{"id":"W1981537987","doi":"10.1016/j.cageo.2004.05.002","title":"Segmentation of petrographic images by integrating edge detection and region growing","year":2004,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Brock University","keywords":"Petrography; Pixel; Edge detection; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer vision; Computer science; Noise (video); Image gradient; Segmentation; Image segmentation; Canny edge detector; Range segmentation; Image (mathematics); Pattern recognition (psychology); Geology; Image processing; Image texture; Mineralogy","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":[],"consensus_categories":[],"category_scores_codex":[0.0002847516,0.0001169961,0.0001254804,0.0002836981,0.0002689652,0.0002212395,0.0003914531,0.00003837193,3.358424e-7],"category_scores_gemma":[0.00002422193,0.0001043309,0.00004997131,0.0007930327,0.0002074589,0.001661508,0.0001260599,0.00009562475,6.466072e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003770949,"about_ca_system_score_gemma":0.00002741174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003499703,"about_ca_topic_score_gemma":0.00001442042,"domain_scores_codex":[0.998966,0.00004800866,0.000216819,0.0003563067,0.0002250288,0.0001878519],"domain_scores_gemma":[0.9994985,0.00004821685,0.0001533439,0.0001750114,0.00007403163,0.00005093006],"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":[0.000003133428,0.00003934938,0.0004567771,0.00002471073,0.000006411355,0.000005441151,0.001026672,0.00003164257,0.199966,0.0009087868,0.00008715061,0.7974439],"study_design_scores_gemma":[0.0002285293,0.0004037114,0.001555153,0.00007370303,0.000005069209,0.00006883284,0.0003597781,0.005076456,0.9875146,0.004422084,0.0001189121,0.0001731289],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1505782,0.0002390747,0.8482786,0.0001961142,0.0003245527,0.0001009325,4.206021e-7,0.0002004666,0.00008157824],"genre_scores_gemma":[0.9210259,0.00006809308,0.07872022,0.0001397769,0.00002511167,0.000008756414,5.94377e-7,0.000003538563,0.000007977179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7972708,"threshold_uncertainty_score":0.425449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006974944809332075,"score_gpt":0.2259577024423952,"score_spread":0.2189827576330631,"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."}}