{"id":"W2546140527","doi":"10.1109/nnsp.1992.253676","title":"Unsupervised multi-level segmentation of multispectral images","year":2003,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multispectral image; Artificial intelligence; Segmentation; Computer science; Cluster analysis; Pattern recognition (psychology); Image segmentation; Scale-space segmentation; Computer vision; Multispectral pattern recognition; Segmentation-based object categorization; Image texture; Representation (politics); Scale (ratio); Geography; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004534919,0.0004835298,0.0006071528,0.001589643,0.0004983838,0.00110064,0.0008827657,0.0009021101,0.002104214],"category_scores_gemma":[0.001064135,0.000439766,0.0008604561,0.001202253,0.0006302945,0.00119551,0.0008024941,0.0006882262,0.001485424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006859956,"about_ca_system_score_gemma":0.0005727712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002332476,"about_ca_topic_score_gemma":0.005935153,"domain_scores_codex":[0.9994833,0.00007431977,0.00003323912,0.0001625367,0.0001994327,0.00004707848],"domain_scores_gemma":[0.9994206,0.0001447289,0.00007164496,0.0001704266,0.0001658281,0.00002675747],"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":[0.0001967165,0.0001026927,0.00169154,0.0002913309,0.0001261986,0.0002068061,0.0003790506,0.1165776,0.3045329,0.02207948,0.005374413,0.5484413],"study_design_scores_gemma":[0.00001672772,0.00006982553,0.002632272,0.0000330845,0.00005129635,0.0003508627,0.00005627868,0.8420448,0.1203827,0.01391365,0.02039895,0.0000496624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009237645,0.0001961031,0.9884204,0.00006239204,0.00002097765,0.00004197217,0.00009015896,0.0006874822,0.001242912],"genre_scores_gemma":[0.08947098,0.0002339286,0.9049175,0.00008204051,0.00003193855,0.00007462753,0.0004366802,0.0002726473,0.004479632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002332476,"threshold_uncertainty_score":0.007039309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05195409889212352,"score_gpt":0.3140164115557111,"score_spread":0.2620623126635876,"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."}}