{"id":"W2104673234","doi":"10.1109/tgrs.2003.817218","title":"Comparing Cooccurrence Probabilities and Markov Random Fields for Texture Analysis of SAR Sea Ice Imagery","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":167,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Synthetic aperture radar; Segmentation; Computer science; Pattern recognition (psychology); Markov random field; Image segmentation; Image texture; Texture (cosmology); Feature (linguistics); Computer vision; Consistency (knowledge bases); Image (mathematics)","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":[0.0002400049,0.0001518655,0.0003029077,0.0003076947,0.0002244536,0.00007165048,0.00005712605,0.00008345526,7.966319e-7],"category_scores_gemma":[0.00002514801,0.0001435217,0.00009164104,0.0006149959,0.0002895427,0.0001994337,0.000001418258,0.0001642743,3.797163e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004717442,"about_ca_system_score_gemma":0.00002895004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000198689,"about_ca_topic_score_gemma":0.0002146057,"domain_scores_codex":[0.9990725,0.00002261453,0.0002558731,0.0002842158,0.000149351,0.0002154645],"domain_scores_gemma":[0.9993637,0.0002101497,0.00005337691,0.0002100416,0.00009613291,0.00006660364],"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":[0.0000863855,0.00002721726,0.00001644811,0.000287872,0.0001664188,0.000003289088,0.001732465,0.2478557,0.03073751,0.000006643426,0.00001210287,0.719068],"study_design_scores_gemma":[0.000496691,0.00003175992,0.0009768424,0.0001347142,0.0002480117,0.00001975427,0.0002247557,0.9796981,0.01782857,0.0001431228,0.00003393112,0.0001637328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2912168,0.00006965614,0.7081097,0.0001063152,0.000181877,0.0001693702,0.00001173838,0.00006288094,0.00007163139],"genre_scores_gemma":[0.9383346,0.0001308482,0.06144163,0.00003100234,0.00001427771,1.309185e-7,0.00000249405,0.00001066945,0.00003436278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7318424,"threshold_uncertainty_score":0.5852643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01897825191831121,"score_gpt":0.2401398014572638,"score_spread":0.2211615495389526,"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."}}