OCR error correction using a noisy channel model

Okan Kolak; Philip Resnik

doi:10.3115/1289189.1289208

ScienceGate Book Chapters

JOURNAL ARTICLE

OCR error correction using a noisy channel model

Okan Kolak Philip Resnik

Year: 2002 Pages: 257-262

DOI: 10.3115/1289189.1289208

Get Full-Text PDF Get Analytical Report

Abstract

In this paper, we take a pattern recognition approach to correcting errors in text generated from printed documents using optical character recognition (OCR). We apply a very general, theoretically optimal model to the problem of OCR word correction, introduce practical methods for parameter estimation, and evaluate performance on real data.

Keywords:

Optical character recognition Computer science Artificial intelligence Error detection and correction Channel (broadcasting) Speech recognition Word (group theory) Character (mathematics) Character recognition Pattern recognition (psychology) Text recognition Natural language processing Algorithm Image (mathematics) Mathematics Telecommunications

Metrics

Cited By

1.11

FWCI (Field Weighted Citation Impact)

Refs

0.80

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Algorithms and Data Compression

Physical Sciences → Computer Science → Artificial Intelligence

Handwritten Text Recognition Techniques

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Blind Source Separation Techniques

Physical Sciences → Computer Science → Signal Processing

OCR error correction using a noisy channel model

Abstract

Metrics

Citation History

Topics

Related Documents

An improved error model for noisy channel spelling correction

Noisy Channel for Low Resource Grammatical Error Correction

Image Data Compression and Noisy Channel Error Correction Using Deep Neural Network

Gaussian Error Correction of Quantum States in a Correlated Noisy Channel

A Framework for Spelling Correction in Persian Language Using Noisy Channel Model