{"id":"W2975485695","doi":"10.1109/tcds.2019.2920364","title":"Deep Residual Network With Adaptive Learning Framework for Fingerprint Liveness Detection","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive and Developmental Systems","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Liveness; Artificial intelligence; Spoofing attack; Convolutional neural network; Fingerprint (computing); Pattern recognition (psychology); Feature extraction; Deep learning; Residual; Fingerprint recognition; Artificial neural network; Multilayer perceptron; Feature (linguistics); Machine learning; Algorithm; Computer security","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":[0.0002857691,0.0001537569,0.000177228,0.0001858437,0.0004351677,0.0001957811,0.0001197729,0.0001077882,0.00001108765],"category_scores_gemma":[0.00001051579,0.0001392777,0.000037101,0.0006348916,0.0000381648,0.0002533669,0.000004055995,0.0002284933,0.00006858233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008791596,"about_ca_system_score_gemma":0.00006459632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004780823,"about_ca_topic_score_gemma":0.00004221129,"domain_scores_codex":[0.9988019,0.0001013536,0.0002031292,0.0004329262,0.0002292736,0.0002313713],"domain_scores_gemma":[0.9990087,0.0005461809,0.00009693628,0.0000880634,0.0001801309,0.00007999332],"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":[0.002327159,0.0007374001,0.003094873,0.0006069772,0.001152822,0.00003239526,0.01503642,0.02330656,0.00117241,0.01398149,0.00004287186,0.9385086],"study_design_scores_gemma":[0.0135635,0.008433159,0.0481196,0.006086595,0.000377537,0.001118887,0.04638242,0.7350347,0.1234413,0.004084233,0.007659392,0.005698619],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04633681,0.00010031,0.9517201,0.00001668124,0.0007789466,0.0007094631,0.000005721542,0.0000986071,0.0002333645],"genre_scores_gemma":[0.9842678,0.00002330185,0.01508903,0.00005758471,0.00004302766,0.0002017739,0.000003208964,0.00001211618,0.0003021192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.937931,"threshold_uncertainty_score":0.5679582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163336013942574,"score_gpt":0.2358166226595319,"score_spread":0.2141832625201062,"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."}}