{"id":"W2950030871","doi":"10.48550/arxiv.1703.08628","title":"AMAT: Medial Axis Transform for Natural Images","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medial axis; Generalization; Artificial intelligence; Computer science; Point (geometry); Pixel; Image (mathematics); Scale (ratio); Pattern recognition (psychology); Code (set theory); Computer vision; Cluster analysis; Set (abstract data type); Mathematics; Cartography; Geography; Geometry","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":[0.000817447,0.00165446,0.001100118,0.003619281,0.000389208,0.002574945,0.001795729,0.001375837,0.008787379],"category_scores_gemma":[0.004934264,0.0006064386,0.001552595,0.002099673,0.0009709895,0.003022569,0.002285794,0.00210646,0.006954174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005134426,"about_ca_system_score_gemma":0.0007718215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001612574,"about_ca_topic_score_gemma":0.001785857,"domain_scores_codex":[0.9988648,0.0001317282,0.0000753662,0.0002680043,0.0005765159,0.00008361656],"domain_scores_gemma":[0.999033,0.0002120349,0.0001694418,0.0002566339,0.0002299528,0.00009896373],"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":[0.0006004857,0.0001531465,0.001939331,0.0008041178,0.0001408158,0.0003801514,0.000230506,0.03112649,0.07675101,0.04412627,0.04095886,0.8027889],"study_design_scores_gemma":[0.00009933318,0.0003180838,0.003037751,0.0001997063,0.00004559717,0.00247663,0.0002014546,0.7501475,0.06569179,0.09040303,0.08725074,0.0001284067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006343978,0.0005606101,0.9813401,0.0002177814,0.0001315563,0.000140129,0.001939576,0.007469786,0.001856485],"genre_scores_gemma":[0.05636504,0.0007093808,0.9300237,0.0001703789,0.0001956687,0.0002875856,0.008091886,0.001649033,0.002507419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008787379,"threshold_uncertainty_score":0.02939665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06367350670218534,"score_gpt":0.2363150764851382,"score_spread":0.1726415697829529,"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."}}