{"id":"W1603691188","doi":"10.1109/icpr.2002.1048018","title":"Region segmentation and matching in stereo images","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Homography; Computer vision; Segmentation; Computer science; Matching (statistics); Similarity (geometry); Discontinuity (linguistics); Region growing; Plane (geometry); Pattern recognition (psychology); Process (computing); Image segmentation; Mathematics; Image (mathematics); Scale-space segmentation; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006812999,0.00003295979,0.00003335232,0.00004623775,0.00002624862,0.00006021459,0.0000544954,0.000006209218,0.000004056743],"category_scores_gemma":[0.000007905011,0.00002823977,0.000004772605,0.00008803838,0.000006405928,0.0006168525,0.00002787113,0.00003019276,0.000004497585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009210577,"about_ca_system_score_gemma":0.000004172337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009276195,"about_ca_topic_score_gemma":0.000002793859,"domain_scores_codex":[0.9996841,0.00002361078,0.00006203103,0.0001161672,0.00004507263,0.00006901568],"domain_scores_gemma":[0.9998596,0.00001783085,0.00001526459,0.00008210137,0.0000065643,0.00001863847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002071584,0.00003300811,0.01198927,0.00001306565,0.000001630549,0.00002959615,0.002018945,0.00008114572,0.0150761,0.148763,0.0004308363,0.8215613],"study_design_scores_gemma":[0.005206892,0.0001922349,0.0980607,0.0002796908,0.000005077,0.0005040218,0.006107236,0.1623515,0.2130427,0.5036356,0.009240297,0.001374128],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01516568,0.00005291244,0.9765708,0.000352193,0.00004168721,0.00003585832,1.614853e-8,0.00003315679,0.007747654],"genre_scores_gemma":[0.6575691,0.00002349427,0.3415214,0.0004643333,0.000002206965,0.000001218414,8.885247e-8,0.000001658454,0.0004164825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8201872,"threshold_uncertainty_score":0.1151584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01494874065528974,"score_gpt":0.2797658742865756,"score_spread":0.2648171336312858,"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."}}