H. D. Liem, N. D. Minh, Nguyen Bao Trung, Hoang Tien Duc, Phạm Hoàng Hiệp, Doan Viet Dung, Dang Hoang Vu
{"title":"FVI: An End-to-end Vietnamese Identification Card Detection and Recognition in Images","authors":"H. D. Liem, N. D. Minh, Nguyen Bao Trung, Hoang Tien Duc, Phạm Hoàng Hiệp, Doan Viet Dung, Dang Hoang Vu","doi":"10.1109/NICS.2018.8606831","DOIUrl":null,"url":null,"abstract":"The neccesity of digitializing all old constrained forms such identification card or register book have become a critical issue due to the importance of practical applications for sales or financial services. To address this issue, we develop an End-to-end Identification Card Recognition system which allows us to quickly detect, recognize text and extract important information from the ID card. We not only present the modeling technique for efficient detection and recognition of texts but also the architecture design of FVI which is currently deployed in several organizations. We performed extensive evaluations of the designed system as the verification of our efficient system for a large-scale detecion and recognition of constrained forms.","PeriodicalId":137666,"journal":{"name":"2018 5th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 5th NAFOSTED Conference on Information and Computer Science (NICS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NICS.2018.8606831","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16
Abstract
The neccesity of digitializing all old constrained forms such identification card or register book have become a critical issue due to the importance of practical applications for sales or financial services. To address this issue, we develop an End-to-end Identification Card Recognition system which allows us to quickly detect, recognize text and extract important information from the ID card. We not only present the modeling technique for efficient detection and recognition of texts but also the architecture design of FVI which is currently deployed in several organizations. We performed extensive evaluations of the designed system as the verification of our efficient system for a large-scale detecion and recognition of constrained forms.