{"id":"W4395081704","doi":"10.20944/preprints202404.1540.v1","title":"Simple Histogram Equalization Technique Improves Performance of VGG models on Facial Emotion Recognition Datasets","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simple (philosophy); Histogram equalization; Histogram; Pattern recognition (psychology); Computer science; Adaptive histogram equalization; Artificial intelligence; Equalization (audio); Speech recognition; Algorithm; Image (mathematics)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009523872,0.0004599407,0.0004837497,0.0006079831,0.0001037463,0.00002704566,0.000385869,0.0008863612,0.001770722],"category_scores_gemma":[0.0001082593,0.00050103,0.0002600167,0.0002631397,0.0001149612,0.0001671573,0.0007663909,0.001196842,0.002556343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002200842,"about_ca_system_score_gemma":0.0001094301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000270933,"about_ca_topic_score_gemma":0.00001773751,"domain_scores_codex":[0.9966571,0.0003526433,0.0009512189,0.001260722,0.0004137362,0.0003645426],"domain_scores_gemma":[0.9978021,0.00005549005,0.0006418773,0.001131732,0.0002551253,0.000113613],"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":[0.00324592,0.006694742,0.01156539,0.01168455,0.001774657,0.00006317651,0.01492421,0.006319341,0.2391216,0.01130957,0.009660324,0.6836365],"study_design_scores_gemma":[0.003738982,0.001751968,0.08252184,0.005740453,0.001473431,0.0001114279,0.001101401,0.02366901,0.5357267,0.3263162,0.01345307,0.004395499],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9575305,0.00006937281,0.004420012,0.00009683547,0.002504508,0.002143174,0.001755265,0.0005465885,0.03093375],"genre_scores_gemma":[0.9854798,0.0001975942,0.0002359101,0.0001404593,0.000281128,0.0008407928,0.01202139,0.00008911241,0.0007138621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.679241,"threshold_uncertainty_score":0.9997441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1901321192584262,"score_gpt":0.3954394452951361,"score_spread":0.2053073260367099,"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."}}