{"id":"W4206503538","doi":"10.17762/de.v2021i3.7789","title":"Optical Character Recognition of Indian Language Manuscripts using Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"Design Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sanskrit; Optical character recognition; Character (mathematics); Computer science; Scripting language; Convolutional neural network; Artificial intelligence; Focus (optics); Natural language processing; Character recognition; Writing system; Artificial neural network; Speech recognition; Image (mathematics); Linguistics; Mathematics; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001653428,0.0004809742,0.0002411061,0.0006554658,0.000232302,0.0006778332,0.0006230278,0.0003780181,0.001309119],"category_scores_gemma":[0.0006665168,0.0002138445,0.0004355041,0.0005327779,0.0002257887,0.0005373166,0.0003000646,0.0005586285,0.0006449663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006722971,"about_ca_system_score_gemma":0.0004878662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063842,"about_ca_topic_score_gemma":0.01425536,"domain_scores_codex":[0.9998324,0.00001571166,0.00001236237,0.00005660107,0.00005070954,0.00003221334],"domain_scores_gemma":[0.9997314,0.00005694585,0.00004356187,0.00003257271,0.0001190134,0.00001646125],"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":[0.0003117942,0.0001567825,0.003115206,0.0001825263,0.00009586929,0.0003523921,0.0001235281,0.0993605,0.1253743,0.001874553,0.004946099,0.7641065],"study_design_scores_gemma":[0.00000607119,0.00006859928,0.002947283,0.00001609909,0.00003500703,0.0001267817,0.00005067469,0.940438,0.05247828,0.0006134346,0.003199787,0.00002000456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4209256,0.002492431,0.5501444,0.0006467812,0.0004728269,0.0001123873,0.0006930864,0.007457719,0.01705472],"genre_scores_gemma":[0.8926049,0.0007114987,0.09301758,0.0001349601,0.0000613652,0.00003858925,0.0006673595,0.00007638217,0.01268742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01063842,"threshold_uncertainty_score":0.02115297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03335090864372424,"score_gpt":0.2330881586382673,"score_spread":0.199737249994543,"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."}}