A new feature ranking method in a HMM-based handwriting recognition system

Sijun Kang; Venu Govindaraju

doi:10.1109/ICDAR.2005.22

A new feature ranking method in a HMM-based handwriting recognition system

Sijun Kang
, Venu Govindaraju

Research and Economic Development

SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper we propose a new feature ranking method in a recognition system, by introducing the concept of the effectiveness of the distinguishing power of features and considering the correlation among features. To find the subset of most important features, first the best feature can be identified by its effective distinguishing power and put in an empty feature set. Then each of the remaining features is ranked based on their effective distinguishing capacity contribution and the highest-ranked feature is added to the selected subset. This process is repeated till the performance of the system reaches its peak or the effective distinguishing contribution falls below a certain value. The application of this method to an existing handwriting recognition system showed strong support for our methodology of feature ranking.

Original language	English
Title of host publication	Proceedings of the Eighth International Conference on Document Analysis and Recognition
Pages	779-783
Number of pages	5
DOIs	https://doi.org/10.1109/ICDAR.2005.22
State	Published - 2005
Event	8th International Conference on Document Analysis and Recognition - Seoul, Korea, Republic of Duration: Aug 31 2005 → Sep 1 2005

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume	2005
ISSN (Print)	1520-5363

Conference

Conference	8th International Conference on Document Analysis and Recognition
Country/Territory	Korea, Republic of
City	Seoul
Period	08/31/05 → 09/1/05

Access to Document

10.1109/ICDAR.2005.22

Cite this

Kang, S., & Govindaraju, V. (2005). A new feature ranking method in a HMM-based handwriting recognition system. In Proceedings of the Eighth International Conference on Document Analysis and Recognition (pp. 779-783). Article 1575651 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005). https://doi.org/10.1109/ICDAR.2005.22

@inproceedings{ef1fb8de64f542c58f7d5a0ffda0a0e3,

title = "A new feature ranking method in a HMM-based handwriting recognition system",

abstract = "In this paper we propose a new feature ranking method in a recognition system, by introducing the concept of the effectiveness of the distinguishing power of features and considering the correlation among features. To find the subset of most important features, first the best feature can be identified by its effective distinguishing power and put in an empty feature set. Then each of the remaining features is ranked based on their effective distinguishing capacity contribution and the highest-ranked feature is added to the selected subset. This process is repeated till the performance of the system reaches its peak or the effective distinguishing contribution falls below a certain value. The application of this method to an existing handwriting recognition system showed strong support for our methodology of feature ranking.",

author = "Sijun Kang and Venu Govindaraju",

year = "2005",

doi = "10.1109/ICDAR.2005.22",

language = "English",

isbn = "0769524206",

series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

pages = "779--783",

booktitle = "Proceedings of the Eighth International Conference on Document Analysis and Recognition",

note = "8th International Conference on Document Analysis and Recognition ; Conference date: 31-08-2005 Through 01-09-2005",

}

Kang, S & Govindaraju, V 2005, A new feature ranking method in a HMM-based handwriting recognition system. in Proceedings of the Eighth International Conference on Document Analysis and Recognition., 1575651, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 2005, pp. 779-783, 8th International Conference on Document Analysis and Recognition, Seoul, Korea, Republic of, 08/31/05. https://doi.org/10.1109/ICDAR.2005.22

A new feature ranking method in a HMM-based handwriting recognition system. / Kang, Sijun; Govindaraju, Venu.
Proceedings of the Eighth International Conference on Document Analysis and Recognition. 2005. p. 779-783 1575651 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new feature ranking method in a HMM-based handwriting recognition system

AU - Kang, Sijun

AU - Govindaraju, Venu

PY - 2005

Y1 - 2005

N2 - In this paper we propose a new feature ranking method in a recognition system, by introducing the concept of the effectiveness of the distinguishing power of features and considering the correlation among features. To find the subset of most important features, first the best feature can be identified by its effective distinguishing power and put in an empty feature set. Then each of the remaining features is ranked based on their effective distinguishing capacity contribution and the highest-ranked feature is added to the selected subset. This process is repeated till the performance of the system reaches its peak or the effective distinguishing contribution falls below a certain value. The application of this method to an existing handwriting recognition system showed strong support for our methodology of feature ranking.

AB - In this paper we propose a new feature ranking method in a recognition system, by introducing the concept of the effectiveness of the distinguishing power of features and considering the correlation among features. To find the subset of most important features, first the best feature can be identified by its effective distinguishing power and put in an empty feature set. Then each of the remaining features is ranked based on their effective distinguishing capacity contribution and the highest-ranked feature is added to the selected subset. This process is repeated till the performance of the system reaches its peak or the effective distinguishing contribution falls below a certain value. The application of this method to an existing handwriting recognition system showed strong support for our methodology of feature ranking.

UR - https://www.scopus.com/pages/publications/33947374732

U2 - 10.1109/ICDAR.2005.22

DO - 10.1109/ICDAR.2005.22

M3 - Conference contribution

AN - SCOPUS:33947374732

SN - 0769524206

SN - 9780769524207

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 779

EP - 783

BT - Proceedings of the Eighth International Conference on Document Analysis and Recognition

T2 - 8th International Conference on Document Analysis and Recognition

Y2 - 31 August 2005 through 1 September 2005

ER -

A new feature ranking method in a HMM-based handwriting recognition system

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this