{"id":"W2043265177","doi":"10.1117/12.819382","title":"Steerable optical flow based image registration: application to aligning human torso images","year":2009,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer vision; Image registration; Computer science; Optical flow; Torso; Pixel; Pyramid (geometry); Affine transformation; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0007970352,0.0004625061,0.0004859352,0.0008920574,0.0002478808,0.0005737197,0.0004793701,0.0007657394,0.001395743],"category_scores_gemma":[0.002288654,0.0002894259,0.0003908486,0.00068362,0.0005097769,0.0005645014,0.0005507683,0.0004798396,0.000484896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002839643,"about_ca_system_score_gemma":0.0005031979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001904171,"about_ca_topic_score_gemma":0.001635748,"domain_scores_codex":[0.9996461,0.00008793957,0.00001296068,0.00006695119,0.0001590628,0.00002701759],"domain_scores_gemma":[0.9995655,0.0001652228,0.00005756192,0.00007221886,0.0001150032,0.00002444737],"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":[0.0002872359,0.0001377572,0.0008290869,0.00022914,0.00005374556,0.0003931708,0.000343079,0.09654824,0.1985353,0.004819948,0.001597194,0.6962262],"study_design_scores_gemma":[0.00003962212,0.0003595221,0.002908237,0.00002903852,0.00003493969,0.001543453,0.0001099464,0.8614529,0.1210698,0.004348024,0.008032174,0.00007232103],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02558205,0.0002786533,0.9717989,0.0001374128,0.00003552582,0.00009940779,0.00003303252,0.0009761285,0.001058883],"genre_scores_gemma":[0.2496755,0.0005859167,0.747813,0.00006537984,0.00003512199,0.00008316979,0.00008582944,0.0001398067,0.00151619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001904171,"threshold_uncertainty_score":0.004669189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00957935221808369,"score_gpt":0.2563592643757143,"score_spread":0.2467799121576306,"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."}}