{"id":"W4229455692","doi":"10.18280/ts.390218","title":"A Hybrid System for Handwritten Character Recognition with High Robustness","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesinstitut für Bau- Stadt- und Raumforschung","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Character (mathematics); Numeral system; Robustness (evolution); Speech recognition; Benchmark (surveying); Bengali; Feature (linguistics); Feature extraction; Support vector machine; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006796364,0.0002233617,0.0002618481,0.0002250324,0.0004776718,0.0002061584,0.0006472221,0.00002881483,0.0003614766],"category_scores_gemma":[0.000004795212,0.0002062165,0.0001011146,0.0002500829,0.00003255501,0.000529581,0.0001720179,0.0001740145,0.00001943872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002113487,"about_ca_system_score_gemma":0.00007912885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001845797,"about_ca_topic_score_gemma":0.000001888773,"domain_scores_codex":[0.9979934,0.0001521244,0.0003679049,0.0005519802,0.0005434224,0.0003911575],"domain_scores_gemma":[0.9990925,0.00009632903,0.000204439,0.0002950906,0.0002075127,0.0001041973],"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":[0.001566536,0.002342989,0.0003265297,0.001133889,0.0006624,0.0006303216,0.001737919,0.002073807,0.02366547,0.02412176,0.02440858,0.9173298],"study_design_scores_gemma":[0.02151519,0.0124682,0.002038371,0.0009986396,0.0004878517,0.003283156,0.001353467,0.3589968,0.5346113,0.008748249,0.05071443,0.004784335],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1513216,0.00001533458,0.8453879,0.0006922016,0.0002081721,0.001180936,0.0001993494,0.0007810539,0.0002134334],"genre_scores_gemma":[0.948123,0.000001833202,0.04771362,0.0004879751,0.0001934868,0.003078568,0.0002616378,0.00003130106,0.0001085335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9125454,"threshold_uncertainty_score":0.8409263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01764062795760965,"score_gpt":0.2130707335862049,"score_spread":0.1954301056285952,"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."}}