datacode2d op• Data kinds: image2d → table
• Call: import fullseye as fs; fs.ledger.qr_locate(image) -> 'dict' (to call the implementation directly, import qrsym; qrsym.qr_locate(image) -> 'dict'; from the registry, opssymbol.get("qr_locate"))
• GPU: none (CPU reference implementation only)
Find a QR Code in an image and estimate the module-space to image homography (table).
Locate a QR symbol (dark modules on a light background) in a 2-D float image in [0, 1]. Returns homography (module [x=col, y=row, 1] -> image [x=col_px, y=row_px, w]), size, version, finder_centers (3,2) (row, col) px in TL/TR/BL order, module_px and timing_score (fraction of timing modules read as expected, a sanity measure). Raises QRDecodeError if not found.
• 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.
• poc_symbol_part_dpm — py -3.11 examples/poc_symbol_part_dpm.py
table as input)render_symbol · symbol_read_trials · symbol_read_pod · ocr_classify · ocr_read_line · ocr_read_trials
datacode2d)qr_encode · qr_decode_modules · qr_sample · qr_read · dm_encode · dm_decode_modules · dm_locate · dm_sample
*Provenance: qrsym.py — SYMBOL operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.