{"id":"W4318763323","doi":"10.1088/1361-6501/acb80b","title":"An intelligent vision recognition method based on deep learning for pointer meters","year":2023,"lang":"en","type":"article","venue":"Measurement Science and Technology","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision; Hough transform; Segmentation; Automatic meter reading; Region of interest; 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":[0.005290008,0.00011588,0.0001191007,0.001569294,0.0004601758,0.0001727292,0.0005835477,0.00008044255,0.000003711884],"category_scores_gemma":[0.0007454756,0.0001006045,0.00003045704,0.002239987,0.0001685737,0.0004887955,0.0001008869,0.0001557674,0.00002298047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001702284,"about_ca_system_score_gemma":0.00007532007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006260605,"about_ca_topic_score_gemma":0.000007966314,"domain_scores_codex":[0.9981231,0.00006318314,0.0001677672,0.0005803807,0.0007229964,0.0003425592],"domain_scores_gemma":[0.9986946,0.00005010242,0.00006967875,0.0003559133,0.000767999,0.00006169937],"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":[0.000009150034,0.00003034734,0.0000263187,0.00000702848,0.000002157943,0.000002016122,0.00005330061,0.00004703584,0.07940131,0.0005397559,0.00008200161,0.9197996],"study_design_scores_gemma":[0.0001707732,0.001224113,0.00009380405,0.00002657847,0.000003723746,0.000004128465,0.0001060563,0.2913291,0.6958948,0.009416471,0.001613853,0.0001165972],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004244785,0.0000134525,0.9916514,0.002046725,0.0001693805,0.0003166824,3.026918e-7,0.001255754,0.0003015841],"genre_scores_gemma":[0.9086488,0.00001305569,0.09079348,0.0003816909,0.00001390935,0.0001295745,0.00000112972,0.000007917463,0.00001043809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.919683,"threshold_uncertainty_score":0.4102534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04308370480635166,"score_gpt":0.3218805146452647,"score_spread":0.2787968098389131,"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."}}