{"id":"W4399290995","doi":"10.3390/a17060238","title":"Simple Histogram Equalization Technique Improves Performance of VGG Models on Facial Emotion Recognition Datasets","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Histogram equalization; Adaptive histogram equalization; Computer science; Histogram; Simple (philosophy); Pattern recognition (psychology); Artificial intelligence; Equalization (audio); Histogram matching; Computer vision; Image (mathematics); Algorithm","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":[0.0003175792,0.0001574234,0.000158497,0.0002894551,0.00007675995,0.00003086896,0.00009213505,0.0001984833,0.0004675711],"category_scores_gemma":[0.00001822129,0.0001544212,0.00007753871,0.0003041025,0.00005294108,0.000335877,0.00002168414,0.0001906934,0.0003257029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006098229,"about_ca_system_score_gemma":0.00002705696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008788353,"about_ca_topic_score_gemma":0.000005501444,"domain_scores_codex":[0.9987731,0.000103701,0.0003491653,0.0003665556,0.0002024188,0.0002050849],"domain_scores_gemma":[0.9994831,0.00004749032,0.0001021173,0.0002289555,0.00008504066,0.00005329596],"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":[0.00006822663,0.0002474732,0.000007354095,0.0001417475,0.00004669443,0.000008199213,0.0006578354,0.00005410901,0.007010191,0.001315802,0.005390327,0.985052],"study_design_scores_gemma":[0.005421271,0.01038262,0.004752781,0.002222086,0.0007272291,0.0004842867,0.002114107,0.5751518,0.1937649,0.09803782,0.1036449,0.003296187],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4746545,0.0005151034,0.4754315,0.000281132,0.005885705,0.002634672,0.003568482,0.001365526,0.03566346],"genre_scores_gemma":[0.9905729,0.0001167513,0.001655712,0.0001581933,0.0002602751,0.0001748547,0.006598279,0.00003889938,0.0004241447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9817559,"threshold_uncertainty_score":0.6297113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05486558358259571,"score_gpt":0.3333654704945068,"score_spread":0.2784998869119111,"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."}}