{"id":"W4249076918","doi":"10.1109/icpr.2004.1334086","title":"Coarse-to-fine multiscale affine invariant shape matching and classification","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Affine transformation; Invariant (physics); Mathematics; Pattern recognition (psychology); Boundary (topology); Matching (statistics); Wavelet transform; Wavelet; Point set registration; Transformation (genetics); Algorithm; Artificial intelligence; Computer science; Point (geometry); Geometry; Mathematical analysis","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":[0.0003828726,0.0002536655,0.0002222629,0.0002683081,0.0001701696,0.0003142529,0.001222622,0.0001099226,0.0001429157],"category_scores_gemma":[0.0001673242,0.0002065246,0.00008461387,0.0004032739,0.0001138834,0.0006962137,0.0002555368,0.0002677501,0.0001222776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639733,"about_ca_system_score_gemma":0.00009128193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006978518,"about_ca_topic_score_gemma":0.00001584547,"domain_scores_codex":[0.9979973,0.0000170526,0.0005285493,0.000565963,0.0006347617,0.0002563619],"domain_scores_gemma":[0.998094,0.00004023944,0.0004287191,0.0002239674,0.001086411,0.0001266681],"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":[0.0001485036,0.0009044316,0.003463384,0.0001648801,0.0001381475,0.000004390576,0.002243958,0.00002143667,0.2002461,0.1789015,0.00211982,0.6116435],"study_design_scores_gemma":[0.003556279,0.0007173904,0.06519611,0.002568189,0.000076682,0.0002009783,0.0006501749,0.03099211,0.600102,0.2928521,0.001579047,0.001508944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3332276,0.00008337971,0.572911,0.06301276,0.001196155,0.001848037,0.0002416283,0.0006658865,0.02681357],"genre_scores_gemma":[0.9851227,0.00004916515,0.01299102,0.001081941,0.0001141126,0.00008486855,0.00002007149,0.0000204994,0.0005155956],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6518951,"threshold_uncertainty_score":0.8421831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05568928683443935,"score_gpt":0.2814795408300453,"score_spread":0.2257902539956059,"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."}}