{"id":"W2575991389","doi":"10.1049/iet-bmt.2016.0067","title":"Efficient multimodal ocular biometric system for person authentication based on iris texture and corneal shape","year":2017,"lang":"en","type":"article","venue":"IET Biometrics","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Université de Montréal; Montreal Heart Institute; Hôtel-Dieu de Montréal","funders":"","keywords":"Biometrics; Computer science; Zernike polynomials; Iris recognition; IRIS (biosensor); Artificial intelligence; Pattern recognition (psychology); Fingerprint (computing); Linear discriminant analysis; Authentication (law); Feature extraction; Identifier; Computer vision","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001282305,0.0002375478,0.0002757724,0.006352381,0.0009163594,0.001277206,0.001358103,0.0002452677,0.000007042915],"category_scores_gemma":[0.001432621,0.0002149588,0.0001528031,0.008099459,0.0001456792,0.0001661626,0.0001512337,0.000139858,0.00005628053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002154415,"about_ca_system_score_gemma":0.00007264147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005649843,"about_ca_topic_score_gemma":6.575166e-7,"domain_scores_codex":[0.9976668,0.00006713247,0.0003170789,0.0008060938,0.000748804,0.0003940733],"domain_scores_gemma":[0.9971212,0.0004118764,0.0004359476,0.001389633,0.0004029502,0.0002383508],"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":[0.0001356445,0.002020197,0.007071081,0.001249694,0.0001487594,0.00003637864,0.001214852,0.000228957,0.009010466,0.02659273,0.005379361,0.9469119],"study_design_scores_gemma":[0.001084593,0.0001767482,0.05864333,0.00002640449,0.00002602645,0.000005702167,0.00004947251,0.9343157,0.001291573,0.00001426728,0.004103997,0.0002621907],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1157241,0.000514325,0.8789758,0.001460586,0.001714607,0.0009091976,0.0001720893,0.0002471323,0.0002821362],"genre_scores_gemma":[0.9731756,0.000009210031,0.02641235,0.0001105852,0.00008260531,0.00004403127,0.00003468201,0.00001689812,0.0001140296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9466497,"threshold_uncertainty_score":0.9997596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03938993771644497,"score_gpt":0.2787759829980165,"score_spread":0.2393860452815716,"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."}}