{"id":"W1972281563","doi":"10.1080/07055900.2001.9649675","title":"Comparison and fusion of co‐occurrence, Gabor and MRF texture features for classification of SAR sea‐ice imagery","year":2001,"lang":"en","type":"article","venue":"ATMOSPHERE-OCEAN","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":194,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Synthetic aperture radar; Gabor filter; Computer science; Histogram; Texture (cosmology); Markov random field; Feature (linguistics); Feature extraction; Computer vision; Geology; Image (mathematics); Image segmentation","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0003048681,0.0001303034,0.0002588648,0.00001469008,0.000115829,0.00004799323,0.0001534428,0.0001046187,0.0001886768],"category_scores_gemma":[0.0000599227,0.000104571,0.00003275852,0.000204638,0.0002456012,0.0001577395,0.00001857893,0.0001439413,0.000003801162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003983044,"about_ca_system_score_gemma":0.00005195112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004919798,"about_ca_topic_score_gemma":0.0003687969,"domain_scores_codex":[0.9988653,0.00006119032,0.0002659497,0.0002671943,0.0002935686,0.0002467952],"domain_scores_gemma":[0.9990664,0.0003432353,0.0001444381,0.0001786412,0.0001491345,0.0001181742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000191374,0.00004383496,0.954321,0.0001698953,0.00001929066,0.000002026973,0.0003341714,0.0008068485,0.001318073,0.00001214329,0.01186529,0.03091606],"study_design_scores_gemma":[0.0005536134,0.0003260194,0.8281634,0.00004383393,0.00003323171,0.00001502415,0.0006955387,0.1625578,0.001215751,0.0003260825,0.005912907,0.0001568002],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918867,0.001322976,0.00405556,0.0001930578,0.00006296559,0.0003734547,0.0004775849,0.0000187435,0.001608897],"genre_scores_gemma":[0.9947459,0.000379926,0.004203233,0.00003794116,0.00004211883,3.603022e-7,0.0003352913,0.000004585349,0.0002507132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1617509,"threshold_uncertainty_score":0.426428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02987056991501882,"score_gpt":0.2984456711404299,"score_spread":0.2685751012254111,"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."}}