{"id":"W2166637660","doi":"10.1109/icdar.2009.230","title":"Evaluation of Different Strategies to Optimize an HMM-Based Character Recognition System","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Hidden Markov model; Computer science; Character (mathematics); Pattern recognition (psychology); Character recognition; Speech recognition; Artificial intelligence; Noise (video); Noise reduction; Reduction (mathematics); Process (computing); Optical character recognition; Mathematics","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":[0.001165934,0.0001457292,0.0001993579,0.0002480801,0.00004777364,0.0001903397,0.0003780915,0.00007272328,0.0001043196],"category_scores_gemma":[0.00003372711,0.0001220297,0.00006022072,0.0002464434,0.00001187146,0.0008666023,0.00002482881,0.00006566643,0.00004783354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216106,"about_ca_system_score_gemma":0.0001179206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001451297,"about_ca_topic_score_gemma":0.000009737735,"domain_scores_codex":[0.9980568,0.0003213862,0.0003407287,0.0003394249,0.0007643371,0.0001773536],"domain_scores_gemma":[0.9983656,0.00003674001,0.000124196,0.0004425877,0.0009216946,0.0001091931],"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":[0.00001888754,0.0003147209,0.00001187176,0.00002850702,0.0000121744,0.000001633369,0.0002705631,0.000129277,0.02328052,0.005748855,0.0001313364,0.9700516],"study_design_scores_gemma":[0.0009444202,0.001325979,0.008744427,0.0002715777,0.0000713798,0.000008756873,0.0002590951,0.3215855,0.6519214,0.01443111,0.00001725904,0.0004190938],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2377523,0.000005432574,0.7535113,0.0003683938,0.00008913186,0.0006277816,0.00000520859,0.0006085175,0.007031948],"genre_scores_gemma":[0.9106128,0.000001116478,0.08889682,0.0003271123,0.0000360098,0.00008274949,0.0000266421,0.000005517136,0.0000111817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9696326,"threshold_uncertainty_score":0.4976226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05528795764964188,"score_gpt":0.3068130193020752,"score_spread":0.2515250616524333,"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."}}