{"id":"W2127156748","doi":"10.1109/cisp.2008.376","title":"Competitive Learning Techniques for Color Image Segmentation","year":2008,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Image segmentation; Segmentation; Segmentation-based object categorization; Cluster analysis; Context (archaeology); Scale-space segmentation; Color space; Color image; Computer vision; Pattern recognition (psychology); Color quantization; Image (mathematics); Image processing; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001425491,0.00007558028,0.00008621564,0.00006336965,0.0002221998,0.00005488013,0.0002556363,0.00003581099,0.00002115795],"category_scores_gemma":[0.00004339522,0.00006606507,0.00004777989,0.0001803737,0.00006168444,0.0004645497,0.00005515316,0.00006437064,0.00002630522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004005985,"about_ca_system_score_gemma":0.00003661657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007070335,"about_ca_topic_score_gemma":5.419853e-7,"domain_scores_codex":[0.9993752,0.0000309759,0.0001379824,0.0002021628,0.0001234217,0.0001302377],"domain_scores_gemma":[0.999475,0.00008403203,0.0000683788,0.0001358131,0.0002041101,0.00003267937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001747311,0.00009311554,0.0001449635,0.00002105156,0.0000112538,0.000006016238,0.0008193026,2.604765e-7,0.4765708,0.4678194,0.002657028,0.05183933],"study_design_scores_gemma":[0.0001114974,0.0001642183,0.0002938941,0.000005000982,0.000001586441,0.00001518337,0.00006859121,0.003645293,0.9737565,0.001066541,0.02076684,0.0001048551],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003949455,0.00001072043,0.9810098,0.0006530501,0.0000286149,0.0003677367,0.000001193887,0.001063767,0.01647014],"genre_scores_gemma":[0.1392631,0.00005263013,0.8560102,0.0002942632,0.00003165449,0.0001668209,0.000008638307,0.000007028722,0.004165699],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4971856,"threshold_uncertainty_score":0.2694055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02187502440799826,"score_gpt":0.2797775912584037,"score_spread":0.2579025668504055,"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."}}