iqa op• Data kinds: any × table → table
• Call: import fullseye as fs; fs.ledger.tid2013_by_distortion(values, index: 'dict', idx=None) -> 'List[dict]' (to call the implementation directly, import iqatid; iqatid.tid2013_by_distortion(values, index: 'dict', idx=None) -> 'List[dict]'; from the registry, opsimgmetrics.get("tid2013_by_distortion"))
> This operator's description has not been translated yet. The original text follows as it is.
歪み種(24)ごとの、指標と MOS の順位相関。
`values は idx(台帳の行番号、省略 = 3000 行全部)に対応する値。各行: type(1 始まり)、name`(readme TABLE I)、
`n、n_inf、srocc、krocc`(τ_b)。1 種 = 25 参照 × 5 段 = 125 組。組が 2 未満の種は nan。歪み 18(彩度変化)は
Y′ の PSNR が 106 / 125 組で inf(同順位)なので、その種の順位相関は低く出る —— 指標の欠陥でなく輝度だけを見る指標の限界。
Raises `ValueError`: 長さ不一致・nan。
• image_difference_metrics family guide
• 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_iqa_fsim_gmsd_vif — py -3.11 examples/poc_iqa_fsim_gmsd_vif.py
• poc_iqa_tid2013 — py -3.11 examples/poc_iqa_tid2013.py
table as input)luma_limited_u8 · rank_data · tid2013_index
iqa)luma_limited_u8 · rank_data · rank_spearman · rank_kendall_b · tid2013_published · tid2013_root · tid2013_index · tid2013_metric_values
*Provenance: iqatid.py — IMGMETRICS 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.