{"id":"W2954389471","doi":"10.1049/iet-its.2019.0082","title":"Deep learning‐based embedded license plate localisation system","year":2019,"lang":"en","type":"article","venue":"IET Intelligent Transport Systems","topic":"Vehicle License Plate Recognition","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"License; Artificial intelligence; Deep learning; Computer science; Computer vision; Transport engineering; Engineering; Operating system","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":[0.0001866823,0.0006054199,0.0004941433,0.0005563476,0.000215491,0.0006248016,0.001227618,0.0005289745,0.004551535],"category_scores_gemma":[0.0003549847,0.0002594554,0.0003468081,0.0003656555,0.0001939837,0.0008002349,0.000718975,0.0006215353,0.00259036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006953769,"about_ca_system_score_gemma":0.0007660734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007350953,"about_ca_topic_score_gemma":0.008678779,"domain_scores_codex":[0.9998193,0.00001154224,0.000009337198,0.00004929791,0.0000669338,0.00004360711],"domain_scores_gemma":[0.9998369,0.0000167292,0.00001919774,0.00002455614,0.00008812377,0.00001454109],"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":[0.0006582114,0.0003547544,0.003653817,0.0003071128,0.0001244231,0.0004077109,0.00008953598,0.1627515,0.07457681,0.0036471,0.01212286,0.7413061],"study_design_scores_gemma":[0.00001691112,0.0001226009,0.001232216,0.00001746984,0.00003600688,0.00009086821,0.00002173141,0.9609824,0.03169281,0.000750694,0.005011347,0.00002491608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09666268,0.0009536957,0.8700771,0.0003437006,0.0004333998,0.000118363,0.0006821536,0.01432889,0.0164],"genre_scores_gemma":[0.8620925,0.0003611197,0.107633,0.0003668803,0.00006032009,0.00008571489,0.001352065,0.00009775393,0.0279507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007350953,"threshold_uncertainty_score":0.01522636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0107807604880353,"score_gpt":0.1948081084740234,"score_spread":0.1840273479859881,"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."}}