iOCR: Informed Optical Character Recognition for Election Ballot Tallies

TL;DR

This paper introduces iOCR, an informed OCR system with spell correction designed to improve election ballot tallying accuracy over traditional OCR methods.

Contribution

The paper presents a novel OCR approach incorporating spell correction specifically tailored for election vote counting, enhancing accuracy.

Findings

iOCR outperforms conventional OCR in ballot tallying

Spell correction significantly reduces OCR errors

Improved accuracy in vote tabulation

Abstract

The purpose of this study is to explore the performance of Informed OCR or iOCR. iOCR was developed with a spell correction algorithm to fix errors introduced by conventional OCR for vote tabulation. The results found that the iOCR system outperforms conventional OCR techniques.