{"id":"W2137993841","doi":"10.1109/tpami.2005.106","title":"Multiregion level-set partitioning of synthetic aperture radar images","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":198,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; National Aeronautics and Space Administration","keywords":"Synthetic aperture radar; Speckle noise; Artificial intelligence; Multiplicative noise; Speckle pattern; Segmentation; Computer vision; Image segmentation; Radar imaging; Computer science; Scale-space segmentation; Regularization (linguistics); Inverse synthetic aperture radar; Multiplicative function; Segmentation-based object categorization; Pattern recognition (psychology); Algorithm; Mathematics; Radar; Transmission (telecommunications)","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":[0.0002292212,0.0001560324,0.0002454061,0.0003723246,0.0001164913,0.00006418359,0.0003349224,0.00005308378,0.0002027471],"category_scores_gemma":[0.00001392783,0.0001342307,0.0001738933,0.0006058231,0.000108107,0.0002454781,0.000005559486,0.0001761351,0.00001743454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002371257,"about_ca_system_score_gemma":0.00001350958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000358793,"about_ca_topic_score_gemma":0.0002879432,"domain_scores_codex":[0.9986879,0.00009444854,0.0003857267,0.0003714059,0.0003027016,0.0001578304],"domain_scores_gemma":[0.9991107,0.0001822225,0.0001271179,0.0004017628,0.00007407104,0.0001041229],"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":[0.00000432323,0.0001216751,0.0001314567,0.00001517839,0.0001522075,0.000002869941,0.0003366937,0.002076269,0.003971551,0.00002334233,0.00004226434,0.9931222],"study_design_scores_gemma":[0.00007164044,0.00008157866,0.0003899596,0.00004200121,0.0001676369,0.000009537634,0.00004085258,0.1082671,0.8906118,0.00006856988,0.00008333776,0.0001659942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006112917,0.00009590878,0.9979035,0.001080967,0.00004435842,0.0000983854,0.00004078577,0.000088557,0.00003626891],"genre_scores_gemma":[0.9471628,0.0003924153,0.05155757,0.0006916019,0.0000123052,0.00001844675,0.000006199681,0.000007235457,0.0001513907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9929562,"threshold_uncertainty_score":0.547377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03177248076099596,"score_gpt":0.2973464705193594,"score_spread":0.2655739897583634,"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."}}