A background-thinning based algorithm for separating connected handwritten digit strings

Zhongkang Lu; Zheru Chi; Pengfei Shi

doi:10.1109/ICASSP.1998.675452

A background-thinning based algorithm for separating connected handwritten digit strings

Zhongkang Lu, Zheru Chi, Pengfei Shi

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. A new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of the digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, these segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.4% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.

Original language	English
Title of host publication	Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Pages	1065-1068
Number of pages	4
Volume	2
DOIs	https://doi.org/10.1109/ICASSP.1998.675452
Publication status	Published - 1 Dec 1998
Event	1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 - Seattle, WA, United States Duration: 12 May 1998 → 15 May 1998

Conference

Conference	1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Country/Territory	United States
City	Seattle, WA
Period	12/05/98 → 15/05/98

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

More information

10.1109/ICASSP.1998.675452

Cite this

@inproceedings{b3bca3d921644336b25e002b57905d6b,

title = "A background-thinning based algorithm for separating connected handwritten digit strings",

abstract = "Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. A new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of the digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, these segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.4% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.",

author = "Zhongkang Lu and Zheru Chi and Pengfei Shi",

year = "1998",

month = dec,

day = "1",

doi = "10.1109/ICASSP.1998.675452",

language = "English",

isbn = "0780344286",

volume = "2",

pages = "1065--1068",

booktitle = "Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998",

note = "1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 ; Conference date: 12-05-1998 Through 15-05-1998",

}

Lu, Z, Chi, Z & Shi, P 1998, A background-thinning based algorithm for separating connected handwritten digit strings. in Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998. vol. 2, 675452, pp. 1065-1068, 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998, Seattle, WA, United States, 12/05/98. https://doi.org/10.1109/ICASSP.1998.675452

A background-thinning based algorithm for separating connected handwritten digit strings. / Lu, Zhongkang; Chi, Zheru; Shi, Pengfei.
Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998. Vol. 2 1998. p. 1065-1068 675452.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A background-thinning based algorithm for separating connected handwritten digit strings

AU - Lu, Zhongkang

AU - Chi, Zheru

AU - Shi, Pengfei

PY - 1998/12/1

Y1 - 1998/12/1

N2 - Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. A new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of the digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, these segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.4% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.

AB - Most algorithms for segmenting connected handwritten digit strings are based on the analysis of the foreground pixel distributions and the features on the upper/lower contours of the image. A new approach is presented to segment connected handwritten two-digit strings based on the thinning of background regions. The algorithm first locates several feature points on the background skeleton of the digit image. Possible segmentation paths are then constructed by matching these feature points. With geometric property measures, these segmentation paths are ranked using fuzzy rules generated from a decision-tree approach. Finally, the top ranked segmentation paths are tested one by one by an optimized nearest neighbor classifier until one of these candidates is accepted based on an acceptance criterion. Experimental results on NIST special database 3 show that our approach can achieve a correct classification rate of 92.4% with only 4.7% of digit strings rejected, which compares favorably with the other techniques tested.

UR - http://www.scopus.com/inward/record.url?scp=84892181731&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1998.675452

DO - 10.1109/ICASSP.1998.675452

M3 - Conference article published in proceeding or book

SN - 0780344286

SN - 9780780344280

VL - 2

SP - 1065

EP - 1068

BT - Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998

T2 - 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998

Y2 - 12 May 1998 through 15 May 1998

ER -

A background-thinning based algorithm for separating connected handwritten digit strings

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this