{"id":"W2110315733","doi":"10.1109/icassp.2008.4517836","title":"Unconstrained logo and trademark retrieval in general color image databases using Color Edge Gradient Co-occurrence Histograms","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Color histogram; Artificial intelligence; Color depth; Color quantization; Color image; Color space; Computer vision; Pattern recognition (psychology); Mathematics; Color normalization; HSL and HSV; Hue; Histogram; Image gradient; Histogram equalization; Computer science; Image processing; Image (mathematics)","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":[0.0004238564,0.0002541717,0.0003048169,0.0002249437,0.0002784208,0.0002311739,0.0007885952,0.0000885534,0.00001018552],"category_scores_gemma":[0.0001774701,0.0002047054,0.00005618364,0.0003356534,0.0008251246,0.0007926768,0.0001584033,0.000341059,7.41895e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001317052,"about_ca_system_score_gemma":0.0002615623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003127119,"about_ca_topic_score_gemma":0.000001409546,"domain_scores_codex":[0.9980705,0.00002005022,0.0005135934,0.0005297787,0.0005820863,0.0002840371],"domain_scores_gemma":[0.998568,0.00007769631,0.0004510407,0.0001053303,0.0006913143,0.0001066075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003013281,0.000331224,0.00352127,0.0002870882,0.00003073103,0.00002250489,0.001153821,0.00001304031,0.9525183,0.01793402,0.0003907506,0.02349592],"study_design_scores_gemma":[0.001136036,0.0003030627,0.002490957,0.000777951,0.00003992148,0.0004113963,0.0005605745,0.6786059,0.3103175,0.004582264,0.0001765904,0.0005977613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8537589,0.0001142317,0.1427614,0.0008537376,0.0003034751,0.0004578351,0.0001177947,0.00011237,0.001520203],"genre_scores_gemma":[0.970356,0.0001868438,0.02910336,0.0001502433,0.00008372758,0.000007155935,0.000007155718,0.000009596548,0.00009592864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6785929,"threshold_uncertainty_score":0.8347643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08497011680450753,"score_gpt":0.316940223709219,"score_spread":0.2319701069047115,"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."}}