{"id":"W3107636056","doi":"10.1109/access.2020.3041519","title":"Iris Segmentation Using Interactive Deep Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Aalborg Universitet; Deutscher Akademischer Austauschdienst; Indian Statistical Institute; University of Alberta; Uppsala Universitet; Institut national de recherche en informatique et en automatique (INRIA); University Grants Commission; Indian National Science Academy; Meiji University; Intel Corporation","keywords":"Computer science; Deep learning; Segmentation; Artificial intelligence; Machine learning; Component (thermodynamics); Biometrics; IRIS (biosensor); Iris recognition","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.00009079662,0.00005847854,0.00006858209,0.0001192703,0.0001091354,0.0005089187,0.0005998213,0.00002739274,0.00004093145],"category_scores_gemma":[0.000063691,0.00005995205,0.00002894738,0.001107664,0.00001333315,0.001398478,0.0001253722,0.0001241127,0.00007051929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004129318,"about_ca_system_score_gemma":0.00001845181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005801498,"about_ca_topic_score_gemma":0.000002156029,"domain_scores_codex":[0.9993026,0.00006640298,0.0001290374,0.000230487,0.0001698667,0.0001015535],"domain_scores_gemma":[0.9995897,0.00004558507,0.0001015481,0.0001147436,0.00008069794,0.00006767913],"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":[0.00004879344,0.0002235317,0.02651848,0.0001231116,0.0001306345,0.00005327328,0.0379139,0.008373826,0.1356369,0.002518362,0.004004363,0.7844549],"study_design_scores_gemma":[0.0002726252,0.00002905872,0.005756191,0.000007266418,0.000007899254,0.000004744431,0.000224447,0.9448178,0.04336217,0.0002396722,0.005095298,0.000182772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1390608,0.00003243919,0.859513,0.0005888074,0.0003903704,0.00006506158,4.478274e-7,0.00009466337,0.0002544707],"genre_scores_gemma":[0.988808,0.000007985507,0.01025444,0.0008196243,0.00007632966,0.00000301698,0.000002615454,0.000003963815,0.0000240464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936444,"threshold_uncertainty_score":0.4907514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08561528923686526,"score_gpt":0.3554876378840964,"score_spread":0.2698723486472311,"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."}}