{"id":"W2079125047","doi":"10.1007/s10032-014-0217-8","title":"Texture sparseness for pixel classification of business document images","year":2014,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Constraint (computer-aided design); Artificial intelligence; Feature (linguistics); Document layout analysis; Pattern recognition (psychology); Segmentation; Filter (signal processing); Pixel; Feature vector; Image (mathematics); Graphics; Basis (linear algebra); Texture (cosmology); Data mining; Computer vision; Mathematics; Computer graphics (images)","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":[0.0008846102,0.0001686615,0.0002858914,0.0007462084,0.0001479161,0.0005399585,0.0005656034,0.00007836185,0.00009879738],"category_scores_gemma":[0.0001414854,0.0001315013,0.0002560413,0.0006053763,0.00006227238,0.0006775691,0.00006841087,0.0001345141,0.00001075459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008488823,"about_ca_system_score_gemma":0.00004354204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078604,"about_ca_topic_score_gemma":0.000003082475,"domain_scores_codex":[0.9981232,0.0001126973,0.0006137873,0.0003352004,0.0006603695,0.0001547218],"domain_scores_gemma":[0.9972206,0.0001709822,0.0006838008,0.0002188574,0.001608997,0.00009677656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001385046,0.0002750041,0.001220397,0.0000297233,0.001122487,0.000002914811,0.0001276454,0.0000424317,0.01245778,0.0286225,0.0006828689,0.9552777],"study_design_scores_gemma":[0.005917628,0.001224732,0.2096059,0.0006949254,0.002069118,0.0002059146,0.0003263254,0.05376979,0.2684861,0.3543813,0.101483,0.001835293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01241016,0.00006523952,0.9810378,0.005244447,0.000411131,0.0001577518,0.00001796161,0.00004499304,0.0006105173],"genre_scores_gemma":[0.982771,0.0006997115,0.01526949,0.0003576131,0.0002772672,0.00003316235,0.00009145814,0.000009085325,0.0004912333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9703608,"threshold_uncertainty_score":0.5362466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01999021022263243,"score_gpt":0.2875741722566527,"score_spread":0.2675839620340203,"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."}}