{"id":"W2058533675","doi":"10.1016/j.cageo.2004.10.003","title":"A semi-automatic segmentation procedure for feature extraction in remotely sensed imagery","year":2004,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada","funders":"Canadian Forest Service; Chinese Academy of Sciences; Government of Ontario","keywords":"Computer science; Thresholding; Artificial intelligence; Computer vision; Feature extraction; Sample (material); Feature (linguistics); Remote sensing; Segmentation; Edge detection; Image segmentation; Pattern recognition (psychology); Software; Image processing; Image (mathematics); Geology","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":[0.0006163403,0.001096229,0.00126977,0.002352118,0.001096584,0.00119021,0.001349513,0.001092876,0.004239684],"category_scores_gemma":[0.001418948,0.0008540233,0.001340989,0.002352423,0.0007014856,0.000891975,0.0009146098,0.001071077,0.003384642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004419945,"about_ca_system_score_gemma":0.001752151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004937139,"about_ca_topic_score_gemma":0.009249218,"domain_scores_codex":[0.9993718,0.00006746151,0.00005208797,0.0001875538,0.0002449952,0.00007616948],"domain_scores_gemma":[0.9990757,0.0002959098,0.00007891076,0.0001677153,0.0003447242,0.00003705039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001607971,0.0001531591,0.0005814407,0.0002594385,0.00008168814,0.0001405057,0.0001859986,0.01039822,0.2441391,0.002894389,0.006139598,0.7348657],"study_design_scores_gemma":[0.00008341947,0.000333725,0.0152443,0.00007774933,0.0002307201,0.001122109,0.0001831921,0.6446625,0.2885639,0.01129708,0.03798765,0.0002136382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006404798,0.0001259051,0.9890894,0.00003310555,0.00004491864,0.0001172266,0.0002562365,0.003376329,0.0005520199],"genre_scores_gemma":[0.03199358,0.0001394629,0.9638018,0.00005609295,0.00004046613,0.000243094,0.001227757,0.0005413338,0.001956456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004937139,"threshold_uncertainty_score":0.01418316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499451929209674,"score_gpt":0.2569601393947394,"score_spread":0.2419656201026427,"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."}}