A 2-D HMM method for offline handwritten character recognition

Hee Seon Park, Bong K. Sin, Jongsub Moon, Seong Whan Lee

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this paper we consider a hidden Markov mesh random field (HMMRF) for character recognition. The model consists of a "hidden" Markov mesh random field (MMRF) and an overlying probabilistic observation function of the MMRF. Just like the 1-D HMM, the hidden layer is characterized by the initial and the transition probability distributions, and the observation layer is defined by distribution functions for vector-quantized (VQ) observations. The HMMRF-Based method consists of two phases: decoding and training. The decoding and the training algorithms are developed using dynamic programming and maximum likelihood estimation methods. To accelerate the computation in both phases, we employed a look-Ahead scheme based on maximum marginal a posteriori probability criterion for third-Order HMMRF. Tested on a larget-set handwritten Korean Hangul character database, the model showed a promising result: up to 87.2% recognition rate with 8 state HMMRF and 128 VQ levels.

Original languageEnglish
Pages (from-to)91-105
Number of pages15
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume15
Issue number1
DOIs
Publication statusPublished - 2001 Feb 1

Fingerprint

Character recognition
Decoding
Maximum likelihood estimation
Dynamic programming
Probability distributions
Distribution functions

Keywords

  • Hidden Markov mesh random field (HMMRF)
  • Look-ahead technique
  • Offline handwritten character recognition
  • Vector quantization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering

Cite this

A 2-D HMM method for offline handwritten character recognition. / Park, Hee Seon; Sin, Bong K.; Moon, Jongsub; Lee, Seong Whan.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 15, No. 1, 01.02.2001, p. 91-105.

Research output: Contribution to journalArticle

@article{b8048863383d4bcebbef22349a44ad2c,
title = "A 2-D HMM method for offline handwritten character recognition",
abstract = "In this paper we consider a hidden Markov mesh random field (HMMRF) for character recognition. The model consists of a {"}hidden{"} Markov mesh random field (MMRF) and an overlying probabilistic observation function of the MMRF. Just like the 1-D HMM, the hidden layer is characterized by the initial and the transition probability distributions, and the observation layer is defined by distribution functions for vector-quantized (VQ) observations. The HMMRF-Based method consists of two phases: decoding and training. The decoding and the training algorithms are developed using dynamic programming and maximum likelihood estimation methods. To accelerate the computation in both phases, we employed a look-Ahead scheme based on maximum marginal a posteriori probability criterion for third-Order HMMRF. Tested on a larget-set handwritten Korean Hangul character database, the model showed a promising result: up to 87.2{\%} recognition rate with 8 state HMMRF and 128 VQ levels.",
keywords = "Hidden Markov mesh random field (HMMRF), Look-ahead technique, Offline handwritten character recognition, Vector quantization",
author = "Park, {Hee Seon} and Sin, {Bong K.} and Jongsub Moon and Lee, {Seong Whan}",
year = "2001",
month = "2",
day = "1",
doi = "10.1142/S0218001401000757",
language = "English",
volume = "15",
pages = "91--105",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

TY - JOUR

T1 - A 2-D HMM method for offline handwritten character recognition

AU - Park, Hee Seon

AU - Sin, Bong K.

AU - Moon, Jongsub

AU - Lee, Seong Whan

PY - 2001/2/1

Y1 - 2001/2/1

N2 - In this paper we consider a hidden Markov mesh random field (HMMRF) for character recognition. The model consists of a "hidden" Markov mesh random field (MMRF) and an overlying probabilistic observation function of the MMRF. Just like the 1-D HMM, the hidden layer is characterized by the initial and the transition probability distributions, and the observation layer is defined by distribution functions for vector-quantized (VQ) observations. The HMMRF-Based method consists of two phases: decoding and training. The decoding and the training algorithms are developed using dynamic programming and maximum likelihood estimation methods. To accelerate the computation in both phases, we employed a look-Ahead scheme based on maximum marginal a posteriori probability criterion for third-Order HMMRF. Tested on a larget-set handwritten Korean Hangul character database, the model showed a promising result: up to 87.2% recognition rate with 8 state HMMRF and 128 VQ levels.

AB - In this paper we consider a hidden Markov mesh random field (HMMRF) for character recognition. The model consists of a "hidden" Markov mesh random field (MMRF) and an overlying probabilistic observation function of the MMRF. Just like the 1-D HMM, the hidden layer is characterized by the initial and the transition probability distributions, and the observation layer is defined by distribution functions for vector-quantized (VQ) observations. The HMMRF-Based method consists of two phases: decoding and training. The decoding and the training algorithms are developed using dynamic programming and maximum likelihood estimation methods. To accelerate the computation in both phases, we employed a look-Ahead scheme based on maximum marginal a posteriori probability criterion for third-Order HMMRF. Tested on a larget-set handwritten Korean Hangul character database, the model showed a promising result: up to 87.2% recognition rate with 8 state HMMRF and 128 VQ levels.

KW - Hidden Markov mesh random field (HMMRF)

KW - Look-ahead technique

KW - Offline handwritten character recognition

KW - Vector quantization

UR - http://www.scopus.com/inward/record.url?scp=0035247075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035247075&partnerID=8YFLogxK

U2 - 10.1142/S0218001401000757

DO - 10.1142/S0218001401000757

M3 - Article

AN - SCOPUS:0035247075

VL - 15

SP - 91

EP - 105

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 1

ER -