{"id":"W2120022046","doi":"10.1109/icdar.2005.129","title":"Hybrid feature extraction and feature selection for improving recognition accuracy of handwritten numerals","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Feature extraction; Computer science; MNIST database; Artificial intelligence; Numeral system; Feature selection; Feature (linguistics); Divergence (linguistics); Artificial neural network","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":[0.0003818853,0.000181445,0.000212902,0.0002215336,0.0001674357,0.0001856492,0.0002085974,0.000152031,0.00003250292],"category_scores_gemma":[0.0002063565,0.000169212,0.00009055595,0.000218866,0.00002796714,0.001955543,0.00006198559,0.000214162,0.000008696126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005891475,"about_ca_system_score_gemma":0.00004793096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003841703,"about_ca_topic_score_gemma":0.00003650596,"domain_scores_codex":[0.998821,0.00005330469,0.0002470329,0.0004411085,0.0001883369,0.0002492804],"domain_scores_gemma":[0.9988511,0.0002153693,0.0002557417,0.0002035458,0.000393861,0.00008036316],"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":[0.00002395297,0.00005236969,0.00005458847,0.00006479207,0.00001289559,3.935008e-7,0.00006643807,9.386783e-7,0.09033924,0.0003615911,0.009381764,0.899641],"study_design_scores_gemma":[0.0006851917,0.000260446,0.0005341303,0.00006578048,0.00003014913,0.0002146979,0.00002383368,0.02944148,0.950541,0.006277006,0.01161546,0.0003108077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03774634,0.0001905567,0.9558259,0.003967936,0.0001173659,0.0007887363,0.00002189839,0.0005660927,0.0007751735],"genre_scores_gemma":[0.472122,0.00007911054,0.5258945,0.000450906,0.0002286749,0.0001200797,0.00003783043,0.00001684148,0.001050063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8993303,"threshold_uncertainty_score":0.6900265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01616392705652347,"score_gpt":0.2751842584176304,"score_spread":0.259020331361107,"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."}}