{"id":"W3161193347","doi":"10.1142/s0219467822500152","title":"Histogram of Marked Background (HMB) Feature Extraction Method for Arabic Handwriting Recognition","year":2021,"lang":"en","type":"article","venue":"International Journal of Image and Graphics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Handwriting; Histogram; Computer science; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model; Handwriting recognition; Pixel; Feature extraction; Feature (linguistics); Arabic; Image (mathematics); Linguistics","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":[0.0008769491,0.0001020285,0.0001996423,0.0003515621,0.00005883045,0.0002024046,0.0002882778,0.00009200835,0.00001830195],"category_scores_gemma":[0.0003248784,0.00009884396,0.0002054972,0.0002180343,0.00004773544,0.00099694,0.000058261,0.0002414007,5.933136e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003422483,"about_ca_system_score_gemma":0.00008852955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006797891,"about_ca_topic_score_gemma":0.00001082097,"domain_scores_codex":[0.9988033,0.000113599,0.0004370497,0.000170906,0.0003672823,0.0001079261],"domain_scores_gemma":[0.9960396,0.0004029268,0.0005469602,0.0001035435,0.00284577,0.00006121987],"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":[0.0001336784,0.0002498674,0.0002538345,0.00008649495,0.0002756772,0.0001825531,0.0002323311,7.555697e-7,0.1204265,0.004596832,0.003877601,0.8696839],"study_design_scores_gemma":[0.00439201,0.0008303464,0.00657728,0.001448518,0.000235421,0.009732521,0.0006421556,0.01057233,0.6801453,0.2472672,0.0374486,0.0007083719],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01567921,0.0004746541,0.9802429,0.002679195,0.000463462,0.00007883757,0.00002403049,0.000023417,0.000334287],"genre_scores_gemma":[0.09031337,0.0009108828,0.9078467,0.0005239898,0.0002638272,0.000008011814,0.00002683543,0.00001114869,0.00009526759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8689755,"threshold_uncertainty_score":0.403074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02662348158805402,"score_gpt":0.3361669086376732,"score_spread":0.3095434270496192,"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."}}