{"id":"W2113751483","doi":"10.1109/icdar.2001.953928","title":"Legal amount recognition based on the segmentation hypotheses for bank check processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Computer science; Word (group theory); Text segmentation; Artificial intelligence; Word recognition; Pattern recognition (psychology); Hidden Markov model; Speech recognition; Natural language processing; Mathematics; Linguistics","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":[0.00009251803,0.00007084705,0.00004481981,0.0000374368,0.0002363755,0.000142894,0.0002255499,0.00001910844,0.00004276476],"category_scores_gemma":[0.00002347673,0.00004911724,0.00003460106,0.0001951405,0.00001813409,0.0002894365,0.00001623836,0.00004367449,0.00002806033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003457948,"about_ca_system_score_gemma":0.00001284865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002471676,"about_ca_topic_score_gemma":9.086806e-7,"domain_scores_codex":[0.9994316,0.00001399386,0.0001157405,0.0001953533,0.0001400347,0.0001032442],"domain_scores_gemma":[0.9994603,0.0002027563,0.000064222,0.0001574506,0.00009460893,0.00002068003],"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":[0.000005678572,0.0001713248,0.000005362317,0.00001500319,0.000003574796,3.734296e-7,0.00009552407,0.003901335,0.001733713,0.2432632,0.005275124,0.7455298],"study_design_scores_gemma":[0.0001121684,0.00006321211,0.00004882848,0.00001421808,0.000002201562,0.000001447945,0.00001456885,0.932485,0.01460718,0.04383606,0.008726765,0.00008826882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000582837,0.000007682423,0.9845921,0.006989299,0.00001857155,0.0004315967,0.000003598929,0.0002185503,0.007155745],"genre_scores_gemma":[0.5205497,0.000002281247,0.4755737,0.003048596,0.00004037229,0.0004755922,0.000007746541,0.000006053191,0.000295916],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9285837,"threshold_uncertainty_score":0.2002943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0736769066133279,"score_gpt":0.2948240916134552,"score_spread":0.2211471850001273,"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."}}