An approach to matching partial word image and its application to document image retrieval

Yue Lu; Chew Lim Tan; Lin Lin

doi:10.1117/12.483240

An approach to matching partial word image and its application to document image retrieval

Yue Lu, Chew Lim Tan, Lin Lin

National University of Singapore

Research output: Contribution to journal › Conference article › peer-review

Abstract

An approach with the capability of matching partial word image is proposed in this paper, to facilitate the issues of document image retrieval, such as detection of user-specified query words, and similarity measurement between documents. Each word image is represented by a feature string. Then, an inexact string matching technology is utilized to measure the similarity between the two feature strings generated from two word images, based on which we can estimate how one word image is relevant to the other one and thereby decide whether one is a portion of the other word. The approach is applied to two issues in the area of document information retrieval: word spotting and document similarity measurement. Experimental results on real document images show that it is a promising approach.

Original language	English
Pages (from-to)	379-387
Number of pages	9
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4929
DOIs	https://doi.org/10.1117/12.483240
State	Published - 16 Sep 2002
Externally published	Yes
Event	Optical Information Processing Technology 2002 - Shanghai, China Duration: 14 Oct 2002 → 18 Oct 2002

Keywords

Document image analysis
Document similarity measurement
Inexact matching
Information retrieval
Word image matching
Word spotting

Access to Document

10.1117/12.483240

Cite this

@article{ea67b74d4b2342788453d517ed684003,

title = "An approach to matching partial word image and its application to document image retrieval",

abstract = "An approach with the capability of matching partial word image is proposed in this paper, to facilitate the issues of document image retrieval, such as detection of user-specified query words, and similarity measurement between documents. Each word image is represented by a feature string. Then, an inexact string matching technology is utilized to measure the similarity between the two feature strings generated from two word images, based on which we can estimate how one word image is relevant to the other one and thereby decide whether one is a portion of the other word. The approach is applied to two issues in the area of document information retrieval: word spotting and document similarity measurement. Experimental results on real document images show that it is a promising approach.",

keywords = "Document image analysis, Document similarity measurement, Inexact matching, Information retrieval, Word image matching, Word spotting",

author = "Yue Lu and Tan, \{Chew Lim\} and Lin Lin",

note = "Publisher Copyright: {\textcopyright} 2002 SPIE.; Optical Information Processing Technology 2002 ; Conference date: 14-10-2002 Through 18-10-2002",

year = "2002",

month = sep,

day = "16",

doi = "10.1117/12.483240",

language = "英语",

volume = "4929",

pages = "379--387",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - An approach to matching partial word image and its application to document image retrieval

AU - Lu, Yue

AU - Tan, Chew Lim

AU - Lin, Lin

PY - 2002/9/16

Y1 - 2002/9/16

N2 - An approach with the capability of matching partial word image is proposed in this paper, to facilitate the issues of document image retrieval, such as detection of user-specified query words, and similarity measurement between documents. Each word image is represented by a feature string. Then, an inexact string matching technology is utilized to measure the similarity between the two feature strings generated from two word images, based on which we can estimate how one word image is relevant to the other one and thereby decide whether one is a portion of the other word. The approach is applied to two issues in the area of document information retrieval: word spotting and document similarity measurement. Experimental results on real document images show that it is a promising approach.

AB - An approach with the capability of matching partial word image is proposed in this paper, to facilitate the issues of document image retrieval, such as detection of user-specified query words, and similarity measurement between documents. Each word image is represented by a feature string. Then, an inexact string matching technology is utilized to measure the similarity between the two feature strings generated from two word images, based on which we can estimate how one word image is relevant to the other one and thereby decide whether one is a portion of the other word. The approach is applied to two issues in the area of document information retrieval: word spotting and document similarity measurement. Experimental results on real document images show that it is a promising approach.

KW - Document image analysis

KW - Document similarity measurement

KW - Inexact matching

KW - Information retrieval

KW - Word image matching

KW - Word spotting

UR - https://www.scopus.com/pages/publications/85076820241

U2 - 10.1117/12.483240

DO - 10.1117/12.483240

M3 - 会议文章

AN - SCOPUS:85076820241

SN - 0277-786X

VL - 4929

SP - 379

EP - 387

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Optical Information Processing Technology 2002

Y2 - 14 October 2002 through 18 October 2002

ER -

An approach to matching partial word image and its application to document image retrieval

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this