{"id":"W2771063748","doi":"10.4018/ijcini.2017100102","title":"Regression-Based Automated Facial Image Quality Model","year":2017,"lang":"en","type":"article","venue":"International Journal of Cognitive Informatics and Natural Intelligence","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Computer science; Biometrics; Quality (philosophy); Artificial intelligence; Facial recognition system; Image quality; Regression analysis; Sample (material); Regression; Face (sociological concept); Linear regression; Linear model; Pattern recognition (psychology); Authentication (law); Computer vision; Machine learning; Image (mathematics); Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000490538,0.0001409451,0.0001931164,0.0001964518,0.000241437,0.0007788539,0.001190745,0.00006845774,0.00001402636],"category_scores_gemma":[0.001081597,0.0001005683,0.0001104052,0.00004409078,0.0001617794,0.002638479,0.0002589694,0.0003127413,0.00002006938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003010341,"about_ca_system_score_gemma":0.0001257198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009010294,"about_ca_topic_score_gemma":0.000002174694,"domain_scores_codex":[0.9984483,0.00003462215,0.0007116423,0.00009150182,0.0005696,0.0001443614],"domain_scores_gemma":[0.9962924,0.0002731609,0.001209761,0.0001589629,0.001961231,0.000104497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005937057,0.0002289151,0.001141535,0.00006216471,0.0002393964,0.0000966609,0.003909136,0.001507592,0.003231147,0.006442228,0.001438093,0.9811094],"study_design_scores_gemma":[0.0004563043,0.00006587099,0.002198523,0.0006073933,0.000009302123,0.00005875108,0.0002814103,0.9654481,0.02542868,0.005180327,0.0000973163,0.0001680519],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2141714,0.00009379978,0.7820363,0.0009949891,0.001171859,0.00008823589,0.00003162592,0.00005093718,0.001360886],"genre_scores_gemma":[0.9590584,0.0001383871,0.04007475,0.0006110898,0.00006665449,0.000001762744,0.000006737745,0.000003602042,0.00003860865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9809414,"threshold_uncertainty_score":0.7510506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03785301755140954,"score_gpt":0.3792968788919789,"score_spread":0.3414438613405694,"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."}}