{"id":"W2040322660","doi":"10.1109/icip.2006.312773","title":"IRIS Segmentation: Detecting Pupil, Limbus and Eyelids","year":2006,"lang":"en","type":"article","venue":"","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boundary (topology); Active contour model; IRIS (biosensor); Segmentation; Pupil; Computer vision; Computer science; Artificial intelligence; Eyelid; Geometry; Mathematics; Image segmentation; Physics; Optics; Mathematical analysis; 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":[0.0001737425,0.00004858945,0.00004713592,0.0001470893,0.0001213829,0.0002659213,0.0001663691,0.00002752271,0.00003567772],"category_scores_gemma":[0.00001437868,0.00004447108,0.00001575789,0.0006742455,0.00001977135,0.0002677093,0.00007162761,0.0000399397,0.00004524521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001570934,"about_ca_system_score_gemma":0.00001018262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001790689,"about_ca_topic_score_gemma":0.0000259421,"domain_scores_codex":[0.9994306,0.0000207704,0.0001237727,0.0001891023,0.0001349081,0.0001008617],"domain_scores_gemma":[0.999677,0.00004028926,0.00003574323,0.0001705266,0.0000436927,0.00003274254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000003483133,0.0001848581,0.0187545,0.00004039931,0.00001791266,0.00001437311,0.0009920989,0.00001309884,0.02338668,0.1621342,0.02060952,0.773849],"study_design_scores_gemma":[0.002403025,0.0002317809,0.4367567,0.00002156777,0.00002651362,0.0001985134,0.0007398188,0.1625545,0.1852994,0.02725264,0.1831438,0.001371742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1010798,0.0002241163,0.8895469,0.001123158,0.0002125573,0.00007243286,5.331495e-7,0.0001812899,0.00755916],"genre_scores_gemma":[0.9199397,0.00001002038,0.0779416,0.0002407556,0.00004644903,0.000003771242,0.000001738514,0.000002154088,0.001813808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8188599,"threshold_uncertainty_score":0.2564285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01317338455593186,"score_gpt":0.2391937291552616,"score_spread":0.2260203445993298,"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."}}