{"id":"W2094621096","doi":"10.1109/cisp.2011.6100497","title":"An SVM-based method for land and sea segmentation in polarimetric SAR images","year":2011,"lang":"en","type":"article","venue":"","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Space Agency","keywords":"Support vector machine; Segmentation; Artificial intelligence; Pattern recognition (psychology); Polarimetry; Computer science; Image segmentation; Synthetic aperture radar; Classifier (UML); Remote sensing; Feature selection; Feature extraction; Computer vision; Geography; Scattering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001575808,0.00007429563,0.00008492752,0.0001504016,0.00002140149,0.00001304108,0.00005083172,0.00005053179,0.00004304835],"category_scores_gemma":[0.000008986181,0.00006484846,0.00001527849,0.0001512076,0.000009611394,0.00006957278,0.000004101475,0.00003761494,0.000001187707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001918159,"about_ca_system_score_gemma":0.000005263225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004979435,"about_ca_topic_score_gemma":0.00003698096,"domain_scores_codex":[0.9996439,0.00001330044,0.00009982229,0.0001112662,0.00003847558,0.00009327266],"domain_scores_gemma":[0.999736,0.00008244928,0.00001163938,0.0001220948,0.00001551216,0.00003234474],"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":[0.00001338261,0.00008892654,0.02833949,0.00006288207,0.00001690071,6.793587e-7,0.0001687241,0.000008910777,0.01059818,0.001432779,0.000396793,0.9588724],"study_design_scores_gemma":[0.0006635279,0.0001283486,0.05831119,0.00001291736,0.00003273715,0.000004658402,0.0001025125,0.1112136,0.8104286,0.002870163,0.01592735,0.0003044732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009362519,0.0001294348,0.987366,0.00003200686,0.00001193983,0.0002944583,0.00001592005,0.00021783,0.002569894],"genre_scores_gemma":[0.2767511,0.00001102671,0.7231318,0.00003881906,0.000008747797,0.00002349708,0.00001276227,0.00001293213,0.000009212427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9585679,"threshold_uncertainty_score":0.2644443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665528783287528,"score_gpt":0.2773892819373953,"score_spread":0.26073399410452,"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."}}