{"id":"W2031610076","doi":"10.1080/09500340308235177","title":"Shift-, scale-, rotation- and pose-invariant object recognition using centroid wedge sampling and a feature space trajectory classifier","year":2003,"lang":"en","type":"article","venue":"Journal of Modern Optics","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Centroid; Artificial intelligence; Pattern recognition (psychology); Computer vision; Classifier (UML); Invariant (physics); Cognitive neuroscience of visual object recognition; Computer science; Scale invariance; Scale space; 3D single-object recognition; Feature extraction; Mathematics; Image processing; Image (mathematics); Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004869045,0.0001352688,0.0001979944,0.000203964,0.000163187,0.0002660682,0.0001180631,0.0001112552,0.000002767462],"category_scores_gemma":[0.00009978755,0.0001221574,0.00006186943,0.0001573176,0.00003798183,0.0006865311,0.00003209248,0.0003479946,5.946583e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000862862,"about_ca_system_score_gemma":0.0001212812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004699416,"about_ca_topic_score_gemma":0.000007193369,"domain_scores_codex":[0.9990344,0.0001096803,0.0002636266,0.000174519,0.000231207,0.0001865842],"domain_scores_gemma":[0.9991888,0.00009144568,0.0002769812,0.0001322167,0.0001975092,0.0001130645],"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":[0.0004504849,0.0007113725,0.003663918,0.0004892222,0.0004870648,0.0005766499,0.02611697,0.002139352,0.3253124,0.003832956,0.0007973294,0.6354223],"study_design_scores_gemma":[0.005076132,0.001578344,0.01424808,0.001149026,0.0004233883,0.01140438,0.00115276,0.3886612,0.4587391,0.1144443,0.001385474,0.00173776],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1760361,0.0007517858,0.8223608,0.000218838,0.0002342269,0.00009373579,0.000001736907,0.00003145082,0.0002713218],"genre_scores_gemma":[0.5859054,0.0002558217,0.4135553,0.0001302465,0.0001150242,8.770797e-7,3.342616e-7,0.00001251676,0.00002450444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6336845,"threshold_uncertainty_score":0.4981433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03167426684831,"score_gpt":0.2605659472183229,"score_spread":0.228891680370013,"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."}}