{"id":"W2158510284","doi":"10.1016/j.isprsjprs.2008.06.005","title":"Region based segmentation of QuickBird multispectral imagery through band ratios and fuzzy comparison","year":2008,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"BAND foundation","keywords":"Multispectral image; Segmentation; Computer science; Artificial intelligence; Image segmentation; Scale-space segmentation; Segmentation-based object categorization; Satellite imagery; Multispectral pattern recognition; Remote sensing; Satellite; Pattern recognition (psychology); Region growing; Computer vision; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002456695,0.0001914892,0.0004084406,0.0002361844,0.000130423,0.00004688809,0.00004647478,0.0001124249,0.000001004778],"category_scores_gemma":[0.00009347482,0.0001803011,0.00009413918,0.000272835,0.000218045,0.0003079674,0.000008157746,0.0003119668,4.503516e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006114648,"about_ca_system_score_gemma":0.00003316373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001334905,"about_ca_topic_score_gemma":0.00002343528,"domain_scores_codex":[0.9986294,0.00009737804,0.0006681185,0.0001514141,0.0002483903,0.0002052945],"domain_scores_gemma":[0.99902,0.0001722359,0.000378982,0.0001456535,0.0001860048,0.00009710221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001390614,0.0000296976,0.0008285296,0.0001747633,0.00006942821,0.0001444775,0.001558635,0.002690516,0.8080989,0.000001546471,0.0002616908,0.1860027],"study_design_scores_gemma":[0.001380535,0.0001678279,0.004090742,0.0003425749,0.00008677557,0.002048297,0.0006224001,0.389506,0.6012429,0.0001207661,0.0001598437,0.0002313608],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6169484,0.0007480565,0.3817075,0.0000624298,0.0002343077,0.0001037848,7.66436e-7,0.00003106201,0.0001637445],"genre_scores_gemma":[0.875145,0.0005775291,0.1240987,0.00003485728,0.0001053865,1.238929e-8,0.000003043752,0.00002898707,0.000006476428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3868155,"threshold_uncertainty_score":0.7352464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0297170945567716,"score_gpt":0.2618328504930777,"score_spread":0.2321157559363061,"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."}}