{"id":"W2180372284","doi":"10.1109/tcsii.2015.2468995","title":"A Robust Multiplicative Watermark Detector for Color Images in Sparse Domain","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Digital watermarking; Watermark; Generalized normal distribution; Artificial intelligence; Detector; Salt-and-pepper noise; Computer science; Robustness (evolution); Gaussian noise; Multiplicative function; Computer vision; Embedding; Cauchy distribution; Pattern recognition (psychology); Mathematics; Algorithm; Image processing; Statistics; Image (mathematics); Median filter; Normal distribution","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006502377,0.00038348,0.0004986923,0.000447676,0.0003754894,0.0001966179,0.001066989,0.0002051434,0.000001278848],"category_scores_gemma":[0.0000146749,0.0003605454,0.0001963027,0.0005596883,0.0001281276,0.000939662,0.00001372651,0.0003117077,0.000008142214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000205068,"about_ca_system_score_gemma":0.0001009424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001857462,"about_ca_topic_score_gemma":0.00003575065,"domain_scores_codex":[0.9972551,0.0002662657,0.0006086968,0.0008513738,0.0003853785,0.000633189],"domain_scores_gemma":[0.9980788,0.0002613229,0.0002091443,0.0009617895,0.000239647,0.0002492951],"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":[0.001306121,0.004908243,0.0004977522,0.001370781,0.000646773,0.0004083332,0.06947706,0.3741251,0.4295122,0.01015319,0.008688654,0.09890572],"study_design_scores_gemma":[0.01020574,0.002374548,0.0003244402,0.001711666,0.00008271615,0.0003244155,0.001378719,0.06349616,0.8654701,0.006063815,0.04549304,0.00307462],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02164611,0.0001325144,0.9742041,0.0001275441,0.0009648036,0.001830272,0.0001463386,0.0006928099,0.0002555712],"genre_scores_gemma":[0.9700031,0.00001505875,0.02710622,0.00008449895,0.00007518692,0.002374256,0.000003784062,0.00004299854,0.0002949311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.948357,"threshold_uncertainty_score":0.9998847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0481699150911228,"score_gpt":0.2597873136737824,"score_spread":0.2116173985826596,"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."}}