TITLE:
Extraction of Arabic Handwriting Fields by Forms Matching
AUTHORS:
Ameur Bensefia
KEYWORDS:
Handwriting Document Analysis, Binarization, Zones of Interest Extraction, Fourier-Mellin Transform
JOURNAL NAME:
Journal of Signal and Information Processing,
Vol.6 No.1,
January
21,
2015
ABSTRACT: Filling forms is one of the most useful and
powerful ways to collect information from people in business, education and
many other domains. Nowadays, almost everything is computerized. That creates a
curtail need for extracting these handwritings from the forms in order to get
them into the computer systems and databases. In this paper, we propose an
original method that will extract handwritings from two types of forms; bank
and administrative form. Our system will take as input any of the two forms
already filled. And according to some statistical measures our system will
identify the form. The second step is to subtract the filled form from a
previously inserted empty form. In order to make the acting easier and faster a
Fourier-Melin transform was used to re-orient the forms correctly. This method
has been evaluated with 50 handwriting forms (from both types Bank and
University) and the results were approximatively 90%.