The Sensitivity of the Modified Viterbi Algorithm to the Source Statistics

Rajjan Shinghal; Godfried T. Toussaint

doi:10.1109/TPAMI.1980.4766998

The Sensitivity of the Modified Viterbi Algorithm to the Source Statistics

Rajjan Shinghal, Godfried T. Toussaint

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

The modified Viterbi algorithm is a powerful, and increasingly used, tool for using contextual information in text recognition in its various forms. As yet, no known studies have been published concerning its robustness with respect to source statistics. This paper describes experiments performed to determine the sensitivity of the algorithm to variations in source statistics. The results of the experiments show that a character-recognition machine incorporating the modified Viterbi algorithm, using N-gram statistics estimated from source A does not deteriorate in performance when operating on a passage from source B even if A and B differ significantly in TV-gram distributions or entropy.

Original language	English (US)
Pages (from-to)	181-185
Number of pages	5
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	PAMI-2
Issue number	2
DOIs	https://doi.org/10.1109/TPAMI.1980.4766998
State	Published - Mar 1980

Keywords

Character recognition
Markov process
Viterbi algorithm
contextural information
entropy
natural language statistics
robustness tests
text processing

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

10.1109/TPAMI.1980.4766998

Cite this

@article{29f109c3dcfb44b8a687e8fbabe7b7e1,

title = "The Sensitivity of the Modified Viterbi Algorithm to the Source Statistics",

abstract = "The modified Viterbi algorithm is a powerful, and increasingly used, tool for using contextual information in text recognition in its various forms. As yet, no known studies have been published concerning its robustness with respect to source statistics. This paper describes experiments performed to determine the sensitivity of the algorithm to variations in source statistics. The results of the experiments show that a character-recognition machine incorporating the modified Viterbi algorithm, using N-gram statistics estimated from source A does not deteriorate in performance when operating on a passage from source B even if A and B differ significantly in TV-gram distributions or entropy.",

keywords = "Character recognition, Markov process, Viterbi algorithm, contextural information, entropy, natural language statistics, robustness tests, text processing",

author = "Rajjan Shinghal and Toussaint, {Godfried T.}",

year = "1980",

month = mar,

doi = "10.1109/TPAMI.1980.4766998",

language = "English (US)",

volume = "PAMI-2",

pages = "181--185",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "2",

}

TY - JOUR

T1 - The Sensitivity of the Modified Viterbi Algorithm to the Source Statistics

AU - Shinghal, Rajjan

AU - Toussaint, Godfried T.

PY - 1980/3

Y1 - 1980/3

N2 - The modified Viterbi algorithm is a powerful, and increasingly used, tool for using contextual information in text recognition in its various forms. As yet, no known studies have been published concerning its robustness with respect to source statistics. This paper describes experiments performed to determine the sensitivity of the algorithm to variations in source statistics. The results of the experiments show that a character-recognition machine incorporating the modified Viterbi algorithm, using N-gram statistics estimated from source A does not deteriorate in performance when operating on a passage from source B even if A and B differ significantly in TV-gram distributions or entropy.

AB - The modified Viterbi algorithm is a powerful, and increasingly used, tool for using contextual information in text recognition in its various forms. As yet, no known studies have been published concerning its robustness with respect to source statistics. This paper describes experiments performed to determine the sensitivity of the algorithm to variations in source statistics. The results of the experiments show that a character-recognition machine incorporating the modified Viterbi algorithm, using N-gram statistics estimated from source A does not deteriorate in performance when operating on a passage from source B even if A and B differ significantly in TV-gram distributions or entropy.

KW - Character recognition

KW - Markov process

KW - Viterbi algorithm

KW - contextural information

KW - entropy

KW - natural language statistics

KW - robustness tests

KW - text processing

UR - http://www.scopus.com/inward/record.url?scp=0018995386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0018995386&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.1980.4766998

DO - 10.1109/TPAMI.1980.4766998

M3 - Article

AN - SCOPUS:0018995386

SN - 0162-8828

VL - PAMI-2

SP - 181

EP - 185

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 2

ER -

The Sensitivity of the Modified Viterbi Algorithm to the Source Statistics

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this