{"id":"W2119306545","doi":"10.1109/icdar.2005.32","title":"A statistical learning approach to document image analysis","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Document layout analysis; Heuristic; Artificial intelligence; Field (mathematics); Segmentation; Image segmentation; Classifier (UML); Software; Statistical learning; Machine learning; Statistical analysis; Variety (cybernetics); Image (mathematics); Pattern recognition (psychology); Data mining","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":[0.00438534,0.001107372,0.001883822,0.005943641,0.0007098814,0.00309753,0.002470954,0.001419039,0.001935998],"category_scores_gemma":[0.01483101,0.0006421951,0.001834673,0.006360852,0.001740305,0.00226292,0.001280228,0.002426413,0.001389238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001311412,"about_ca_system_score_gemma":0.001684793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003445374,"about_ca_topic_score_gemma":0.002779957,"domain_scores_codex":[0.9960589,0.001230837,0.0003725004,0.0008458372,0.001345256,0.0001467178],"domain_scores_gemma":[0.9899547,0.00660469,0.0006184597,0.0009525939,0.00172781,0.0001417287],"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":[0.00009534394,0.0002282127,0.003615698,0.0005041898,0.0003651189,0.0002078386,0.0001876461,0.1946185,0.004897165,0.06236043,0.007998249,0.7249216],"study_design_scores_gemma":[0.00001807149,0.00008439864,0.001152106,0.00004259006,0.00004576355,0.0001785198,0.00005106198,0.8878708,0.00267654,0.1005368,0.007302938,0.0000404157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001448397,0.000579578,0.9966503,0.0002103371,0.00004299837,0.00004530726,0.0001212255,0.0004351476,0.0004668453],"genre_scores_gemma":[0.1146336,0.001933638,0.8778327,0.0003702013,0.0007347731,0.0004730458,0.001173103,0.000207095,0.002641844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005943641,"threshold_uncertainty_score":0.02319217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01128092482742816,"score_gpt":0.2770110766983321,"score_spread":0.265730151870904,"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."}}