{"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of Multi-Level Classifiers and Clustering for Automatic Word Spotting in Historical Document Images","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer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Supérieure","funders":"","keywords":"Spotting; Computer science; Artificial intelligence; Word (group theory); Historical document; Preprocessor; Natural language processing; Cluster analysis; Pattern recognition (psychology); Text segmentation; Segmentation; Speech recognition;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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000308325,0.00007556269,0.0001397568,0.0001446203,0.0000305356,0.00003634156,0.0001893454,0.00004217545,0.000001719084],"category_scores_gemma":[0.00004286504,0.00007164245,0.00002685282,0.0001565285,0.00001269199,0.0002656725,0.00005323617,0.00004888449,8.610995e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001657206,"about_ca_system_score_gemma":0.00001381776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003808147,"about_ca_topic_score_gemma":0.00001445468,"domain_scores_codex":[0.9992569,0.00002011065,0.0002809956,0.000214579,0.00009335174,0.0001340604],"domain_scores_gemma":[0.9995846,0.00007972166,0.00009298599,0.0001614379,0.0000433765,0.00003794136],"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":[0.000001734719,0.00003832162,0.0001658491,0.00002955393,0.000001366255,4.25387e-7,0.0001544251,0.000003148269,0.005113179,0.0009876435,0.0001040285,0.9934003],"study_design_scores_gemma":[0.0009468924,0.0001664475,0.03694952,0.0001062968,0.000005870648,0.00001030146,0.00005804127,0.9109047,0.03830559,0.01184434,0.0004379094,0.00026408],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006082139,0.00003841918,0.9923583,0.0007599176,0.00002246218,0.0003799936,5.264899e-7,0.0001773836,0.0001808991],"genre_scores_gemma":[0.4774685,0.000005824304,0.5223173,0.00007599878,0.000005339045,0.00004401242,5.33757e-7,0.000002219944,0.0000802627],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9931362,"threshold_uncertainty_score":0.2921495,"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."}}