{"id":"W3119900290","doi":"10.18280/ts.370623","title":"A Hybrid Classifier for Handwriting Recognition on Multi-domain Financial Bills Based on DCNN and SVM","year":2020,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Support vector machine; Classifier (UML); Handwriting; Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Machine learning; Benchmark (surveying); Artificial neural network; Finance","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455537,0.0001540199,0.0001394173,0.0001054245,0.0002143958,0.0001293368,0.0001083747,0.00004239007,0.00005847425],"category_scores_gemma":[0.00007340878,0.0001476746,0.00008649562,0.0001379806,0.00002480026,0.0001698992,0.00002168726,0.0001220808,0.00004617923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004107832,"about_ca_system_score_gemma":0.00004336051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002024334,"about_ca_topic_score_gemma":0.000002347971,"domain_scores_codex":[0.9988169,0.00006464553,0.0002406347,0.0004384736,0.0002231646,0.0002161486],"domain_scores_gemma":[0.9994838,0.0001536567,0.0000842798,0.00007594623,0.00006936351,0.0001330011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005252896,0.0003726502,0.00005736528,0.0001137055,0.00001297593,0.00001872732,0.0003636023,0.000134371,0.006771944,0.00128671,0.002581567,0.9877611],"study_design_scores_gemma":[0.005732796,0.002119652,0.0009847106,0.0001801659,0.00001675499,0.000007579703,0.00005471967,0.9589984,0.02435054,0.001004695,0.006169228,0.0003806868],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0683447,0.000006972113,0.9287934,0.001411507,0.000215972,0.0005056306,0.00008296315,0.0001816169,0.0004572468],"genre_scores_gemma":[0.9779674,0.000001830161,0.01794714,0.003595227,0.0003037534,0.0001238364,0.00004257907,0.00001066607,0.000007544728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9873804,"threshold_uncertainty_score":0.6021994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07036183805954983,"score_gpt":0.2547364047613149,"score_spread":0.1843745667017651,"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."}}