{"id":"W3019703315","doi":"10.1117/12.2555553","title":"Defects detection in infrared thermography by deep learning algorithm","year":2020,"lang":"en","type":"article","venue":"","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Thermography; Robustness (evolution); Artificial intelligence; Deep learning; Computer science; Object detection; Field (mathematics); Machine learning; Artificial neural network; Deep neural networks; Infrared; Computer vision; Algorithm; Pattern recognition (psychology)","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":[0.00005704997,0.000125236,0.0001164025,0.0001073312,0.00002985063,0.00002046643,0.00008431464,0.00009686009,0.00009707113],"category_scores_gemma":[0.00001030639,0.0001270119,0.00006747594,0.0005530049,0.00001600619,0.00008107317,0.00001147436,0.0002814132,0.000003565115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001172424,"about_ca_system_score_gemma":0.000001553448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002338896,"about_ca_topic_score_gemma":0.00001046666,"domain_scores_codex":[0.9994478,0.00002824503,0.0001326077,0.0001330188,0.00007636054,0.0001819193],"domain_scores_gemma":[0.999802,0.00003436377,0.0000136746,0.00006956141,0.000008920017,0.00007147505],"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":[0.00001553508,0.00002106111,0.001621609,0.00006207868,0.00004777278,0.00001060436,0.001449341,0.002344529,0.3875892,0.00002256515,0.0007273299,0.6060884],"study_design_scores_gemma":[0.0006628212,0.0002885576,0.006419969,0.00003110466,0.00002545912,0.000005052761,0.0004962649,0.4412211,0.5341659,0.0009744831,0.01501425,0.0006950371],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2156655,0.0009249118,0.7702838,0.00001260785,0.00008899587,0.0002447895,0.00002212926,0.002954335,0.009802995],"genre_scores_gemma":[0.9981614,0.0001001987,0.00153021,0.00009670524,0.00002989346,0.00003236585,0.000007754291,0.00003011529,0.00001139697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7824959,"threshold_uncertainty_score":0.5179394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004058076077164262,"score_gpt":0.1735281418003017,"score_spread":0.1694700657231374,"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."}}