{"id":"W1728159704","doi":"10.1109/crv.2005.27","title":"Combining Local and Global Features for Image Segmentation Using Iterative Classification and Region Merging","year":2005,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Image segmentation; Artificial intelligence; Segmentation; Pattern recognition (psychology); Computer science; Image (mathematics); Feature (linguistics); Iterative method; Scale-space segmentation; Energy (signal processing); Function (biology); Segmentation-based object categorization; Contextual image classification; Enhanced Data Rates for GSM Evolution; Computer vision; Mathematics; Algorithm; Statistics","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":[0.0001669012,0.00008799483,0.00008590075,0.00004691315,0.0001440705,0.0002329008,0.00009392,0.00003960502,0.000002391303],"category_scores_gemma":[0.00003146784,0.00008005077,0.00001427126,0.000117741,0.00009616468,0.001101156,0.00006444554,0.00004615557,4.995492e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000883936,"about_ca_system_score_gemma":0.00001920144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001808954,"about_ca_topic_score_gemma":0.000007183175,"domain_scores_codex":[0.9992695,0.00004683439,0.0001609111,0.000266426,0.0001340022,0.0001223218],"domain_scores_gemma":[0.999602,0.00006711387,0.00008294501,0.000103619,0.00007495402,0.00006941277],"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":[0.00001511049,0.00003475433,0.000558525,0.00003480683,0.00001412178,0.000002787983,0.001729154,0.00001718058,0.05577262,0.03630045,0.001669411,0.9038511],"study_design_scores_gemma":[0.001005742,0.0001205772,0.00412605,0.00006046489,0.00001720517,0.0001076996,0.001093151,0.8714735,0.1178151,0.003837149,0.0001017114,0.0002416283],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01003927,0.0000826353,0.9877409,0.001377263,0.00003540701,0.000284104,0.000001133038,0.0001414281,0.0002978894],"genre_scores_gemma":[0.363713,0.00001432144,0.635622,0.0005741385,0.00002003261,0.00001547296,0.000005007364,0.000002965648,0.0000330928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9036095,"threshold_uncertainty_score":0.3264376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0327353438303245,"score_gpt":0.3389234841563195,"score_spread":0.306188140325995,"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."}}