A method for document zone content classification

Yalin Wang, Ihsin T. Phillips, Robert M. Haralick

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper describes an algorithm to classify each given document zone into one of nine classes and provides a protocol for its performance evaluation. The classification scheme uses an optimized binary decision tree and Viterbi algorithm for HMM to find the optimal solution. Our algorithm was trained and tested on a total of 24,177 zones within the 1600 images from UWCDROM III database. Its accuracy rate is 98.45% with a mean false alarm rate of 0.50%.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages196-199
Number of pages4
Volume16
Edition3
StatePublished - 2002
Externally publishedYes

Fingerprint

Viterbi algorithm
Decision trees

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Wang, Y., Phillips, I. T., & Haralick, R. M. (2002). A method for document zone content classification. In Proceedings - International Conference on Pattern Recognition (3 ed., Vol. 16, pp. 196-199)

A method for document zone content classification. / Wang, Yalin; Phillips, Ihsin T.; Haralick, Robert M.

Proceedings - International Conference on Pattern Recognition. Vol. 16 3. ed. 2002. p. 196-199.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Y, Phillips, IT & Haralick, RM 2002, A method for document zone content classification. in Proceedings - International Conference on Pattern Recognition. 3 edn, vol. 16, pp. 196-199.
Wang Y, Phillips IT, Haralick RM. A method for document zone content classification. In Proceedings - International Conference on Pattern Recognition. 3 ed. Vol. 16. 2002. p. 196-199
Wang, Yalin ; Phillips, Ihsin T. ; Haralick, Robert M. / A method for document zone content classification. Proceedings - International Conference on Pattern Recognition. Vol. 16 3. ed. 2002. pp. 196-199
@inproceedings{7a95667ad4c64982b609a849a342bc34,
title = "A method for document zone content classification",
abstract = "This paper describes an algorithm to classify each given document zone into one of nine classes and provides a protocol for its performance evaluation. The classification scheme uses an optimized binary decision tree and Viterbi algorithm for HMM to find the optimal solution. Our algorithm was trained and tested on a total of 24,177 zones within the 1600 images from UWCDROM III database. Its accuracy rate is 98.45{\%} with a mean false alarm rate of 0.50{\%}.",
author = "Yalin Wang and Phillips, {Ihsin T.} and Haralick, {Robert M.}",
year = "2002",
language = "English (US)",
volume = "16",
pages = "196--199",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "3",

}

TY - GEN

T1 - A method for document zone content classification

AU - Wang, Yalin

AU - Phillips, Ihsin T.

AU - Haralick, Robert M.

PY - 2002

Y1 - 2002

N2 - This paper describes an algorithm to classify each given document zone into one of nine classes and provides a protocol for its performance evaluation. The classification scheme uses an optimized binary decision tree and Viterbi algorithm for HMM to find the optimal solution. Our algorithm was trained and tested on a total of 24,177 zones within the 1600 images from UWCDROM III database. Its accuracy rate is 98.45% with a mean false alarm rate of 0.50%.

AB - This paper describes an algorithm to classify each given document zone into one of nine classes and provides a protocol for its performance evaluation. The classification scheme uses an optimized binary decision tree and Viterbi algorithm for HMM to find the optimal solution. Our algorithm was trained and tested on a total of 24,177 zones within the 1600 images from UWCDROM III database. Its accuracy rate is 98.45% with a mean false alarm rate of 0.50%.

UR - http://www.scopus.com/inward/record.url?scp=25144445778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=25144445778&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:25144445778

VL - 16

SP - 196

EP - 199

BT - Proceedings - International Conference on Pattern Recognition

ER -