{"id":"W2004374514","doi":"10.1007/s10044-014-0428-0","title":"Omnifont text recognition of printed cursive scripts via HMMs, compact lossless features, and soft data clustering","year":2014,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute of Cosmetic and Laser Surgery","funders":"","keywords":"Cursive; Computer science; Vector quantization; Pattern recognition (psychology); Artificial intelligence; Optical character recognition; Speech recognition; Feature vector; Cluster analysis; Hidden Markov model","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":[0.0002474074,0.0001059411,0.0002191192,0.0001680437,0.0001220811,0.0001217822,0.0004843946,0.00004272315,0.000009351459],"category_scores_gemma":[0.0000145344,0.00009319043,0.00004508996,0.0005547103,0.00007622551,0.0002214129,0.0002370151,0.00008420397,0.000005627765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001071362,"about_ca_system_score_gemma":0.000008629415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002785966,"about_ca_topic_score_gemma":0.0001185063,"domain_scores_codex":[0.9990265,0.00005306477,0.0002431611,0.0004220789,0.0001417761,0.0001134181],"domain_scores_gemma":[0.9987589,0.00006538184,0.0001973834,0.0007739165,0.0001298912,0.00007454872],"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":[0.000002385276,0.00008523879,0.006069642,0.00004702486,0.000145166,1.842563e-7,0.0001106239,0.000003143165,0.005847441,0.0004831494,0.0001485198,0.9870575],"study_design_scores_gemma":[0.0004901368,0.00007928735,0.3182219,0.00008758543,0.0008181526,0.00002781942,0.0001238328,0.6266752,0.03806612,0.004982722,0.009816978,0.0006101995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001560822,0.0001814242,0.9972202,0.0005441756,0.000008026626,0.0001824683,0.00005904735,0.0000613359,0.0001825708],"genre_scores_gemma":[0.9942136,0.0001396804,0.005168319,0.000142127,0.00002983145,0.00002450377,0.0002225944,0.00000508649,0.00005418705],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9926528,"threshold_uncertainty_score":0.3800195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03277821513927734,"score_gpt":0.2844556664686302,"score_spread":0.2516774513293528,"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."}}