{"id":"W3126410806","doi":"10.5121/csit.2021.110101","title":"Preprocessing Techniques to Improve CNN based Face Recognition System","year":2021,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Softmax function; Preprocessor; Computer science; Artificial intelligence; Pattern recognition (psychology); Facial recognition system; Face (sociological concept); Data pre-processing; Classifier (UML); Deep learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002448547,0.0008424653,0.0004174763,0.0006445767,0.0003129364,0.000516657,0.0009007076,0.0004800945,0.00841741],"category_scores_gemma":[0.000624284,0.0003103128,0.0005604818,0.0003958379,0.0001389791,0.0007124056,0.0004099002,0.0006923747,0.003715076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005192935,"about_ca_system_score_gemma":0.0005548254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00629614,"about_ca_topic_score_gemma":0.005359049,"domain_scores_codex":[0.9997398,0.00001454651,0.00001845879,0.00006180094,0.0001266516,0.00003862321],"domain_scores_gemma":[0.9998109,0.0000217441,0.00001451165,0.00002866069,0.0001171637,0.000007045527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003715125,0.0001535048,0.002744253,0.0004863636,0.0001018996,0.00044609,0.00008549303,0.03411319,0.2555637,0.004016838,0.01745911,0.684458],"study_design_scores_gemma":[0.00004161058,0.0005041094,0.009739748,0.0001078932,0.0001718378,0.001102434,0.0001008033,0.5706853,0.3508556,0.003440097,0.06315899,0.00009159574],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05833349,0.003000885,0.9056819,0.0006765364,0.0008303212,0.0004349926,0.001006452,0.01187728,0.01815812],"genre_scores_gemma":[0.5005209,0.003453672,0.4570594,0.0008493016,0.0002602341,0.0006096894,0.004488095,0.0004461506,0.03231254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00841741,"threshold_uncertainty_score":0.02815902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01923237070911679,"score_gpt":0.2526617383153776,"score_spread":0.2334293676062608,"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."}}