{"id":"W2959936046","doi":"10.1109/tpami.2019.2927311","title":"Blind Deblurring of Barcodes via Kullback-Leibler Divergence","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"QR Code Applications and Technologies","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universities Space Research Association; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Deblurring; Barcode; Computer science; Artificial intelligence; Computer vision; Divergence (linguistics); Kullback–Leibler divergence; Focus (optics); Exploit; Image (mathematics); Pattern recognition (psychology); Encoding (memory); Image processing; Image restoration; Computer security","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":[0.0001549411,0.0001707564,0.0002860507,0.0005478601,0.0001110329,0.00005787702,0.0006996855,0.00006769509,0.0002164657],"category_scores_gemma":[0.000002175635,0.0001454115,0.0001878502,0.001437428,0.0000763506,0.0002207474,0.00001800228,0.000186213,0.00007385537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001564976,"about_ca_system_score_gemma":0.00001222825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007294428,"about_ca_topic_score_gemma":0.0003089231,"domain_scores_codex":[0.9987335,0.00002853955,0.0003417095,0.0004798447,0.0002247763,0.0001916195],"domain_scores_gemma":[0.9988719,0.0001011507,0.0001121263,0.0007687901,0.00008583719,0.00006014421],"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":[0.000008568986,0.0001745839,0.01130598,0.00002724516,0.0003769204,0.000001876661,0.0001791143,0.01983373,0.005505979,0.001123292,0.000002398983,0.9614603],"study_design_scores_gemma":[0.0001192099,0.0001398063,0.003881888,0.00002656005,0.0002134162,0.000006686545,0.00006101003,0.5267408,0.4671409,0.001289989,0.00008052432,0.0002991101],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06251198,0.0001233988,0.9367484,0.0001825653,0.00008037632,0.0001319685,0.00001356294,0.00009336777,0.0001144042],"genre_scores_gemma":[0.9924715,0.0004280409,0.006855052,0.00008241101,0.000003810311,0.00002284336,0.000001315492,0.000006716384,0.000128289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9611612,"threshold_uncertainty_score":0.592971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01940410793286551,"score_gpt":0.2595032048779631,"score_spread":0.2400990969450976,"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."}}