Information extraction and unfilled-form structure retrieval from filled-up forms

Abstract

Form processing is an essential operation in business and government organizations. In this digital arena, it is necessary to extract the information from the form documents and the Information extraction is useful in postal address extraction and forgery detection in bank cheques etc. This process can also recover the Unfilled-Form structure from a filled up form and can be used in retrieval of empty bank cheques and postal cards etc. This paper presents the method for information extraction and retrieval of unfilled form structure from filled-up form documents in two steps. First step deals with the detection of lines present in the form document along with starting and ending points of those lines and second step involves the extraction of character information present above these detected lines using mask processing.