{"id":"W2305894560","doi":"10.1007/s11042-015-3200-6","title":"Adaptive blind image watermarking using edge pixel concentration","year":2016,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Contourlet; Watermark; Computer science; Digital watermarking; Robustness (evolution); Artificial intelligence; Discrete cosine transform; Embedding; Entropy (arrow of time); Computer vision; Pixel; Image (mathematics); Pattern recognition (psychology); Block (permutation group theory); Algorithm; Mathematics; Wavelet transform; Wavelet","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":[0.0001114138,0.000124465,0.0001110701,0.00005132961,0.000248394,0.0001364003,0.0002874328,0.0000567982,0.000003773865],"category_scores_gemma":[0.00001066779,0.00008716845,0.00003915744,0.0001737091,0.0001379549,0.0009220724,0.0001232615,0.00006221629,0.000008577101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002473184,"about_ca_system_score_gemma":0.0000204489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004200821,"about_ca_topic_score_gemma":9.163861e-7,"domain_scores_codex":[0.9991242,0.00002958079,0.0001854087,0.0003347237,0.0001046059,0.000221519],"domain_scores_gemma":[0.9992998,0.0001303911,0.00008934212,0.0003205936,0.00007472101,0.00008511166],"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":[0.00001131478,0.00004581602,0.0005945286,0.000007165699,0.00001287663,0.000001631376,0.0003109784,0.000002284199,0.2538225,0.01762852,0.0000525423,0.7275099],"study_design_scores_gemma":[0.0049179,0.000241193,0.01158991,0.0004375366,0.000087929,0.00009616309,0.0001311561,0.2097425,0.5480827,0.110564,0.1119629,0.002146114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008009001,0.00007145689,0.9903905,0.000303748,0.00004567473,0.0004345746,0.00002603206,0.0002239282,0.0004950574],"genre_scores_gemma":[0.6236339,0.00009136277,0.3758761,0.00006691491,0.0001078065,0.0001794892,0.000006737083,0.000007899628,0.0000297512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7253637,"threshold_uncertainty_score":0.3554626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0391221192496881,"score_gpt":0.2820635145499666,"score_spread":0.2429413953002785,"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."}}