{"id":"W2085121419","doi":"10.5402/2011/672353","title":"Edge-Detection in Noisy Images Using Independent Component Analysis","year":2011,"lang":"en","type":"article","venue":"ISRN Signal Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Independent component analysis; Edge detection; Computer science; Computer vision; Pattern recognition (psychology); Phase congruency; Enhanced Data Rates for GSM Evolution; Noise (video); Image (mathematics); Digital image; Gaussian; Image gradient; Image processing","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":[0.0007160284,0.0001503859,0.0002183967,0.0007292557,0.0001441498,0.0002481424,0.000460023,0.00008888968,0.00002215565],"category_scores_gemma":[0.000008689491,0.0001504233,0.0000857758,0.001562259,0.00004276242,0.001130795,0.0001532997,0.0002442476,0.000008718785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001116027,"about_ca_system_score_gemma":0.00008555227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003528771,"about_ca_topic_score_gemma":0.0001722177,"domain_scores_codex":[0.9985042,0.0001457399,0.0003495523,0.0004102474,0.0003345203,0.0002557403],"domain_scores_gemma":[0.9993528,0.00002254325,0.0001978869,0.0002388379,0.0001251934,0.00006274433],"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":[0.00008696121,0.0008762479,0.02850561,0.0001295386,0.0002445908,0.0001271141,0.02674725,0.006461397,0.3251172,0.002331327,0.00001930449,0.6093534],"study_design_scores_gemma":[0.0002667177,0.00006474726,0.02979753,0.00005828598,0.0000681952,0.00002003253,0.0001693561,0.6097099,0.3539433,0.005493858,0.0000307791,0.0003773051],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1496014,0.00008083356,0.8487593,0.00003018164,0.0000296702,0.000102336,4.164541e-7,0.0002447666,0.00115109],"genre_scores_gemma":[0.934899,0.000002251149,0.06490525,0.0001270583,0.00002432583,0.000009756839,0.00000105341,0.00001025307,0.00002109188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7852976,"threshold_uncertainty_score":0.6134084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04254674233718084,"score_gpt":0.2830846228225765,"score_spread":0.2405378804853957,"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."}}