{"id":"W4381512791","doi":"10.21203/rs.3.rs-3074040/v1","title":"Unpaired Document Image Denoising for OCR using BiLSTM enhanced CycleGAN","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Ground truth; Discriminator; Optical character recognition; Pattern recognition (psychology); Feature (linguistics); Image (mathematics); Deep learning; Noise (video); Focus (optics); Feature extraction; Noise reduction; Historical document","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":[0.0003520622,0.0008268779,0.0004758495,0.0005298493,0.0002157677,0.000468162,0.0008826737,0.0006415827,0.002706892],"category_scores_gemma":[0.0007899134,0.0002104273,0.0004934825,0.0002860937,0.0003752806,0.0007577665,0.0005078345,0.0009124807,0.001105384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005692621,"about_ca_system_score_gemma":0.000489442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003452882,"about_ca_topic_score_gemma":0.006190183,"domain_scores_codex":[0.999811,0.0000207306,0.000009040651,0.00005856111,0.00006674762,0.00003387719],"domain_scores_gemma":[0.9997408,0.00006555609,0.00003000518,0.00005604545,0.00009108942,0.00001651843],"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":[0.0005007776,0.0002387757,0.001417641,0.0002872,0.0001411112,0.0002772128,0.0001069291,0.1354492,0.2077839,0.003665158,0.004615844,0.6455162],"study_design_scores_gemma":[0.00001158052,0.0001538882,0.0007867434,0.00002126503,0.00003632362,0.0001300383,0.00001632835,0.9271302,0.06784104,0.001055454,0.002800012,0.0000171075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.203742,0.001550982,0.7768452,0.0004649829,0.0002901581,0.0001740921,0.0003140814,0.006631629,0.009986725],"genre_scores_gemma":[0.7614084,0.0005641255,0.2246147,0.0003755124,0.00006476764,0.0001148228,0.0007641193,0.0002537507,0.01183963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003452882,"threshold_uncertainty_score":0.009055436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1399532917035627,"score_gpt":0.4447921253720211,"score_spread":0.3048388336684584,"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."}}