{"id":"W4385689129","doi":"10.21203/rs.3.rs-3236568/v1","title":"Research on Low-light Image Enhancement Based on MER-Retinex Algorithm","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"MD Precision (Canada)","funders":"Government of Jiangsu Province; Jiangsu University; National Natural Science Foundation of China","keywords":"Fuse (electrical); Color constancy; Artificial intelligence; Computer vision; Computer science; Brightness; Image enhancement; Pyramid (geometry); Image (mathematics); Convolution (computer science); Feature (linguistics); Algorithm; Mathematics; Artificial neural network; Optics; Engineering","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":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01874001,0.0007656965,0.000733937,0.004268083,0.001059865,0.001864555,0.007193417,0.0006446227,0.0004699936],"category_scores_gemma":[0.001312657,0.0007211115,0.0003651029,0.003601146,0.000552452,0.0003651226,0.009117441,0.00721106,0.006720116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002006477,"about_ca_system_score_gemma":0.001542257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000300261,"about_ca_topic_score_gemma":0.00001328881,"domain_scores_codex":[0.9785594,0.003712059,0.0008683699,0.003326711,0.01056138,0.002972137],"domain_scores_gemma":[0.9875751,0.00240301,0.0002014584,0.00610907,0.003175363,0.0005360473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003054324,0.003570985,0.00001879331,0.003452143,0.0001674044,0.002653824,0.001329741,0.0006956171,0.01965772,0.0145092,0.7639566,0.1896826],"study_design_scores_gemma":[0.0009979845,0.003978965,0.0003439197,0.008482472,0.000007763326,0.000001905186,0.0002308406,0.3243248,0.613711,0.01529819,0.03114785,0.001474318],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008733648,0.0001924209,0.9114279,0.02983028,0.001611886,0.006898914,0.0001575155,0.002771177,0.04623651],"genre_scores_gemma":[0.350487,0.002221099,0.5349303,0.001837222,0.004911454,0.02570257,0.001349506,0.001218218,0.07734261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7328087,"threshold_uncertainty_score":0.999524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074420871726595,"score_gpt":0.4573890434734251,"score_spread":0.3499469563007656,"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."}}