{"id":"W4247340124","doi":"10.1109/icpr.2004.1334207","title":"Feature fusion for image texture segmentation","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Image texture; Computer science; Feature (linguistics); Image segmentation; Segmentation; Computer vision; Gabor filter; Curse of dimensionality; Texture (cosmology); Fuse (electrical); Scale-space segmentation; Filter (signal processing); Feature vector; Noise (video); Feature extraction; Dimensionality reduction; Image (mathematics); Engineering","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":[0.0002781146,0.0002417664,0.0001851479,0.0001930507,0.0001896452,0.0002837561,0.001275835,0.0001426198,0.00008612337],"category_scores_gemma":[0.0001425096,0.0001862979,0.0001711763,0.0003203497,0.00009743948,0.0008455687,0.0001287893,0.0002458635,0.00005492796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001993588,"about_ca_system_score_gemma":0.0001109659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001667349,"about_ca_topic_score_gemma":0.000003546419,"domain_scores_codex":[0.9983016,0.00001124659,0.0003424032,0.0004733994,0.0006294668,0.0002418663],"domain_scores_gemma":[0.9973503,0.00003308394,0.0004992142,0.0001899317,0.001857079,0.00007044197],"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":[0.0002253438,0.0008953278,0.001177488,0.0003170641,0.0001787409,0.000002823479,0.00131311,0.00000779479,0.3297364,0.06386862,0.0302595,0.5720177],"study_design_scores_gemma":[0.001476771,0.0002728156,0.001871756,0.0006011422,0.00003050324,0.00004037591,0.0002223841,0.00178873,0.8937654,0.09766389,0.001855617,0.0004106279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01522835,0.00008967426,0.9176188,0.04957201,0.001259912,0.001736579,0.000345808,0.000407381,0.01374151],"genre_scores_gemma":[0.9535562,0.0001314456,0.04130952,0.002051902,0.0003222292,0.0002745292,0.0001243903,0.00003665781,0.002193071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9383279,"threshold_uncertainty_score":0.7597008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03601060114087731,"score_gpt":0.2882926720674979,"score_spread":0.2522820709266206,"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."}}