{"id":"W2112531565","doi":"10.1007/bf03192570","title":"Fast two-step segmentation of natural color scenes using hierarchical region-growing and a Color-Gradient Network","year":2008,"lang":"en","type":"article","venue":"Journal of the Brazilian Computer Society","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Westfälische Wilhelms-Universität Münster; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Artificial intelligence; Segmentation; Computer science; Computer vision; Ground truth; Image segmentation; Matching (statistics); Focus (optics); Bipartite graph; Pattern recognition (psychology); Graph; Mathematics; Theoretical computer science","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":[0.001092645,0.001041229,0.0007918823,0.002049081,0.0004225578,0.0008494038,0.001259845,0.001000314,0.002212629],"category_scores_gemma":[0.001945633,0.0003756058,0.0006249772,0.001333982,0.0003613333,0.001236642,0.0006470689,0.0004657886,0.0007451788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008143454,"about_ca_system_score_gemma":0.0007622583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009207604,"about_ca_topic_score_gemma":0.01300877,"domain_scores_codex":[0.9994534,0.0001117338,0.00003053415,0.0001632805,0.0001772913,0.00006377247],"domain_scores_gemma":[0.9990461,0.0004851082,0.00007172769,0.0001288433,0.000206254,0.00006195981],"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":[0.001290847,0.000321479,0.003218056,0.0004668175,0.000241769,0.0002186604,0.0002479203,0.1654806,0.19073,0.002628116,0.002442335,0.6327134],"study_design_scores_gemma":[0.00002645886,0.0001102436,0.001725566,0.000009381084,0.00004222654,0.0001712399,0.00004892748,0.9406875,0.05534815,0.0009492889,0.0008564153,0.00002465358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1271616,0.0005594604,0.8633375,0.0001140878,0.00005134409,0.0002793353,0.0003416254,0.005600394,0.002554765],"genre_scores_gemma":[0.2126534,0.0001954671,0.7848235,0.00004519187,0.00001451235,0.00009356556,0.0005278203,0.0003384575,0.001308109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009207604,"threshold_uncertainty_score":0.01830804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01841774192027234,"score_gpt":0.2702198995421865,"score_spread":0.2518021576219142,"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."}}