{"id":"W4389264937","doi":"10.1016/j.eswa.2023.122749","title":"Computer vision defect detection on unseen backgrounds for manufacturing inspection","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Deep learning; Visual inspection; Task (project management); Machine learning; Variety (cybernetics); Object detection; Parameterized complexity; Pattern recognition (psychology); Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004682482,0.0007020526,0.0006634984,0.001772678,0.0002835685,0.0007041147,0.0007309166,0.0009591504,0.001413033],"category_scores_gemma":[0.001689226,0.0003354059,0.0003936775,0.0006588915,0.0003279708,0.0006526709,0.0007512273,0.0007366661,0.0007443801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002936048,"about_ca_system_score_gemma":0.0004866544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00142344,"about_ca_topic_score_gemma":0.002651532,"domain_scores_codex":[0.9995304,0.00005908003,0.00001428344,0.0001091379,0.000224037,0.0000630385],"domain_scores_gemma":[0.9990915,0.0003099996,0.00009176032,0.0001273829,0.0002999961,0.00007937128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008047197,0.000359686,0.003551555,0.0003509306,0.00006516256,0.0003672282,0.000103899,0.02274726,0.4956575,0.001419229,0.003254237,0.4713186],"study_design_scores_gemma":[0.00002718178,0.0004133687,0.01240563,0.00004181761,0.00008352287,0.0008157799,0.00007251149,0.831603,0.1496758,0.001488859,0.003343913,0.00002863871],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3288759,0.002009775,0.6621215,0.0002886018,0.0001427514,0.00008919406,0.0003493026,0.002521085,0.003601966],"genre_scores_gemma":[0.7805611,0.0008282269,0.2135549,0.0001529989,0.00006225205,0.00003391649,0.0006654107,0.0002401721,0.003900976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001772678,"threshold_uncertainty_score":0.004727125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01970219987755033,"score_gpt":0.2603581894886739,"score_spread":0.2406559896111236,"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."}}