{"id":"W2905374808","doi":"10.1007/978-3-030-04375-9_39","title":"EREL-Net: A Remedy for Industrial Bottle Defect Detection","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Bottle; Artificial intelligence; Classifier (UML); Bounding overwatch; Process (computing); Computer vision; Pattern recognition (psychology); Training set; Manufacturing process; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008715068,0.0004032362,0.0004475708,0.0006494163,0.0002132549,0.0002123305,0.0004008372,0.00087785,0.00005827313],"category_scores_gemma":[0.0001675958,0.0003786641,0.0002173954,0.0003520813,0.0001897043,0.0001745406,0.00009322736,0.0007177819,0.0000686129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000432407,"about_ca_system_score_gemma":0.0001267434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002562805,"about_ca_topic_score_gemma":0.0001863068,"domain_scores_codex":[0.9978813,0.00002026178,0.0004812802,0.0006809405,0.0004674629,0.0004687579],"domain_scores_gemma":[0.998794,0.0002949117,0.0001371343,0.0004980973,0.0001679944,0.0001078704],"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":[0.00006658441,0.000007861834,0.000007852012,0.0000650166,0.00003980408,0.000007623566,0.0002539755,0.03978271,0.002581658,0.00007181049,0.0005579548,0.9565572],"study_design_scores_gemma":[0.0031871,0.002289518,0.00003003572,0.001604496,0.0001086379,0.0001837598,0.000001369225,0.7009273,0.09143782,0.03091626,0.1668849,0.002428795],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00194246,0.0001652756,0.9842618,0.00001327687,0.01039721,0.0009049926,0.00001589005,0.0002856065,0.002013548],"genre_scores_gemma":[0.980593,0.00001525343,0.007834727,0.0001066506,0.01066451,0.00006528982,0.00001098754,0.0001468579,0.0005627534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9786505,"threshold_uncertainty_score":0.9998665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03274848581710834,"score_gpt":0.2401842213640418,"score_spread":0.2074357355469335,"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."}}