{"id":"W2121013500","doi":"10.1109/34.954605","title":"A dyadic wavelet affine invariant function for 2D shape recognition","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics; Invariant (physics); Wavelet transform; Wavelet; Affine transformation; Pattern recognition (psychology); Artificial intelligence; Discrete wavelet transform; Pure mathematics; Computer science","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":[0.0007312974,0.0006747359,0.000710775,0.001715689,0.0003359658,0.0009062453,0.0006452872,0.0007245053,0.00314261],"category_scores_gemma":[0.001663978,0.0002313524,0.0006942592,0.002316903,0.0005353308,0.001270316,0.0004498315,0.0007862636,0.002295055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005769234,"about_ca_system_score_gemma":0.0005475531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001198125,"about_ca_topic_score_gemma":0.0008320993,"domain_scores_codex":[0.9995772,0.00008556508,0.00002487034,0.0000651536,0.000210923,0.00003628998],"domain_scores_gemma":[0.9995545,0.0001209834,0.00004382595,0.00009372425,0.0001639332,0.00002302277],"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":[0.0001415895,0.00007765843,0.0007183464,0.0001757377,0.00004896581,0.0001807797,0.0000779658,0.03657012,0.1052311,0.03535755,0.00460097,0.8168192],"study_design_scores_gemma":[0.0000171131,0.0001746727,0.002432563,0.00002554208,0.0000448938,0.0006074471,0.00004262655,0.9154164,0.05208689,0.009754672,0.01933198,0.00006513076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00456106,0.0002686301,0.9936218,0.0000397762,0.00004247444,0.0000271887,0.00006872672,0.0003752407,0.0009951522],"genre_scores_gemma":[0.1159721,0.0009602431,0.8785168,0.00007678132,0.0001141853,0.0001593603,0.0006326031,0.0001986167,0.003369374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00314261,"threshold_uncertainty_score":0.01051313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03869579972245687,"score_gpt":0.2719271901221397,"score_spread":0.2332313903996828,"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."}}