{"id":"W2094850031","doi":"10.1109/icassp.2010.5495334","title":"Improving image segmentation via shape PCA reconstruction","year":2010,"lang":"en","type":"article","venue":"","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer vision; Image segmentation; Segmentation; Active shape model; Computer science; Point distribution model; Scale-space segmentation; Shape analysis (program analysis); Principal component analysis; Interpolation (computer graphics); Pattern recognition (psychology); Segmentation-based object categorization; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001699983,0.00007281075,0.00005571817,0.000108403,0.0001205226,0.0001933246,0.0002243961,0.00005283805,0.0002386783],"category_scores_gemma":[0.00002017136,0.00006686695,0.00003554968,0.0001827664,0.00002779304,0.001348733,0.00006836871,0.00015857,0.00008982403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001970704,"about_ca_system_score_gemma":0.00002079356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001174376,"about_ca_topic_score_gemma":0.00003910963,"domain_scores_codex":[0.9993995,0.00001614677,0.0001340779,0.0002167612,0.0001046095,0.0001289128],"domain_scores_gemma":[0.9995425,0.00001513645,0.00006235943,0.0002611462,0.00008107055,0.00003772602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[4.027103e-7,0.000003594677,0.00001406197,0.000001581192,7.665939e-7,7.752897e-7,0.00002260842,1.914048e-8,0.4655859,0.0002035856,0.00007166115,0.534095],"study_design_scores_gemma":[0.00007810252,0.00003610264,0.0002446201,0.000001362178,0.000001537123,0.0001093224,0.00001680073,0.03725028,0.9598829,0.002113462,0.0001801425,0.00008532837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02546793,0.000002167797,0.9654888,0.0001409613,0.0007173032,0.0001073255,1.988567e-7,0.0007830008,0.007292323],"genre_scores_gemma":[0.4009319,0.000001879278,0.5984341,0.0002286092,0.00009308842,0.0000160454,7.078565e-7,0.000005367925,0.0002883002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5340097,"threshold_uncertainty_score":0.2726755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004780787700614664,"score_gpt":0.2244197417275821,"score_spread":0.2196389540269674,"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."}}