{"id":"W4281571019","doi":"10.18178/ijmlc.2022.12.5.1095","title":"Improvement in OCR Technologies in Postal Industry Using CNN-RNN Architecture: Literature Review","year":2022,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Computing","topic":"Vehicle License Plate Recognition","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Architecture; Artificial intelligence; Speech recognition; Information retrieval","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":[0.0005288175,0.0001002821,0.0001716011,0.0004294573,0.00004525595,0.00004281114,0.0001602955,0.00005665249,0.00001333548],"category_scores_gemma":[0.00009839774,0.0001004045,0.00004015063,0.000249714,0.00001018786,0.00008105086,0.0001535498,0.002301123,2.173089e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00015799,"about_ca_system_score_gemma":0.00001560654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001484842,"about_ca_topic_score_gemma":0.00000390511,"domain_scores_codex":[0.9990655,0.00007329648,0.0003867288,0.00009266519,0.0002523737,0.0001294922],"domain_scores_gemma":[0.9996655,0.00006805133,0.0001616056,0.00003149108,0.00005423394,0.00001912732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003297333,0.00003772875,0.02724712,0.0001831172,0.0000608224,0.000542071,0.0006087862,0.4922788,0.004634121,0.00001555381,0.00001098011,0.4743479],"study_design_scores_gemma":[0.001963867,0.0002832511,0.005040241,0.01013656,0.00002717418,0.006130818,0.00129372,0.9703577,0.0006394135,0.000539179,0.003165089,0.000422998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779463,0.02026919,0.0005862103,0.0007314738,0.0002801581,0.00005960962,0.000004077764,0.00004752944,0.00007547333],"genre_scores_gemma":[0.9970061,0.001803167,0.001013576,0.00007912659,0.00007234377,9.38104e-7,0.000007897893,0.00001286406,0.000003946437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4780789,"threshold_uncertainty_score":0.9997364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006444327550301196,"score_gpt":0.249473974748473,"score_spread":0.2430296471981718,"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."}}