{"id":"W2160334819","doi":"10.1109/icdsp.2009.5201062","title":"Image segmentation using Scale-Space Random Walks","year":2009,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Random walk; Computer science; Extension (predicate logic); Image segmentation; Noise (video); Segmentation; Image (mathematics); Artificial intelligence; Space (punctuation); Scale (ratio); Scale-space segmentation; Random walker algorithm; Algorithm; Pattern recognition (psychology); Computer vision; Mathematics; Statistics","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":[0.000177837,0.00007661359,0.00008468384,0.00006217178,0.00009195816,0.0001793544,0.0002843816,0.00003257552,0.00003263706],"category_scores_gemma":[0.00001216847,0.00006301782,0.00004390734,0.0002924557,0.00002113009,0.0006947683,0.00003155178,0.00005260574,0.00003884184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004072714,"about_ca_system_score_gemma":0.00002470482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000982104,"about_ca_topic_score_gemma":3.920164e-7,"domain_scores_codex":[0.9993156,0.00003541385,0.0001375357,0.0001969609,0.0001778044,0.0001366452],"domain_scores_gemma":[0.9995409,0.00001988625,0.00005483692,0.0002566622,0.00008118563,0.00004656012],"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":[0.00001130972,0.00005185936,0.00003804973,0.000003632377,0.000002658019,0.000002909596,0.0001987608,0.000001270926,0.8571634,0.01169294,0.0007646971,0.1300685],"study_design_scores_gemma":[0.0005894713,0.00005775006,0.001045159,0.000009670261,0.000004825229,0.00001535079,0.00003752498,0.1342362,0.8568438,0.006319295,0.0006707909,0.0001701835],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002870809,0.00002843202,0.9855138,0.002198849,0.00005106505,0.0001424949,2.748117e-7,0.0004271976,0.008767042],"genre_scores_gemma":[0.2580574,0.00001773213,0.7403596,0.0006566863,0.00003184359,0.000002883297,0.000001453421,0.000003275775,0.0008690928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2551866,"threshold_uncertainty_score":0.2569792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01776286300384639,"score_gpt":0.2853637186529648,"score_spread":0.2676008556491184,"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."}}