{"id":"W4402307091","doi":"10.18280/ts.410417","title":"Optimizing and Assessing the Quality of E-Commerce Product Images Using Deep Learning Techniques","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Product (mathematics); Computer science; Artificial intelligence; Deep learning; Machine learning; Data science; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001253377,0.0001170102,0.0001683188,0.00009198487,0.0001346049,0.00019215,0.00005327343,0.00004771837,0.00002748276],"category_scores_gemma":[0.00002551163,0.0000859408,0.00005522764,0.0001812459,0.00003515192,0.0002378462,0.00002298528,0.0002452687,9.474581e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004560524,"about_ca_system_score_gemma":0.00001056169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007356482,"about_ca_topic_score_gemma":0.000001512503,"domain_scores_codex":[0.9990503,0.0001332634,0.000346083,0.0001493576,0.0001823478,0.0001386468],"domain_scores_gemma":[0.9996727,0.0001355797,0.00004944555,0.00008415333,0.0000346599,0.00002348382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000750459,0.00001009781,0.000409008,0.0003870166,0.0000717896,0.000003026982,0.001200771,0.01471096,0.8237726,0.0001361815,0.00006250785,0.1592285],"study_design_scores_gemma":[0.0003788829,0.0001413897,0.004784928,0.001041747,0.0001145088,0.00005839,0.002244314,0.3009627,0.6827868,0.0001001351,0.006860774,0.0005253927],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8033101,0.002082226,0.1926546,0.0000405309,0.0002618651,0.000293121,0.000001764029,0.0004116342,0.0009441716],"genre_scores_gemma":[0.9972662,0.00002462456,0.002378855,0.000005685815,0.0002738971,0.00001057274,0.000001305283,0.00002275541,0.00001612518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2862518,"threshold_uncertainty_score":0.3504564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04675535411847966,"score_gpt":0.3242456481312153,"score_spread":0.2774902940127357,"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."}}