{"id":"W2109001758","doi":"10.1016/j.patcog.2005.02.008","title":"Rotation invariant pattern recognition using ridgelets, wavelet cycle-spinning and Fourier features","year":2005,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency; Fonds Québécois de la Recherche sur la Nature et les Technologies; Concordia University; Foundation for Community Association Research","keywords":"Wavelet; Artificial intelligence; Invariant (physics); Pattern recognition (psychology); Fourier transform; Gravitational singularity; Gabor wavelet; Rotation (mathematics); Wavelet transform; Mathematics; Computer science; Computer vision; Discrete wavelet transform; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004214917,0.0003340062,0.0006300303,0.001081186,0.0001773152,0.0007445989,0.000396564,0.0004044865,0.001403533],"category_scores_gemma":[0.001495161,0.0002288499,0.0005191262,0.001706634,0.0003342117,0.0009669352,0.0003130686,0.0005955254,0.0008609076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109631,"about_ca_system_score_gemma":0.0003147733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006700127,"about_ca_topic_score_gemma":0.0007585273,"domain_scores_codex":[0.9997615,0.00003277571,0.00001735187,0.0000441323,0.0001199732,0.00002413353],"domain_scores_gemma":[0.9994172,0.0001593072,0.0001111071,0.000116605,0.000164023,0.00003174913],"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":[0.000314331,0.0001388228,0.001786368,0.0001652744,0.00005856237,0.0001570056,0.0000733209,0.01537593,0.144006,0.00804909,0.003127628,0.8267477],"study_design_scores_gemma":[0.00005243997,0.0002992407,0.01121405,0.00004583948,0.0001187015,0.0008685338,0.00008962455,0.8809297,0.08467466,0.01465007,0.006974072,0.00008304884],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05633705,0.0007591348,0.9388545,0.0001675824,0.0001321067,0.00006105584,0.0002145889,0.001128069,0.002345913],"genre_scores_gemma":[0.3873588,0.00152827,0.6044697,0.0001149272,0.0001748706,0.0001028932,0.0008065258,0.0002677143,0.00517625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001403533,"threshold_uncertainty_score":0.004695296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04142191104688983,"score_gpt":0.2670375263606032,"score_spread":0.2256156153137134,"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."}}