{"id":"W3143770518","doi":"10.1109/iciap.2007.4362749","title":"Collarette Area Localization and Asymmetrical Support Vector Machines for Efficient Iris Recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Support vector machine; Iris recognition; Artificial intelligence; Pattern recognition (psychology); Computer science; IRIS (biosensor); Feature (linguistics); Feature extraction; Feature vector; Computer vision; Biometrics","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":[0.0008103046,0.00008086178,0.00009657819,0.0005124282,0.0001372889,0.0001569912,0.0001663167,0.00007523313,0.00003798859],"category_scores_gemma":[0.0002693504,0.0000714033,0.00003687652,0.001857346,0.00003008329,0.0001170063,0.00005443075,0.00004234998,0.00002041541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004316815,"about_ca_system_score_gemma":0.00002574836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001996602,"about_ca_topic_score_gemma":0.0000125017,"domain_scores_codex":[0.9990374,0.00002098377,0.000236724,0.000293814,0.0002288316,0.0001822049],"domain_scores_gemma":[0.9992103,0.0002040252,0.00006918865,0.0001725867,0.0002381645,0.0001057256],"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":[0.0000631591,0.0005699039,0.004885247,0.00009697877,0.00003647412,0.000009669128,0.0007662299,0.0000261304,0.0009970143,0.0516198,0.04520493,0.8957245],"study_design_scores_gemma":[0.001237059,0.0002508682,0.03812465,0.000009377758,0.00002302243,0.00003742236,0.0000550635,0.8651264,0.011423,0.002594779,0.08068454,0.0004338754],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01187344,0.00004729626,0.9855013,0.0006695859,0.0003493265,0.0002784555,0.00001312612,0.0001164094,0.001151072],"genre_scores_gemma":[0.9537166,0.00001112904,0.04479203,0.000901274,0.0000541809,0.00001322194,0.0000806657,0.000006624387,0.0004242834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9418432,"threshold_uncertainty_score":0.2911742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03148888884385603,"score_gpt":0.2732338798476915,"score_spread":0.2417449910038355,"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."}}