{"id":"W2976682141","doi":"10.3390/electronics8101088","title":"Face Recognition via Deep Learning Using Data Augmentation Based on Orthogonal Experiments","year":2019,"lang":"en","type":"article","venue":"Electronics","topic":"Face recognition and analysis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China; Nvidia","keywords":"Artificial intelligence; Computer science; Facial recognition system; Convolutional neural network; Class (philosophy); Artificial neural network; Deep learning; Pattern recognition (psychology); Machine learning; Attendance; Face (sociological concept)","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":[0.001060839,0.0007464312,0.000631269,0.0005370721,0.0002600887,0.0004184425,0.0008366597,0.0005445591,0.001857118],"category_scores_gemma":[0.002580909,0.0002713235,0.0007121619,0.0004425934,0.00060354,0.001071075,0.001020335,0.000954287,0.0006195767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004134584,"about_ca_system_score_gemma":0.0004710219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001828682,"about_ca_topic_score_gemma":0.001987652,"domain_scores_codex":[0.9992502,0.0001698079,0.00003971408,0.0002057144,0.0002474677,0.0000871899],"domain_scores_gemma":[0.9989969,0.0002827667,0.0001050959,0.000310623,0.0002670977,0.00003754571],"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":[0.0006485818,0.0006767813,0.004810815,0.000123639,0.0001040625,0.0001250358,0.00009442449,0.1268075,0.08530276,0.002341247,0.003397681,0.7755675],"study_design_scores_gemma":[0.0000145275,0.0001566901,0.001527856,0.000007592028,0.00001954983,0.00006237262,0.00001590991,0.9703879,0.02577436,0.001178979,0.000840403,0.00001388698],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2153277,0.0004277539,0.7756142,0.0002839766,0.0002138516,0.0001681452,0.0003114064,0.004095131,0.003557745],"genre_scores_gemma":[0.7592223,0.0001735906,0.2367558,0.0002103684,0.00005063253,0.0002297636,0.0008227116,0.00008039168,0.002454427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001857118,"threshold_uncertainty_score":0.006212711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0435839519201968,"score_gpt":0.2987460188628792,"score_spread":0.2551620669426823,"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."}}