{"id":"W2098345386","doi":"10.1007/s10032-006-0020-2","title":"A survey of document image classification: problem statement, classifier architecture and performance evaluation","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Xerox Foundation","keywords":"Computer science; Classifier (UML); Document classification; Contextual image classification; Artificial intelligence; Pattern recognition (psychology); Problem statement; Ambiguity; Information retrieval; Machine learning; Data mining; Image (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":[0.003731072,0.001218116,0.002794222,0.003964697,0.00075907,0.003185854,0.002452061,0.001967617,0.001434986],"category_scores_gemma":[0.008718997,0.0007173229,0.0009653019,0.006239125,0.0004197347,0.003615565,0.0006418457,0.001242224,0.001712759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008978,"about_ca_system_score_gemma":0.001748562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003638311,"about_ca_topic_score_gemma":0.003862725,"domain_scores_codex":[0.9970958,0.0004520192,0.0003520037,0.0007316673,0.001231137,0.0001373405],"domain_scores_gemma":[0.9938629,0.002693512,0.0003624112,0.0004619262,0.002459633,0.000159736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001593427,0.0002539401,0.004536844,0.001134036,0.00009467301,0.00002546059,0.00005404063,0.005032678,0.004021173,0.001621063,0.007957368,0.9751093],"study_design_scores_gemma":[0.0001219464,0.002926777,0.03261197,0.00185069,0.0009206504,0.002744338,0.0007909804,0.7052299,0.06805705,0.0206951,0.1637381,0.0003125297],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.06427073,0.3215495,0.5986701,0.002675424,0.0007385037,0.0004338848,0.001171101,0.002961402,0.007529376],"genre_scores_gemma":[0.226587,0.2213648,0.5292168,0.001423523,0.002899596,0.0005866138,0.005379091,0.0004909603,0.01205164],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003964697,"threshold_uncertainty_score":0.01973206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02727027337698614,"score_gpt":0.3066844968063903,"score_spread":0.2794142234294041,"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."}}