{"id":"W2121197467","doi":"10.1109/rose.2008.4669192","title":"Feature selection for a real-time vision-based food inspection system","year":2008,"lang":"en","type":"article","venue":"","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Consistency (knowledge bases); Automation; Machine vision; Feature extraction; Artificial intelligence; Feature (linguistics); Feature selection; Quality (philosophy); Visual inspection; Product (mathematics); Computer vision; Filter (signal processing); Data mining; Engineering; Mathematics","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":[0.001309636,0.0007580734,0.0009362333,0.001210477,0.0003013737,0.000472994,0.0007819497,0.0006402615,0.001260165],"category_scores_gemma":[0.001889564,0.0002322469,0.0004696442,0.0007839496,0.0001708016,0.0005153811,0.0002778039,0.0003018153,0.0006431775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003400135,"about_ca_system_score_gemma":0.0003048594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001591459,"about_ca_topic_score_gemma":0.001377429,"domain_scores_codex":[0.9995959,0.00009474874,0.00003277753,0.00009688451,0.0001318583,0.00004780186],"domain_scores_gemma":[0.9991566,0.0003845697,0.0001022462,0.00006280494,0.0002584141,0.00003540559],"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":[0.00184872,0.0004820553,0.006699109,0.0001984666,0.00009695451,0.0003094716,0.0001032064,0.04261796,0.2071896,0.0001872461,0.003836496,0.7364307],"study_design_scores_gemma":[0.0001647164,0.0007878861,0.02253946,0.00001327985,0.00009281305,0.0003431996,0.0001001117,0.8624209,0.1114891,0.0003536545,0.001646954,0.00004790819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5509663,0.0003882348,0.4380804,0.0002403778,0.00004539806,0.0001843519,0.0005441945,0.008774206,0.0007765021],"genre_scores_gemma":[0.7466534,0.0000917396,0.2509245,0.00007647737,0.00002519281,0.000189418,0.001078049,0.00006877298,0.0008925158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001591459,"threshold_uncertainty_score":0.00692606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01129260614861465,"score_gpt":0.2534196037415878,"score_spread":0.2421269975929731,"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."}}