{"id":"W4302009119","doi":"10.32920/21265788.v1","title":"Optimized Multichannel Filter Bank with Flat Frequency Response for Texture Segmentation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Filter bank; Artificial intelligence; Gabor filter; Filter (signal processing); Segmentation; Pattern recognition (psychology); Computer science; Computer vision; Feature (linguistics); Discriminative model; Image texture; Feature extraction; Frequency domain; Image segmentation","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":[0.0005804628,0.0006077155,0.0006379766,0.0007223908,0.0003192946,0.0006787544,0.000639419,0.0008736852,0.001956592],"category_scores_gemma":[0.0007674671,0.0003280559,0.0005998559,0.0007342471,0.0003944761,0.0007142992,0.0002669346,0.0005019748,0.0006360424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008995805,"about_ca_system_score_gemma":0.0006669644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003813957,"about_ca_topic_score_gemma":0.00695101,"domain_scores_codex":[0.9996891,0.00004502274,0.00001685571,0.00009361895,0.0001064411,0.00004905996],"domain_scores_gemma":[0.9996729,0.0001193709,0.00003359679,0.00005356795,0.0001042932,0.00001627634],"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":[0.0006230763,0.0002001016,0.001329902,0.0002250731,0.0001431279,0.0001440679,0.000101342,0.1478852,0.3714239,0.006507041,0.00262616,0.468791],"study_design_scores_gemma":[0.00001329565,0.00006707311,0.001318355,0.000007109526,0.0000323393,0.00007459262,0.00001339209,0.9098382,0.08560721,0.0008996194,0.002109462,0.00001935532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03170745,0.0003750738,0.9653486,0.00007682195,0.00005084453,0.00003659583,0.00007520049,0.000761079,0.001568409],"genre_scores_gemma":[0.2171006,0.0002866027,0.7791127,0.00009337018,0.00002845566,0.0000925512,0.0002044693,0.0001304641,0.002950908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003813957,"threshold_uncertainty_score":0.007583499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02472833787855887,"score_gpt":0.3022682012979412,"score_spread":0.2775398634193824,"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."}}