{"id":"W2117260013","doi":"10.1109/icip.2005.1530280","title":"A generalized Mumford-Shah model for roof-edge detection","year":2005,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Piecewise; Segmentation; Roof; Contrast (vision); Artificial intelligence; Edge detection; Enhanced Data Rates for GSM Evolution; Computer science; Minification; Image segmentation; Constant (computer programming); Energy (signal processing); Image (mathematics); Mathematics; Computer vision; Algorithm; Pattern recognition (psychology); Mathematical optimization; Image processing; Statistics; Mathematical analysis; Engineering; Structural engineering","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":[0.0002194811,0.00008549792,0.00009205176,0.00007751267,0.0000763949,0.00007547496,0.0003806296,0.00005083463,0.0000519629],"category_scores_gemma":[0.0000475408,0.00007376837,0.00006066931,0.0001311361,0.00002527183,0.0005760571,0.00007989998,0.00005217887,0.00003022388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005551202,"about_ca_system_score_gemma":0.0000325291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001029589,"about_ca_topic_score_gemma":0.00005774804,"domain_scores_codex":[0.9991652,0.00001957047,0.0001978549,0.000249336,0.0001793946,0.0001886439],"domain_scores_gemma":[0.9994659,0.00003415212,0.00004770347,0.0002849576,0.00007285803,0.00009441901],"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":[0.000005418518,0.00004174729,0.000001276701,0.000007117743,0.000005433522,3.106016e-7,0.0002500473,0.0004038746,0.03054608,0.00786383,0.01001434,0.9508605],"study_design_scores_gemma":[0.0002854928,0.00002745875,0.000002677701,0.000001898447,0.00000199293,0.000002124982,0.000003002355,0.7220009,0.2735726,0.002740228,0.001288439,0.00007319188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009710064,0.00001830678,0.9958227,0.0009560365,0.00007643252,0.0003329616,0.000001108847,0.0006989782,0.001122462],"genre_scores_gemma":[0.07310229,0.00000679595,0.9194196,0.002884516,0.00008671889,0.0001673035,0.000002421204,0.000007882638,0.004322477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9507873,"threshold_uncertainty_score":0.3008187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03619535005391968,"score_gpt":0.3126513470504602,"score_spread":0.2764559969965405,"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."}}