{"id":"W4285070320","doi":"10.1109/lgrs.2022.3185557","title":"SAR Despeckling Based on CNN and Bayesian Estimator in Complex Wavelet Domain","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; Centre For Cold Ocean Resources Engineering; Institut National de la Recherche Scientifique","funders":"","keywords":"Wavelet; Artificial intelligence; Computer science; Convolutional neural network; Pattern recognition (psychology); Speckle noise; Speckle pattern; Synthetic aperture radar; Estimator; Noise reduction; Shrinkage estimator; Wavelet transform; Maximum a posteriori estimation; Mathematics; Bias of an estimator; Statistics; Minimum-variance unbiased estimator; Maximum likelihood","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":[0.001432533,0.0001804712,0.000216591,0.0003538521,0.000819255,0.0002853956,0.0003438476,0.00002991788,0.000002708355],"category_scores_gemma":[0.00004604953,0.0001734666,0.00003800513,0.0006792222,0.0002496913,0.0002142488,0.0001549433,0.0003075078,0.000001691455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007929149,"about_ca_system_score_gemma":0.00005697783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002551361,"about_ca_topic_score_gemma":0.000007731976,"domain_scores_codex":[0.9978379,0.0003674831,0.0002262731,0.0006479989,0.000450163,0.0004701511],"domain_scores_gemma":[0.9991926,0.000240154,0.00007998433,0.0003543578,0.00001720966,0.000115711],"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":[0.00006104541,0.00003960087,0.0001018448,0.00003409695,0.000005056316,0.001515296,0.00214569,0.007043092,0.3289356,0.0002721773,0.0007654061,0.6590812],"study_design_scores_gemma":[0.0005934866,0.00008947997,0.001420419,0.00004636341,0.000002735514,0.0002017178,0.00007279466,0.993576,0.001350004,0.00127231,0.001118643,0.0002560687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2650212,0.0000171188,0.7277494,0.006629084,0.0002946523,0.00009802618,0.000001105625,0.00004899925,0.0001403678],"genre_scores_gemma":[0.3610935,0.000002077463,0.6263379,0.01249644,0.00003698968,8.625942e-8,9.109741e-7,0.000008907768,0.00002316126],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9865329,"threshold_uncertainty_score":0.7073762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02005916016192574,"score_gpt":0.2570432534528794,"score_spread":0.2369840932909537,"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."}}