{"id":"W1595472190","doi":"10.1109/icip.2002.1039085","title":"Adaptive color image segmentation using Markov random fields","year":2003,"lang":"en","type":"article","venue":"Proceedings - International Conference on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Image segmentation; Random field; Gibbs sampling; Markov random field; Markov chain; Computer science; Artificial intelligence; Markov process; Variable-order Markov model; Segmentation; Markov model; Hidden Markov model; Algorithm; Pattern recognition (psychology); Computer vision; Mathematics; Machine learning; Bayesian probability; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003204021,0.0003329525,0.0002520506,0.0002851154,0.0001943935,0.0007899938,0.0002710402,0.0001343052,0.0002125702],"category_scores_gemma":[0.0003433683,0.0003535677,0.00007417946,0.0002841462,0.000127089,0.001546737,0.00002978408,0.000374563,0.00006014451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003769348,"about_ca_system_score_gemma":0.0001033206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000616093,"about_ca_topic_score_gemma":0.000001507338,"domain_scores_codex":[0.9982215,0.00002058082,0.0004551395,0.0004449917,0.0005042304,0.0003535972],"domain_scores_gemma":[0.9985124,0.00004516571,0.0002155124,0.0001012696,0.00102233,0.0001033398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002407216,0.00009157734,0.0002312135,0.0002147384,0.00009654804,0.00001365907,0.001365578,0.000558929,0.9655142,0.00407687,0.0008524157,0.02674357],"study_design_scores_gemma":[0.001257818,0.00004362548,0.0001352392,0.0003191536,0.00004008525,0.00005563561,0.001339591,0.8213881,0.172832,0.001942067,0.0002061323,0.0004406349],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.237828,0.0001088439,0.5013659,0.0004987072,0.0009831324,0.0007240252,0.00001817584,0.0007669615,0.2577063],"genre_scores_gemma":[0.8853355,0.00004187952,0.1140053,0.00009798184,0.0001286646,0.00002868605,0.0000164361,0.00006247407,0.0002830107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8208292,"threshold_uncertainty_score":0.9998916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04212077650255112,"score_gpt":0.2917701363816775,"score_spread":0.2496493598791263,"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."}}