{"id":"W2011352218","doi":"10.1109/icip.2010.5651069","title":"Improved machine learning for image category recognition by local color constancy","year":2010,"lang":"en","type":"article","venue":"","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Color constancy; Artificial intelligence; Computer vision; Color normalization; Invariant (physics); Computer science; Cognitive neuroscience of visual object recognition; Pattern recognition (psychology); Color histogram; Color balance; Standard illuminant; Object (grammar); Local color; Color model; Color image; Mathematics; Color space; Image (mathematics); Image processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002303451,0.0006974579,0.001081804,0.001333789,0.000366396,0.0009112139,0.001697169,0.0007740964,0.002082408],"category_scores_gemma":[0.007203906,0.0002767383,0.0006627091,0.002351685,0.0006326721,0.002295858,0.001036719,0.001250078,0.001256617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006650212,"about_ca_system_score_gemma":0.0007470844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003082849,"about_ca_topic_score_gemma":0.003455374,"domain_scores_codex":[0.9990239,0.0002750995,0.00005433711,0.0002257518,0.000327983,0.00009294137],"domain_scores_gemma":[0.9968554,0.001286808,0.0002002295,0.0008732789,0.0007009302,0.00008338979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002605218,0.0002741378,0.002716626,0.0001193544,0.0001102937,0.0000519229,0.00006035231,0.08775911,0.03638474,0.005371795,0.00302691,0.8638643],"study_design_scores_gemma":[0.0000170917,0.00009625682,0.001425739,0.000004665401,0.00002342684,0.00007208781,0.00001189826,0.9790965,0.01550479,0.002710656,0.001015472,0.00002145479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05227885,0.0006554842,0.9426754,0.0001344808,0.00006297502,0.00007747463,0.00008917088,0.002822626,0.001203529],"genre_scores_gemma":[0.4232898,0.0003482961,0.5731203,0.0001631281,0.0000715342,0.0001264496,0.0005063634,0.0001961336,0.002177999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003082849,"threshold_uncertainty_score":0.01218194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007527949715869793,"score_gpt":0.2457583321217541,"score_spread":0.2382303824058843,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}