{"id":"W2096780289","doi":"10.1109/tip.2007.901245","title":"Iterative Cross Section Sequence Graph for Handwritten Character Segmentation","year":2007,"lang":"en","type":"letter","venue":"IEEE Transactions on Image Processing","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ingredion (Canada)","funders":"","keywords":"Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Computer science; Optical character recognition; Feature extraction; Pixel; Thresholding; Graph; Character (mathematics); Iterative method; Feature (linguistics); Computer vision; Image (mathematics); Algorithm; Mathematics; Theoretical computer science","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004320331,0.0005291089,0.0003755501,0.0009614663,0.001058809,0.001793229,0.0005929805,0.0006959345,0.00002333208],"category_scores_gemma":[0.000008985341,0.0005367188,0.0003205361,0.0007931124,0.0001655737,0.003272665,0.000004045236,0.001723471,0.00002480915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003587565,"about_ca_system_score_gemma":0.0001731385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002906879,"about_ca_topic_score_gemma":0.000007793188,"domain_scores_codex":[0.9971411,0.00009818375,0.0005859282,0.001013608,0.0005376082,0.0006235287],"domain_scores_gemma":[0.9981221,0.0001482138,0.0004106969,0.0004891945,0.0007621308,0.00006767851],"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":[0.0001540599,0.0002005868,0.000001180599,0.001381746,0.0001445444,0.0002242433,0.002501019,0.00009355979,0.09041807,0.000002842265,0.07490807,0.8299701],"study_design_scores_gemma":[0.000534645,0.0002987163,0.00000453983,0.0003288389,0.00006228145,0.0001483344,0.00002633301,0.005104695,0.9631557,0.0005356386,0.02905609,0.0007441624],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.00004342264,0.00004831292,0.9777616,0.0181753,0.001714347,0.0009198899,0.00008240466,0.001029777,0.0002249144],"genre_scores_gemma":[0.0182508,0.0001133135,0.4533758,0.510313,0.005795791,0.00257076,0.000222022,0.0003212347,0.009037212],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8727376,"threshold_uncertainty_score":0.9997084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02668287625721912,"score_gpt":0.3152314745828336,"score_spread":0.2885485983256145,"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."}}