{"id":"W4392200088","doi":"10.18280/isi.290102","title":"An Arabic OCR Approach Using Levenshtein Distance and CNNs","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Levenshtein distance; Arabic; Computer science; Natural language processing; Artificial intelligence; Edit distance; Pattern recognition (psychology); Information retrieval; Linguistics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001139933,0.0003400008,0.0003042512,0.000444561,0.0004018475,0.003398075,0.0004203674,0.0002701048,0.00003852077],"category_scores_gemma":[0.0001147807,0.0003624635,0.00009057855,0.0009689567,0.0004398007,0.01815416,0.0001506013,0.000351452,0.0001110337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004866459,"about_ca_system_score_gemma":0.0002623769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002372359,"about_ca_topic_score_gemma":0.0000105113,"domain_scores_codex":[0.9976898,0.0002433815,0.0007770134,0.0003891443,0.0003811231,0.0005195377],"domain_scores_gemma":[0.998708,0.00009203769,0.0002094629,0.0004668041,0.0003132206,0.0002104757],"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":[0.000007869427,0.00004662616,0.0001119301,0.002347365,0.00003995766,0.00001828671,0.01656816,0.0002729164,0.0003074584,0.1133169,0.0004989797,0.8664636],"study_design_scores_gemma":[0.0001437127,0.0001514811,0.0003566838,0.00154569,0.0000416683,0.0006771107,0.0007359341,0.9442692,0.00183319,0.03255515,0.01718496,0.0005051552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02934629,0.006377574,0.9549117,0.0001918218,0.0009765766,0.0004922703,0.00009099145,0.0008505409,0.006762199],"genre_scores_gemma":[0.8508208,0.0003076898,0.1479677,0.0002028645,0.0002106759,0.00005633417,0.00008660689,0.00002595099,0.0003213373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9439964,"threshold_uncertainty_score":0.9998828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03419965796406964,"score_gpt":0.2712157592345862,"score_spread":0.2370161012705166,"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."}}