{"id":"W2057508308","doi":"10.1016/j.patrec.2007.05.002","title":"Globally adaptive region information for automatic color–texture image segmentation","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Image texture; Region growing; Image segmentation; Computer vision; Scale-space segmentation; Segmentation-based object categorization; Segmentation; Computer science; Pattern recognition (psychology); Range segmentation; Minimum spanning tree-based segmentation; Partition (number theory); Image (mathematics); Color image; Homogeneous; Texture (cosmology); Boundary (topology); Mathematics; Image processing","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":[0.0006402523,0.0001825365,0.0001503008,0.0002473018,0.0001367077,0.0002669605,0.0003816559,0.00008813363,0.00005355815],"category_scores_gemma":[0.00009274473,0.0001858552,0.00008901626,0.0002525472,0.00006139158,0.002840301,0.00006403696,0.0001280932,0.0002307544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002085695,"about_ca_system_score_gemma":0.00002733936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002175423,"about_ca_topic_score_gemma":0.000007161893,"domain_scores_codex":[0.9983405,0.00007608534,0.0005263856,0.0002675191,0.0004578661,0.0003316474],"domain_scores_gemma":[0.9988572,0.0002024828,0.0003683984,0.0002296117,0.0002182624,0.0001240308],"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":[0.00001695913,0.00003185702,0.00007082349,0.00006363505,0.0000189391,0.00001097227,0.0007224416,0.000001646099,0.008926787,0.00002853404,0.01703284,0.9730746],"study_design_scores_gemma":[0.01053427,0.001773834,0.02174449,0.0009687276,0.000223261,0.0004159105,0.002371756,0.2142793,0.7335842,0.007876866,0.003134902,0.003092435],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009438657,0.000004498876,0.9848094,0.00336902,0.0003567994,0.001141601,0.00002583255,0.0005837299,0.0002704828],"genre_scores_gemma":[0.1202353,0.000009820073,0.8267539,0.05186567,0.0001885693,0.000356241,0.0005564069,0.00002084379,0.00001326436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9699821,"threshold_uncertainty_score":0.7578956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02051284080758864,"score_gpt":0.2712800684977635,"score_spread":0.2507672276901748,"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."}}