{"id":"W2028003041","doi":"10.1109/icdar.2013.261","title":"A Binarization-Free Clustering Approach to Segment Curved Text Lines in Historical Manuscripts","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Artificial intelligence; Cluster analysis; Search engine indexing; Segmentation; Line (geometry); Curvature; Point (geometry); Pattern recognition (psychology); Spotting; Image segmentation; Word (group theory); Image (mathematics); Computer vision; Information retrieval; Mathematics; Geometry","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":[0.0002228688,0.0001504893,0.0001811246,0.0003449823,0.00005380556,0.0002088537,0.0009786766,0.00007510775,0.00005373331],"category_scores_gemma":[0.00008624533,0.0001354146,0.000042139,0.0006491105,0.00001037259,0.0005975947,0.0006584562,0.0001099367,0.0002220127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003544303,"about_ca_system_score_gemma":0.00002740431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00066003,"about_ca_topic_score_gemma":0.00005758326,"domain_scores_codex":[0.9986033,0.00006486073,0.0003385382,0.0004417635,0.0002640175,0.0002874484],"domain_scores_gemma":[0.9990408,0.00002800437,0.00004616792,0.0006195915,0.0001222472,0.000143119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001571846,0.002043122,0.007343407,0.0001764878,0.00003381917,0.00002442688,0.005774241,0.0003567566,0.01282801,0.01612097,0.2332744,0.7220086],"study_design_scores_gemma":[0.002653087,0.0007319456,0.04032161,0.0003110293,0.00001167222,0.00009073771,0.0002724743,0.8757498,0.01538297,0.02364703,0.03844968,0.002377961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004995115,0.00002923825,0.9810405,0.002890051,0.0001750795,0.0006220918,4.042827e-7,0.0005364443,0.009711044],"genre_scores_gemma":[0.2645702,0.00000811393,0.7299035,0.001487035,0.00006411986,0.0005657609,0.000003642247,0.00001599383,0.003381656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.875393,"threshold_uncertainty_score":0.5522047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03067479077636793,"score_gpt":0.2336305491102551,"score_spread":0.2029557583338872,"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."}}