Segmentation of iranian bank checks

Document Type : Original Article

Authors

Islamic Azad University, Abhar Branch, Abhar, Iran.

Abstract

Abstract:
This paper aims to provide a segmentation algorithm for the Iranian bank checks. The
central idea is based on the morphological analysis and connected component concept.
The proposed algorithm uses the connected component properties to segment
unconstrained Iranian bank checks and prepares those for OCR application. To evaluate
the performance of the algorithm, it has been tested on a set of 240 Iranian bank checks
which collected from 6 types of Iranian bank checks (40 samples for each type). The
algorithm has a good success on document restoration and segmentation. Numerical
results indicate that the proposed algorithm has 96.582% accuracy on segmentation of 5
fields of the Iranian bank checks.

Keywords