{"id":"W2965749646","doi":"10.1109/crv.2019.00013","title":"Rectification of Camera-Captured Document Images with Mixed Contents and Varied Layouts","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Perspective distortion; Rectification; Computer science; Distortion (music); Artificial intelligence; Computer vision; Image rectification; Perspective (graphical); Transformation (genetics); Document layout analysis; Readability; Graphics; Computer graphics (images); Geometric transformation; Information retrieval; Pattern recognition (psychology); Image (mathematics); Physics","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":[0.000164691,0.00009080009,0.0001478082,0.00008172917,0.00002397572,0.00007542234,0.0002192862,0.00003983836,0.00005093385],"category_scores_gemma":[0.00001391675,0.00006712832,0.00001826883,0.0001548545,0.000039887,0.0003874847,0.00006709949,0.00005638459,0.00002546089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001542947,"about_ca_system_score_gemma":0.00001888846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283199,"about_ca_topic_score_gemma":0.00001126764,"domain_scores_codex":[0.9992164,0.00004937338,0.0001693984,0.0002710445,0.0001818338,0.0001119266],"domain_scores_gemma":[0.9992728,0.0000516853,0.0001087459,0.0003425635,0.0001783961,0.00004581981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001757691,0.0003988617,0.02609542,0.0002039229,0.0002211153,0.00001150561,0.002700601,0.000005880484,0.5861295,0.05752638,0.006128597,0.3204025],"study_design_scores_gemma":[0.0007697968,0.0003083679,0.02221008,0.00005884929,0.000009834084,0.00001924647,0.0001140854,0.0004326529,0.9727666,0.002540774,0.0005714311,0.0001983179],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.278609,0.00006278368,0.7072056,0.0008265126,0.0001254996,0.0006973072,0.00000389428,0.0002985667,0.01217085],"genre_scores_gemma":[0.931031,0.00001586258,0.06741119,0.0001463388,0.000004571064,0.00002166064,0.000003597669,0.000005275037,0.001360493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.652422,"threshold_uncertainty_score":0.2737414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005210700750291,"score_gpt":0.2270316061926949,"score_spread":0.2169794991851919,"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."}}