{"id":"W2168375829","doi":"10.1109/mwscas.2004.1353934","title":"Local thresholding of composite documents using multi-layer perceptron nerual network","year":2004,"lang":"en","type":"article","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Thresholding; Computer science; Pixel; Artificial intelligence; Pattern recognition (psychology); Perceptron; Artificial neural network; Feature (linguistics); Image (mathematics); Layer (electronics); Multilayer perceptron; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009576383,0.0004147967,0.0007840145,0.00084414,0.0002736003,0.001010526,0.0008623292,0.0008718972,0.00161699],"category_scores_gemma":[0.002019714,0.0002969936,0.0005305636,0.0006903249,0.0003722406,0.001140504,0.0004424238,0.0007060969,0.0007085064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008567036,"about_ca_system_score_gemma":0.0002996263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003354936,"about_ca_topic_score_gemma":0.004227782,"domain_scores_codex":[0.9995974,0.00007170609,0.00002914642,0.0001192054,0.0001195293,0.00006306497],"domain_scores_gemma":[0.9992203,0.0002775291,0.00009255334,0.00008879037,0.000284902,0.00003598115],"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":[0.0008310544,0.0001915524,0.002645704,0.0001710145,0.0001069693,0.000187532,0.0001460423,0.2463942,0.04562272,0.001683828,0.002962678,0.6990567],"study_design_scores_gemma":[0.00000553888,0.00003357046,0.0006396692,0.000004445813,0.00001194148,0.00002352847,0.00001295715,0.9923728,0.006161652,0.0004834261,0.000245082,0.00000551292],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1873204,0.0008603004,0.8038772,0.000204228,0.0001200719,0.00005255113,0.00009163026,0.003955857,0.003517758],"genre_scores_gemma":[0.7861038,0.0002450807,0.2070918,0.00009706213,0.0000604759,0.00004853577,0.0001911869,0.0001341138,0.006027929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003354936,"threshold_uncertainty_score":0.006670833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04250018013138079,"score_gpt":0.2795750398503095,"score_spread":0.2370748597189287,"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."}}