{"id":"W4385607400","doi":"10.1145/3608114","title":"Robust OCR Pipeline for Automated Digitization of Mother and Child Protection Cards in India","year":2023,"lang":"en","type":"article","venue":"ACM Journal on Computing and Sustainable Societies","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Biotechnology Industry Research Assistance Council; Ministry of Electronics and Information technology; Indian Institute of Technology Delhi; Bill and Melinda Gates Foundation","keywords":"Computer science; Digitization; Pipeline (software); Artificial intelligence; Optical character recognition; Computer vision; Computer security; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006669186,0.001233549,0.0008961786,0.002688475,0.0005136844,0.001358339,0.001528823,0.0008660945,0.007444676],"category_scores_gemma":[0.002269125,0.0003717101,0.0008902721,0.001462518,0.0004381999,0.0009002776,0.001155131,0.0008508227,0.009896862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005015,"about_ca_system_score_gemma":0.001170002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008960174,"about_ca_topic_score_gemma":0.01266884,"domain_scores_codex":[0.9989485,0.00007867891,0.00008961195,0.0003261181,0.0003874215,0.000169681],"domain_scores_gemma":[0.9987526,0.0001980179,0.0001346827,0.0004532766,0.0004113248,0.00005014251],"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":[0.0003793607,0.0001034824,0.003786245,0.0007235011,0.00008033137,0.000506525,0.0002288072,0.004236823,0.07871905,0.0006822725,0.0243545,0.8861991],"study_design_scores_gemma":[0.0001326186,0.0007314233,0.09295375,0.0003437067,0.0003686099,0.005920999,0.001130973,0.2251735,0.5128129,0.00316608,0.1570068,0.0002585668],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3152038,0.009026836,0.4385302,0.00123377,0.001123861,0.002184816,0.02564707,0.1797847,0.02726488],"genre_scores_gemma":[0.4511379,0.002461485,0.497645,0.0005784763,0.0001697922,0.0006242478,0.02890211,0.001996651,0.01648431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008960174,"threshold_uncertainty_score":0.02490491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01844732457606583,"score_gpt":0.2838287740640956,"score_spread":0.2653814494880297,"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."}}