{"id":"W2269700260","doi":"10.5623/cig2011-005","title":"Detecting Water Bodies on Radarsat Imagery","year":2011,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National University of Defense Technology","keywords":"Initialization; Synthetic aperture radar; Speckle noise; Level set (data structures); Computer science; Enhanced Data Rates for GSM Evolution; Speckle pattern; Artificial intelligence; Active contour model; Edge detection; Computer vision; Operator (biology); Detector; Function (biology); Algorithm; Remote sensing; Image segmentation; Segmentation; Image (mathematics); Image processing; Geology","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":[0.0003199069,0.00009759892,0.0001094704,0.00008477773,0.00009554856,0.00007053815,0.0004593985,0.0000331263,0.0003860356],"category_scores_gemma":[0.0001108514,0.00006606988,0.00003965162,0.00005569501,0.00005738492,0.0003285967,0.0001915207,0.00009846636,0.0007125734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001901057,"about_ca_system_score_gemma":0.00001017657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002140446,"about_ca_topic_score_gemma":8.054936e-7,"domain_scores_codex":[0.9990164,0.00005634184,0.0002072511,0.000210988,0.0002498256,0.0002591672],"domain_scores_gemma":[0.9993438,0.00007223705,0.0000407086,0.0004281469,0.00003456238,0.00008054518],"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":[0.000014519,0.0002350492,0.0002444593,0.0001165166,0.00005047063,0.0001977304,0.02340452,6.349968e-7,0.05538471,0.005159359,0.01070493,0.9044871],"study_design_scores_gemma":[0.0001006164,0.00008588131,0.0003886251,0.00003294791,0.000003584077,0.00001279022,0.00005579936,0.0009531439,0.9854085,0.01256799,0.0002642794,0.0001257914],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01191773,0.000009401989,0.9683392,0.0003159949,0.000169587,0.0001296382,3.299747e-7,0.0006019653,0.01851614],"genre_scores_gemma":[0.2839682,0.000003618863,0.7141197,0.001460888,0.0000370536,0.00001306373,9.849683e-7,0.000009692884,0.0003868238],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9300238,"threshold_uncertainty_score":0.9158927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0338612654269689,"score_gpt":0.2516309010696888,"score_spread":0.2177696356427199,"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."}}