{"id":"W4403102908","doi":"10.1007/s10032-024-00499-2","title":"Unpaired document image denoising for OCR using BiLSTM enhanced CycleGAN","year":2024,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Image (mathematics); Noise reduction; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004331021,0.0008216289,0.0005293205,0.0008279482,0.0003208564,0.0006198544,0.0005122786,0.0006783314,0.005501985],"category_scores_gemma":[0.0008693707,0.0002235745,0.0005420398,0.000560876,0.0002601805,0.0006416028,0.0006818137,0.0009938268,0.00305199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018271,"about_ca_system_score_gemma":0.0007658515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002010443,"about_ca_topic_score_gemma":0.005458413,"domain_scores_codex":[0.999721,0.00002485656,0.00001552274,0.0000677102,0.0001191395,0.00005170852],"domain_scores_gemma":[0.999653,0.00005261093,0.00002079551,0.00007333241,0.0001823905,0.00001779437],"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":[0.0004315579,0.0001187889,0.001000041,0.0002769693,0.00005898598,0.0001267576,0.00008816135,0.006869481,0.3026885,0.002013169,0.004071963,0.6822556],"study_design_scores_gemma":[0.00002843051,0.0004456171,0.006793453,0.00007885181,0.0001695934,0.0007049369,0.0001149749,0.4423486,0.521585,0.002383577,0.02529039,0.0000565177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1020211,0.001743798,0.8792474,0.0003653048,0.0003886012,0.0001654836,0.0007110529,0.0057003,0.00965689],"genre_scores_gemma":[0.3967418,0.001315649,0.5729058,0.0003582097,0.000117315,0.0001721636,0.002582805,0.0007169545,0.02508929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005501985,"threshold_uncertainty_score":0.01840597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02578919183659872,"score_gpt":0.3390521256032745,"score_spread":0.3132629337666758,"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."}}