{"id":"W1990643530","doi":"10.1016/j.patcog.2008.10.021","title":"RSLDI: Restoration of single-sided low-quality document images","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Concordia University","keywords":"Computer science; Artificial intelligence; Classifier (UML); Bayesian probability; Document image processing; Pixel; Pattern recognition (psychology); Image restoration; Machine learning; Data mining; Image (mathematics); Computer vision; Image processing; Image segmentation","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002401557,0.0001149384,0.0001522127,0.00013051,0.00006087919,0.00006035536,0.0001838965,0.00005363847,0.0000222994],"category_scores_gemma":[0.0002059384,0.0001179777,0.00006630127,0.0002363762,0.00007126552,0.001153532,0.00006841417,0.00007310934,0.0001816154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007912227,"about_ca_system_score_gemma":0.00002770097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067393,"about_ca_topic_score_gemma":0.00002619503,"domain_scores_codex":[0.998668,0.0001031237,0.0003845801,0.0002886008,0.000389503,0.0001662455],"domain_scores_gemma":[0.9990447,0.0001175332,0.0002507452,0.0003109126,0.0002145189,0.00006157676],"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":[0.00001581545,0.0001693842,0.001106851,0.00004881898,0.00001297264,0.00001550426,0.0005088731,0.00000667391,0.03090805,0.00002790061,0.0006026963,0.9665765],"study_design_scores_gemma":[0.0008432941,0.0004519655,0.03553011,0.0002104697,0.00001106698,0.00008723263,0.00004222381,0.0005185591,0.948552,0.01322332,0.0001661946,0.0003635866],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7018253,0.00001452629,0.2950054,0.0001757845,0.000693249,0.0001718918,0.00001067878,0.0001377353,0.001965367],"genre_scores_gemma":[0.9953166,0.0000136388,0.00430729,0.0001412922,0.00009180867,0.00002463124,0.0000473913,0.000008626179,0.00004873493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9662129,"threshold_uncertainty_score":0.4810993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05353682242814526,"score_gpt":0.2622833866411715,"score_spread":0.2087465642130262,"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."}}