BUILDING A SYSTEM TO EXTRACT PERSONAL DOCUMENT INFOMATION FROM IMAGE FOR eKYC SYSTEM

Abstract

In this modern information technology era, automatically extracting
information from identity documents is applied in bank, telecommunications,
healthcare, hotels, and more. This paper uses of computer vision techniques to
build a system which extracts information from identity documents for eKYC
system. There are three main steps: Identifying identity documents, locating
information and extracting information. In particular, identifying indentity cards
and locating information are accomplished by basic image processing techniques to
increase the speed of the entire system. At the information extraction step, the
achievements in text recognition on complex background are used to increase
accuracy. After development and experimentation, the system has achieved a
relatively high degree of accuracy. The accuracy of the whole system is over 90%,
this result can be applied to the eKYC system of banks and credit institutions.