An EMD-based recognition approach for similar handwritten numerals

He-Long LI; Sam KWONG; Yan-Xiong LI

doi:10.1109/ICMLC.2009.5212792

An EMD-based recognition approach for similar handwritten numerals

He-Long LI, Sam KWONG, Yan-Xiong LI

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

Abstract

This paper presents a novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD), We firstly use the local maximum modulus of wavelet transform (MMWT) to get the width-invariant and grey-level invariant characterization of contours in an image. Then we apply EMD analysis to decompose the synthetic shift normalization of curvature into their components, which could produce more compact features. Finally, three different classifiers, i.e. support vector machine (SVM), hidden Markov model (HMM), and artificial neural network (ANN), are used to discriminate similar handwritten numerals for testing the effectiveness of the extracted features. Experimental results show that the proposed approach obtains higher recognition rates compared with the traditional algorithm for extracting features. © 2009 IEEE.

Original language	English
Title of host publication	Proceedings of the 2009 International Conference on Machine Learning and Cybernetics
Publisher	IEEE
Pages	3600-3605
Number of pages	6
ISBN (Print)	9781424437023
DOIs	https://doi.org/10.1109/ICMLC.2009.5212792
Publication status	Published - Jul 2009
Externally published	Yes
Event	2009 International Conference on Machine Learning and Cybernetics - Hebei, China Duration: 12 Jul 2009 → 15 Jul 2009

Conference

Conference	2009 International Conference on Machine Learning and Cybernetics
Country/Territory	China
City	Hebei
Period	12/07/09 → 15/07/09

Keywords

Discrimination of handwritten numerals
Empirical mode decomposition (EMD)
Feature extraction
Hilbert-Huang transform (HHT)

Access to Document

10.1109/ICMLC.2009.5212792

Cite this

@inproceedings{9719ff28c0e54355bae47de8e09b97c4,

title = "An EMD-based recognition approach for similar handwritten numerals",

abstract = "This paper presents a novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD), We firstly use the local maximum modulus of wavelet transform (MMWT) to get the width-invariant and grey-level invariant characterization of contours in an image. Then we apply EMD analysis to decompose the synthetic shift normalization of curvature into their components, which could produce more compact features. Finally, three different classifiers, i.e. support vector machine (SVM), hidden Markov model (HMM), and artificial neural network (ANN), are used to discriminate similar handwritten numerals for testing the effectiveness of the extracted features. Experimental results show that the proposed approach obtains higher recognition rates compared with the traditional algorithm for extracting features. {\textcopyright} 2009 IEEE.",

keywords = "Discrimination of handwritten numerals, Empirical mode decomposition (EMD), Feature extraction, Hilbert-Huang transform (HHT)",

author = "He-Long LI and Sam KWONG and Yan-Xiong LI",

year = "2009",

month = jul,

doi = "10.1109/ICMLC.2009.5212792",

language = "English",

isbn = "9781424437023",

pages = "3600--3605",

booktitle = "Proceedings of the 2009 International Conference on Machine Learning and Cybernetics",

publisher = "IEEE",

note = "2009 International Conference on Machine Learning and Cybernetics ; Conference date: 12-07-2009 Through 15-07-2009",

}

TY - GEN

T1 - An EMD-based recognition approach for similar handwritten numerals

AU - LI, He-Long

AU - KWONG, Sam

AU - LI, Yan-Xiong

PY - 2009/7

Y1 - 2009/7

N2 - This paper presents a novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD), We firstly use the local maximum modulus of wavelet transform (MMWT) to get the width-invariant and grey-level invariant characterization of contours in an image. Then we apply EMD analysis to decompose the synthetic shift normalization of curvature into their components, which could produce more compact features. Finally, three different classifiers, i.e. support vector machine (SVM), hidden Markov model (HMM), and artificial neural network (ANN), are used to discriminate similar handwritten numerals for testing the effectiveness of the extracted features. Experimental results show that the proposed approach obtains higher recognition rates compared with the traditional algorithm for extracting features. © 2009 IEEE.

AB - This paper presents a novel approach to recognize similar handwritten numerals based on empirical mode decomposition (EMD), We firstly use the local maximum modulus of wavelet transform (MMWT) to get the width-invariant and grey-level invariant characterization of contours in an image. Then we apply EMD analysis to decompose the synthetic shift normalization of curvature into their components, which could produce more compact features. Finally, three different classifiers, i.e. support vector machine (SVM), hidden Markov model (HMM), and artificial neural network (ANN), are used to discriminate similar handwritten numerals for testing the effectiveness of the extracted features. Experimental results show that the proposed approach obtains higher recognition rates compared with the traditional algorithm for extracting features. © 2009 IEEE.

KW - Discrimination of handwritten numerals

KW - Empirical mode decomposition (EMD)

KW - Feature extraction

KW - Hilbert-Huang transform (HHT)

UR - http://www.scopus.com/inward/record.url?scp=70449338686&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2009.5212792

DO - 10.1109/ICMLC.2009.5212792

M3 - Conference paper (refereed)

SN - 9781424437023

SP - 3600

EP - 3605

BT - Proceedings of the 2009 International Conference on Machine Learning and Cybernetics

PB - IEEE

T2 - 2009 International Conference on Machine Learning and Cybernetics

Y2 - 12 July 2009 through 15 July 2009

ER -

An EMD-based recognition approach for similar handwritten numerals

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this