{"id":"W2078914384","doi":"10.1109/icdar.2011.43","title":"Novel Data Representation for Text Extraction from Multispectral Historical Document Images","year":2011,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Multispectral image; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Classifier (UML); Pixel; Grayscale; Support vector machine; Visualization; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001716993,0.0000838843,0.00009108915,0.00005002744,0.00007595639,0.00008736156,0.0008274177,0.00004598356,0.00008806217],"category_scores_gemma":[0.0000744717,0.00007215926,0.00003889363,0.000133057,0.00001652798,0.001438948,0.0001717648,0.00006073122,0.00002681483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001514547,"about_ca_system_score_gemma":0.0000264688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00167129,"about_ca_topic_score_gemma":0.00001609216,"domain_scores_codex":[0.998989,0.00001796566,0.0002164949,0.0004715627,0.0001708209,0.0001341],"domain_scores_gemma":[0.9987832,0.00008832546,0.0001023115,0.0008904675,0.00008535661,0.00005034624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006855695,0.000571918,0.0003587162,0.00001041595,0.00003735422,0.000003586399,0.0006705357,1.620151e-7,0.4142821,0.073649,0.04121236,0.4691353],"study_design_scores_gemma":[0.000508494,0.0001052225,0.01445098,0.000006624166,0.00001832494,0.00000852762,0.00004919471,0.02140985,0.9212512,0.01915824,0.02277154,0.000261838],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001203161,0.00005040571,0.9958825,0.0008539084,0.0003034066,0.0002433793,0.00001500136,0.0003354575,0.002195696],"genre_scores_gemma":[0.1081366,0.00003001267,0.8887518,0.00008973101,0.00009687928,0.00004316971,0.00005887016,0.0000067152,0.002786176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.506969,"threshold_uncertainty_score":0.2942569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1589893034306319,"score_gpt":0.3497189274167667,"score_spread":0.1907296239861348,"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."}}