{"id":"W2031691644","doi":"10.1007/s10032-002-0081-9","title":"Iterative model-based binarization algorithm for cheque images","year":2002,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cheque; Computer science; Artificial intelligence; Handwriting; Pattern recognition (psychology); Histogram; Noise (video); Image (mathematics); Computer vision; Wavelet; Grayscale; Algorithm","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":[0.0003648245,0.0001559394,0.000188686,0.0007657083,0.000215173,0.0009353423,0.0003768918,0.00006445188,0.0002000614],"category_scores_gemma":[0.00004737906,0.000126931,0.0002595999,0.0004499014,0.00003959737,0.0008100018,0.00003730979,0.0001476595,0.00001873923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000116236,"about_ca_system_score_gemma":0.0000251415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002876882,"about_ca_topic_score_gemma":6.31709e-7,"domain_scores_codex":[0.9985542,0.00007020024,0.0004091951,0.0003072152,0.0005096061,0.0001495429],"domain_scores_gemma":[0.9984527,0.00007600019,0.0003354987,0.0001294134,0.0009048181,0.000101621],"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":[0.00002291308,0.0002577254,0.00008314396,0.000004467474,0.0006724519,0.00001243741,0.0002165821,0.0003695332,0.000789905,0.002505329,0.000645668,0.9944199],"study_design_scores_gemma":[0.0006974758,0.0001729334,0.0001558887,0.00004469694,0.0001501238,0.00001576663,0.00001427666,0.9531544,0.02434364,0.01972955,0.001310531,0.0002107239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007418558,0.00009555017,0.9939329,0.004421634,0.0001941734,0.000142531,0.00003675346,0.00006593214,0.0003686867],"genre_scores_gemma":[0.7099068,0.001070399,0.2844027,0.002152192,0.0003515618,0.00008523581,0.0001717938,0.00001734248,0.00184194],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9942091,"threshold_uncertainty_score":0.9019527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316602904311791,"score_gpt":0.2844399393836243,"score_spread":0.2612739103405063,"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."}}