{"id":"W2089391573","doi":"10.1109/tgrs.2011.2164085","title":"Unsupervised Polarimetric SAR Image Segmentation and Classification Using Region Growing With Edge Penalty","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":205,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"European Space Agency","keywords":"Image segmentation; Polarimetry; Artificial intelligence; Synthetic aperture radar; Computer science; Pattern recognition (psychology); Wishart distribution; Segmentation; Radar imaging; Context (archaeology); Contextual image classification; Markov random field; Feature (linguistics); Feature extraction; Computer vision; Radar; Image (mathematics); Machine learning; Scattering; Geology; Physics","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":[0.0001231123,0.0001511275,0.0001199889,0.0002753555,0.0003706067,0.00005575834,0.00005144918,0.00007525089,0.000002634099],"category_scores_gemma":[0.000002450565,0.0001296306,0.0000253945,0.0005330043,0.0001624416,0.0003877399,0.000001204779,0.0001498428,0.000001504362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005902644,"about_ca_system_score_gemma":0.00001825896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004181213,"about_ca_topic_score_gemma":0.00001670471,"domain_scores_codex":[0.9992222,0.00002335646,0.0001590404,0.0002737147,0.0001369042,0.0001848445],"domain_scores_gemma":[0.9996164,0.00003806853,0.00003764436,0.000184348,0.00004779144,0.00007570598],"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":[0.000009424258,0.00001299021,0.000005518321,0.00002141431,0.000008861186,0.000003299824,0.0004466841,0.00000697735,0.05121466,0.00001744475,0.000001633815,0.9482511],"study_design_scores_gemma":[0.0003424111,0.0001101747,0.002347689,0.0001971822,0.000107674,0.0004558231,0.0009919712,0.7005156,0.2936368,0.0002555979,0.000621981,0.0004171091],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1515257,0.00005350346,0.8475624,0.00004176641,0.0000668688,0.0001833816,0.000001965282,0.0001712128,0.0003932395],"genre_scores_gemma":[0.5006449,0.0001313789,0.4991617,0.00002691839,0.000009845406,1.26199e-7,6.219099e-7,0.0000138919,0.00001064224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.947834,"threshold_uncertainty_score":0.5286183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03167668586375752,"score_gpt":0.2337385613192602,"score_spread":0.2020618754555026,"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."}}