{"id":"W4410982446","doi":"10.1007/s42452-025-07163-2","title":"Brightness adjustment and contrast matching in low-light underwater images using feedforward neural networks","year":2025,"lang":"en","type":"article","venue":"Discover Applied Sciences","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Becton Dickinson (Canada)","funders":"","keywords":"Brightness; Contrast (vision); Underwater; Feedforward neural network; Matching (statistics); Artificial intelligence; Feed forward; Computer vision; Computer science; Artificial neural network; Pattern recognition (psychology); Optics; Mathematics; Geology; Physics; Engineering; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005034896,0.0006622722,0.0005754574,0.0005269104,0.0002359657,0.0005883228,0.0008800329,0.0007823999,0.00107458],"category_scores_gemma":[0.001386408,0.0003613304,0.0005541988,0.000352108,0.0003268294,0.0007688536,0.0004691936,0.0008271758,0.0002488047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006441717,"about_ca_system_score_gemma":0.0004625974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005855304,"about_ca_topic_score_gemma":0.006819552,"domain_scores_codex":[0.9998441,0.00002242506,0.000009099077,0.00005445506,0.00003897748,0.00003097135],"domain_scores_gemma":[0.9996649,0.0001380118,0.000047124,0.00002380443,0.0001086415,0.000017575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003247196,0.0002154653,0.002309692,0.0001309642,0.00009628123,0.0001527421,0.00009467271,0.4930686,0.04409833,0.002412089,0.001603524,0.455493],"study_design_scores_gemma":[0.00000419456,0.0000174542,0.0002406947,0.000004159434,0.00000906668,0.0000121265,0.000003658937,0.9960163,0.003174306,0.000394708,0.0001198632,0.00000338167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009104,0.0005480114,0.8948125,0.0001914126,0.00007851544,0.00006609286,0.00006170446,0.001027826,0.002303625],"genre_scores_gemma":[0.7860238,0.0004133898,0.2080138,0.000199944,0.00006665885,0.00008275559,0.0002359696,0.0001009114,0.004862692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005855304,"threshold_uncertainty_score":0.0116424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009539752483074043,"score_gpt":0.261366968090301,"score_spread":0.251827215607227,"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."}}