Integrated segmentation and recognition of handwritten numerals with cascade neural network

Seong Whan Lee, Sang Yup Kim

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.

Original languageEnglish
Pages (from-to)285-290
Number of pages6
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume29
Issue number2
DOIs
Publication statusPublished - 1999 Jan 1

Fingerprint

Neural networks
Feedforward neural networks
Multilayer neural networks
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

@article{e195c4cd287b4255b592a7a9d59a77f6,
title = "Integrated segmentation and recognition of handwritten numerals with cascade neural network",
abstract = "In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.",
author = "Lee, {Seong Whan} and Kim, {Sang Yup}",
year = "1999",
month = "1",
day = "1",
doi = "10.1109/5326.760572",
language = "English",
volume = "29",
pages = "285--290",
journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Integrated segmentation and recognition of handwritten numerals with cascade neural network

AU - Lee, Seong Whan

AU - Kim, Sang Yup

PY - 1999/1/1

Y1 - 1999/1/1

N2 - In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.

AB - In this paper, we propose an integrated segmentation and recognition method using cascade neural network. In the proposed method, a new type of cascade neural network is developed to train the spatial dependences in connected handwritten numerals. This cascade neural network was originally extended from the multilayer feedforward neural network to improve the discrimination and generalization power. In order to verify the performance of the proposed method, recognition experiments with the National Institute of Standards and Technology (NIST) numeral databases have been performed. The experimental results reveal that the proposed method has higher discrimination and generalization power than the previous integrated segmentation and recognition (ISR) methods have. Moreover, the network-size of the proposed method is smaller than that of previous integrated segmentation and recognition methods.

UR - http://www.scopus.com/inward/record.url?scp=0032664317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032664317&partnerID=8YFLogxK

U2 - 10.1109/5326.760572

DO - 10.1109/5326.760572

M3 - Article

VL - 29

SP - 285

EP - 290

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

SN - 1094-6977

IS - 2

ER -