{"id":"W2142992265","doi":"10.1109/icip.2008.4712431","title":"Maximum likelihood neural network based on the correlation among neighboring pixels for noisy image segmentation","year":2008,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; UC Berkeley College of Chemistry","keywords":"Pixel; Artificial intelligence; Expectation–maximization algorithm; Pattern recognition (psychology); Computer science; Spatial correlation; Image segmentation; Image (mathematics); Gaussian; Mixture model; Artificial neural network; Correlation; Algorithm; Mathematics; Maximum likelihood; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003156779,0.0001237318,0.00009126893,0.00004988841,0.0004167898,0.0001299838,0.0003873566,0.00004925152,0.00002764169],"category_scores_gemma":[0.00004516247,0.0000852266,0.00008268224,0.0003677447,0.00005560276,0.0005485057,0.00004191909,0.0001084953,0.00002166333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004881252,"about_ca_system_score_gemma":0.00003712236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001104653,"about_ca_topic_score_gemma":0.000001577944,"domain_scores_codex":[0.9989533,0.00006400013,0.0002171281,0.0002699831,0.0002506904,0.0002449447],"domain_scores_gemma":[0.9990382,0.0002886193,0.0001246339,0.0003728492,0.0001276832,0.00004805733],"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":[0.0004114438,0.001103771,0.0560883,0.0001440495,0.0001036595,0.00004078281,0.00325242,0.01401458,0.06334123,0.1977216,0.09190904,0.5718691],"study_design_scores_gemma":[0.0002408062,0.0001255955,0.01593463,0.00001204839,0.000004778269,0.000002583436,0.00001483443,0.9451192,0.03430369,0.003724216,0.0003780709,0.0001395392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004483566,0.00000942051,0.9896042,0.001890542,0.0003354936,0.0005873342,0.000001349218,0.0003748988,0.002713225],"genre_scores_gemma":[0.8984122,0.000007755477,0.09940416,0.001298017,0.0001534081,0.0001480893,0.00001382621,0.00001341692,0.0005491527],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9311046,"threshold_uncertainty_score":0.347544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163407610603537,"score_gpt":0.2425152439883823,"score_spread":0.2208811678823469,"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."}}