You are here

AUTONOMOUS REPAIR OF OPTICAL CHARACTER RECOGNITION DATA THROUGH SIMPLE VOTING AND MULTI-DIMENSIONAL INDEXING TECHNIQUES

Download pdf | Full Screen View

Date Issued:
2005
Abstract/Description:
The three major optical character recognition (OCR) engines (ExperVision, Scansoft OCR, and Abby OCR) in use today are all capable of recognizing text at near perfect percentages. The remaining errors however have proven very difficult to identify within a single engine. Recent research has shown that a comparison between the errors of the three engines proved to have very little correlation, and thus, when used in conjunction, may be useful to increase accuracy of the final result. This document discusses the implementation and results of a simple voting system designed to prove the hypothesis and show a statistical improvement in overall accuracy. Additional aspects of implementing an improved OCR scheme such as dealing with multiple engine data output alignment and recognizing application specific solutions are also addressed in this research. Although voting systems are currently in use by many major OCR engine developers, this research focuses on the addition of a collaborative system which is able to utilize the various positive aspects of multiple engines while also addressing the immediate need for practical industry applications such as litigation and forms processing. Doculex TM, a major developer and leader in the document imaging industry, has provided the funding for this research.
Title: AUTONOMOUS REPAIR OF OPTICAL CHARACTER RECOGNITION DATA THROUGH SIMPLE VOTING AND MULTI-DIMENSIONAL INDEXING TECHNIQUES.
15 views
8 downloads
Name(s): Sprague, Christopher, Author
Weeks, Arthur, Committee Chair
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2005
Publisher: University of Central Florida
Language(s): English
Abstract/Description: The three major optical character recognition (OCR) engines (ExperVision, Scansoft OCR, and Abby OCR) in use today are all capable of recognizing text at near perfect percentages. The remaining errors however have proven very difficult to identify within a single engine. Recent research has shown that a comparison between the errors of the three engines proved to have very little correlation, and thus, when used in conjunction, may be useful to increase accuracy of the final result. This document discusses the implementation and results of a simple voting system designed to prove the hypothesis and show a statistical improvement in overall accuracy. Additional aspects of implementing an improved OCR scheme such as dealing with multiple engine data output alignment and recognizing application specific solutions are also addressed in this research. Although voting systems are currently in use by many major OCR engine developers, this research focuses on the addition of a collaborative system which is able to utilize the various positive aspects of multiple engines while also addressing the immediate need for practical industry applications such as litigation and forms processing. Doculex TM, a major developer and leader in the document imaging industry, has provided the funding for this research.
Identifier: CFE0000380 (IID), ucf:46337 (fedora)
Note(s): 2005-05-01
M.S.Cp.E.
Engineering and Computer Science, Department of Electrical and Computer Engineering
Masters
This record was generated from author submitted information.
Subject(s): optical
character
recognition
OCR
simple
voting
multi-dimensional
indexing
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0000380
Restrictions on Access: public
Host Institution: UCF

In Collections