{"id":"W2954836870","doi":"10.1016/j.ifacol.2019.06.061","title":"A GMM-MRF Based Image Segmentation approach for Interface Level Estimation","year":2019,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov random field; Interface (matter); Computer science; Process (computing); Segmentation; Maximum a posteriori estimation; Image segmentation; Artificial intelligence; Image (mathematics); Scale (ratio); Layer (electronics); Mixture model; Computer vision; Pattern recognition (psychology); Maximum likelihood; Mathematics; Materials science; Statistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001167896,0.0002199943,0.0002722506,0.0001123051,0.00007684496,0.00006121195,0.0001987706,0.000131258,0.001875249],"category_scores_gemma":[0.0001194989,0.0002072154,0.0001448924,0.0002922205,0.00003693357,0.0001954458,0.00002644241,0.0001491594,0.00008970364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001555581,"about_ca_system_score_gemma":0.00005477886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003496009,"about_ca_topic_score_gemma":0.000003378653,"domain_scores_codex":[0.9988184,0.00001017139,0.000265161,0.0004026507,0.0002266563,0.000276937],"domain_scores_gemma":[0.9992492,0.0001311641,0.0001580938,0.0002998629,0.00009043356,0.00007121328],"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":[0.0001335376,0.000266387,0.0008440356,0.0004220672,0.0001001162,6.61785e-7,0.0001730297,0.001780587,0.9936673,0.00003066859,0.00005789347,0.002523726],"study_design_scores_gemma":[0.001501481,0.00006009883,0.0001124506,0.00001912926,0.000149782,0.000003016394,0.0009096122,0.2847005,0.7121782,0.00002704246,0.00009507589,0.0002436473],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3393658,0.0002136563,0.6512179,0.0005180156,0.00007517292,0.0003567398,0.0003067263,0.0001843055,0.007761662],"genre_scores_gemma":[0.2959425,0.000004513861,0.6971408,0.000160694,0.00009555241,0.00005594062,0.0008940505,0.00003194088,0.005673997],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2829199,"threshold_uncertainty_score":0.9990371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02757690165428411,"score_gpt":0.3138629903581034,"score_spread":0.2862860887038193,"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."}}