{"id":"W3120371870","doi":"10.1016/j.measurement.2021.109012","title":"Development of a CNN edge detection model of noised X-ray images for enhanced performance of non-destructive testing","year":2021,"lang":"en","type":"article","venue":"Measurement","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Beijing Institute of Technology Research Fund Program for Young Scholars; Beijing Institute of Technology; Google","keywords":"Canny edge detector; Edge detection; Artificial intelligence; Convolutional neural network; Noise (video); Computer science; Nondestructive testing; Enhanced Data Rates for GSM Evolution; Deriche edge detector; Pattern recognition (psychology); Computer vision; Filter (signal processing); Image processing; Image (mathematics); Physics","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":[0.0002690095,0.0001195528,0.000225031,0.00006382522,0.00004499233,0.000003208452,0.00007139007,0.00002909454,0.000002061839],"category_scores_gemma":[0.00009770114,0.0001284217,0.00004512806,0.0001838282,0.0000229573,0.000110327,0.00001989049,0.00006363611,3.979195e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001296234,"about_ca_system_score_gemma":0.0001126508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001287347,"about_ca_topic_score_gemma":0.000004315935,"domain_scores_codex":[0.999006,0.000006982257,0.0003917389,0.000132201,0.0002976446,0.000165475],"domain_scores_gemma":[0.9990032,0.00002298644,0.0001177749,0.0001369733,0.000692171,0.00002686652],"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":[0.00002293136,0.00002618396,0.00007514806,0.0005496176,0.00003800539,6.875085e-8,0.0007027303,0.1930931,0.7661233,0.000001715269,9.420105e-7,0.03936623],"study_design_scores_gemma":[0.0004318054,0.00003262272,0.001508175,0.0002567516,0.00002056805,3.270374e-7,0.0002083655,0.1513479,0.8460476,0.00003518604,0.000008796922,0.0001019724],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5409257,0.00008014216,0.4584729,0.000001205726,0.00006059645,0.0001277919,0.000003090154,0.00001811588,0.0003104105],"genre_scores_gemma":[0.7955639,0.000005537154,0.2043429,0.000001748459,0.00001232072,0.00004982322,0.000001320372,0.00001570791,0.000006717125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2546382,"threshold_uncertainty_score":0.5236884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03854272541550052,"score_gpt":0.226636116575722,"score_spread":0.1880933911602215,"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."}}