{"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science; Grayscale; Relevance (law); Heuristic; Artificial intelligence; Texture (cosmology); Information retrieval; Historical document; Pattern recognition (psychology); Image texture; Image (mathematics); Image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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002183477,0.00006509085,0.00009495744,0.0001854119,0.00001342611,0.00003769676,0.000258604,0.00003515874,0.0003183735],"category_scores_gemma":[0.00004036654,0.00005772676,0.00003128738,0.0003294502,0.00001950203,0.000517099,0.00007751062,0.00007085472,0.00005426177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000391227,"about_ca_system_score_gemma":0.00001920286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001686176,"about_ca_topic_score_gemma":0.00003505123,"domain_scores_codex":[0.9992966,0.00003904647,0.0002181609,0.0001790954,0.0001449657,0.0001221495],"domain_scores_gemma":[0.9995331,0.00005818905,0.00006351944,0.0002397415,0.0000733562,0.0000321424],"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":[0.00001470726,0.0003298712,0.008231701,0.0000183894,0.000009942101,0.00005217979,0.0002373158,0.000004935102,0.0459924,0.02040122,0.002181879,0.9225255],"study_design_scores_gemma":[0.0004057925,0.0001415094,0.07781012,0.0001185118,0.000002851655,0.000121496,0.00007563608,0.002014988,0.8855578,0.02712344,0.006378682,0.0002491388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06286649,0.00002456026,0.8850474,0.0007250545,0.00005433153,0.0001848294,3.03188e-7,0.0002888247,0.05080818],"genre_scores_gemma":[0.9299114,0.00007714816,0.06869326,0.0000906456,0.000008965404,0.00002121965,7.003567e-7,0.000003236814,0.001193441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9222763,"threshold_uncertainty_score":0.3485967,"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."}}