{"id":"W2032227036","doi":"10.1145/502187.502211","title":"Extraction of text areas in printed document images","year":2001,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"","keywords":"Computer science; Grayscale; Relevance (law); Heuristic; Artificial intelligence; Texture (cosmology); Information retrieval; Historical document; Pattern recognition (psychology); Image texture; Image (mathematics); Image segmentation","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":[0.0001924516,0.0007646639,0.000817382,0.004299433,0.0003723598,0.001046738,0.0005477972,0.0005766846,0.003223521],"category_scores_gemma":[0.00110535,0.000290214,0.00053909,0.002069675,0.0003518181,0.001131003,0.0003559685,0.0004178319,0.003658007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002187429,"about_ca_system_score_gemma":0.0002610808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007651362,"about_ca_topic_score_gemma":0.00105797,"domain_scores_codex":[0.9997509,0.00001867207,0.00002474566,0.00008039507,0.00008377977,0.00004146245],"domain_scores_gemma":[0.9993744,0.0001904868,0.0001145879,0.00008169298,0.0001849373,0.00005386409],"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":[0.0004052796,0.00006391622,0.001800531,0.0007185558,0.00005062496,0.0006821025,0.0001368042,0.001272175,0.4237483,0.0005264095,0.002582311,0.568013],"study_design_scores_gemma":[0.00009960915,0.0005735015,0.06184287,0.0001587884,0.0004323599,0.004015245,0.0004965863,0.06731611,0.8316486,0.002287083,0.0310117,0.0001175764],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.360397,0.008852611,0.5978369,0.0004952974,0.0003674708,0.0006721336,0.00305655,0.01623998,0.01208213],"genre_scores_gemma":[0.4981675,0.002872124,0.4856296,0.0001600472,0.000382201,0.0001666518,0.002832974,0.0008879108,0.008901037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004299433,"threshold_uncertainty_score":0.01078373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397286425030037,"score_gpt":0.2853917206151558,"score_spread":0.2714188563648555,"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."}}