{"id":"W1996952906","doi":"10.2478/s11772-014-0202-2","title":"Enhanced image processing for infrared non-destructive testing","year":2014,"lang":"en","type":"article","venue":"Opto-Electronics Review","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Ciência sem Fronteiras; Foreign Affairs and International Trade Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canada Research Chairs","keywords":"Thermography; SIGNAL (programming language); Signal processing; Nondestructive testing; Contrast (vision); Image processing; Signal-to-noise ratio (imaging); Computer science; Noise (video); Artificial intelligence; Statistical analysis; Infrared; Pattern recognition (psychology); Optics; Materials science; Image (mathematics); Mathematics; Statistics; Digital signal processing; Telecommunications; Physics; Computer hardware","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000350367,0.0002287435,0.0003750568,0.00005441313,0.0000967087,0.00004192343,0.000213202,0.00007798622,0.00001576474],"category_scores_gemma":[0.0001514339,0.0002212982,0.0001192981,0.0004025641,0.00003176709,0.0001522229,0.00001672728,0.0002297976,0.000002678707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006840356,"about_ca_system_score_gemma":0.00005170845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001156803,"about_ca_topic_score_gemma":9.451439e-7,"domain_scores_codex":[0.9989166,0.00002350254,0.0003014359,0.0002230654,0.00009949997,0.0004358881],"domain_scores_gemma":[0.999347,0.0001251981,0.00008652134,0.0002473636,0.0001318887,0.00006204739],"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":[0.00000560366,0.00001293504,0.0000024038,0.006701639,0.0000346195,4.247966e-7,0.00006869645,0.00003367499,0.1635238,0.000509285,0.0007574022,0.8283495],"study_design_scores_gemma":[0.001239979,0.0008842546,0.0001359976,0.02032922,0.0006617534,0.00007078911,0.00002961988,0.09386674,0.5052705,0.03839309,0.3367453,0.002372737],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007310822,0.09046423,0.8751237,0.00003295681,0.0001215623,0.001847431,0.00004489813,0.001194891,0.02385945],"genre_scores_gemma":[0.826414,0.03466298,0.1360958,0.0004956753,0.0002934534,0.001577284,0.00006754844,0.0002520838,0.0001411571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8259768,"threshold_uncertainty_score":0.902428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008215813556186878,"score_gpt":0.2501772188285498,"score_spread":0.2419614052723629,"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."}}