{"id":"W2127184823","doi":"10.1109/euvip.2010.5699135","title":"Text extraction from degraded document images","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Skeletonization; Computer science; Cluster analysis; Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Pixel; Coherence (philosophical gambling strategy); Historical document; Image (mathematics); Computer vision; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002582276,0.00106073,0.001046013,0.002823367,0.0004432852,0.0009734579,0.0007878555,0.0009180807,0.00301805],"category_scores_gemma":[0.001198779,0.0004495536,0.0008088864,0.001602609,0.0004157189,0.001212172,0.0004397241,0.0005831398,0.00352039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003536182,"about_ca_system_score_gemma":0.0003106822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001040241,"about_ca_topic_score_gemma":0.001527208,"domain_scores_codex":[0.9995833,0.00003671283,0.00003612428,0.0001258151,0.0001729854,0.00004507666],"domain_scores_gemma":[0.9993035,0.0001353754,0.0001069645,0.000148665,0.000277244,0.00002830924],"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":[0.0005825961,0.00004307505,0.0008511061,0.0007514618,0.0001006368,0.0008638304,0.0001717073,0.01067808,0.3684748,0.0009207484,0.004227501,0.6123344],"study_design_scores_gemma":[0.00006902449,0.0002862844,0.01427725,0.0001114621,0.0002866149,0.003487456,0.000392157,0.2904031,0.6459304,0.004633793,0.03998992,0.0001325522],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08445763,0.0026222,0.8984339,0.0002314205,0.00025233,0.0001794356,0.001096465,0.008641862,0.004084703],"genre_scores_gemma":[0.2668502,0.001835877,0.7173696,0.0001260279,0.0002491908,0.0001335848,0.002754695,0.001052454,0.009628474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00301805,"threshold_uncertainty_score":0.01009637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01075154259886924,"score_gpt":0.2694868028965848,"score_spread":0.2587352602977156,"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."}}