W / board_row (the row of z = 0) proportionally (dimensions in mm are unchanged). Defaults are 8 px/mm for the front view (800×480) and 20 px/mm edge-on (520×560). Unknown keys raise ValueError (misspellings are not passed silently).

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

• The canonical algorithm (author, year) and its uses are named in the family usage guide above.

Runnable examples (verified samples that actually call this op)

• poc_food_cutting_measure — py -3.11 examples/poc_food_cutting_measure.py

• poc_knife_tactile_toughness — py -3.11 examples/poc_knife_tactile_toughness.py

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

course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same

Same category (`cutting`)

cutting_face_render · cutting_edge_render · cutting_episode_synth · cutting_wrist_mjcf · knife_edge_track · cut_depth_from_side · slice_thickness_profile · cut_surface_roughness

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

cutting_scene — DRIVE cutting op