{"id":"W2069444915","doi":"10.1016/j.patcog.2004.04.015","title":"Unsupervised image segmentation using a simple MRF model with a new implementation scheme","year":2004,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Segmentation; Image segmentation; Computer science; Pattern recognition (psychology); Markov random field; Scale-space segmentation; Weighting; Segmentation-based object categorization; Computer vision","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":[0.0001853046,0.0001868757,0.0001399113,0.0001755283,0.0001246046,0.0002323749,0.0002482503,0.0000524619,0.000182633],"category_scores_gemma":[0.0000138833,0.0001801023,0.00004524293,0.0003386086,0.00003316554,0.001816134,0.00007376161,0.0001174357,0.00007233351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002186323,"about_ca_system_score_gemma":0.0002097539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005586669,"about_ca_topic_score_gemma":0.00009619911,"domain_scores_codex":[0.9984312,0.00004673828,0.0003377055,0.000428437,0.0004698126,0.0002861224],"domain_scores_gemma":[0.9992091,0.00002044037,0.0001841666,0.0002591356,0.0001618996,0.0001652753],"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":[0.00001795926,0.0001230939,0.0009162371,0.00005658907,0.00003515767,0.00001813228,0.001973901,0.0003086813,0.2832346,0.00003094679,0.0002559922,0.7130287],"study_design_scores_gemma":[0.004300486,0.0002836307,0.0006577718,0.0001393008,0.00004619014,0.00005568022,0.0005650858,0.1498508,0.8257972,0.01776332,0.000003534962,0.0005369565],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.218057,0.000005058121,0.7807952,0.0002938966,0.00003245099,0.0004648058,0.00001526458,0.0002892823,0.00004700134],"genre_scores_gemma":[0.1940946,0.000009825487,0.803962,0.001479693,0.00006064559,0.00006681831,0.0002963549,0.00002283087,0.000007261689],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7124917,"threshold_uncertainty_score":0.734436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05403315852528015,"score_gpt":0.3282210463789449,"score_spread":0.2741878878536648,"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."}}