{"id":"W2111676986","doi":"10.1109/icdar.2009.104","title":"Application of Multi-Level Classifiers and Clustering for Automatic Word Spotting in Historical Document Images","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Spotting; Computer science; Artificial intelligence; Word (group theory); Historical document; Preprocessor; Natural language processing; Cluster analysis; Pattern recognition (psychology); Text segmentation; Segmentation; Speech recognition; Mathematics","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":[0.0008261526,0.0006830572,0.000999955,0.002740844,0.0007416105,0.001029125,0.001110691,0.0009654127,0.002134868],"category_scores_gemma":[0.001957067,0.0004349863,0.0007514127,0.001751675,0.0003078822,0.001108798,0.0005165091,0.0008097482,0.002181912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005752518,"about_ca_system_score_gemma":0.0005878219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003447816,"about_ca_topic_score_gemma":0.004269169,"domain_scores_codex":[0.9991276,0.0001082764,0.00007823804,0.0002557685,0.0003300702,0.0001001279],"domain_scores_gemma":[0.9989244,0.0002664748,0.00009378693,0.0001842899,0.0004696042,0.00006124387],"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":[0.000194483,0.000106906,0.001324149,0.0001507546,0.00006307005,0.0001347476,0.0001261048,0.01068328,0.09509625,0.0007290265,0.003130475,0.8882607],"study_design_scores_gemma":[0.00003876013,0.0002250231,0.01283807,0.0000410394,0.0001078182,0.0005383557,0.0002100394,0.7691191,0.203635,0.002747037,0.01039934,0.0001004682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04635229,0.0005112044,0.9446003,0.00009517808,0.00008875322,0.0001605073,0.0002299531,0.006408033,0.001553732],"genre_scores_gemma":[0.1554167,0.000256856,0.8406493,0.00003875106,0.00004905062,0.0001228913,0.0005850134,0.0002674325,0.002613917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003447816,"threshold_uncertainty_score":0.007141829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03382729573277333,"score_gpt":0.2929195803504617,"score_spread":0.2590922846176884,"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."}}