{"id":"W2953958484","doi":"10.1109/access.2019.2925561","title":"Real-Time Tiny Part Defect Detection System in Manufacturing Using Deep Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Petroleum Technology Research Centre; Guizhou Science and Technology Department; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Artificial intelligence; Real-time computing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004758853,0.0004779536,0.0004236466,0.0005298248,0.0001810782,0.0003758982,0.0008485338,0.0005383816,0.0009725278],"category_scores_gemma":[0.0007119933,0.0002365006,0.0002967935,0.00030252,0.0002387394,0.0007451799,0.000492128,0.0004178305,0.0002104474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006153801,"about_ca_system_score_gemma":0.00051284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002925716,"about_ca_topic_score_gemma":0.003140674,"domain_scores_codex":[0.9997513,0.0000229234,0.00001513659,0.00007908983,0.00009634264,0.00003529346],"domain_scores_gemma":[0.9996755,0.00007788739,0.00004735648,0.00005021121,0.0001205101,0.00002860392],"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":[0.0004933666,0.0003340932,0.009848882,0.0002162794,0.0001145286,0.0003601873,0.0001587934,0.2212344,0.1736337,0.002131327,0.003715595,0.5877588],"study_design_scores_gemma":[0.000008520476,0.00007962019,0.001518744,0.000003470683,0.00001131917,0.00004402592,0.000008745456,0.9768707,0.02055002,0.0004189241,0.0004760047,0.00001007097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1774068,0.0002510443,0.8158804,0.0001498485,0.00006462858,0.00006659769,0.0001189013,0.004810263,0.001251478],"genre_scores_gemma":[0.8782372,0.00007728751,0.1200934,0.00009438305,0.00001260798,0.00005518945,0.0001602906,0.00004986675,0.001219752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002925716,"threshold_uncertainty_score":0.005817354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01904745040525403,"score_gpt":0.248293758961795,"score_spread":0.2292463085565409,"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."}}