Keyword Extraction and Search Technique Using Transformation Angle Estimation to Candidate Character Set in Scene Image

Akira Suzuki, Shingo Ando, Satoshi Shimada, Shunichi Yonemura

Research output: Contribution to journalArticle

Abstract

This paper proposes an image search technology that processes character candidate sets by scanning scene images containing character strings such as signboard messages with a recognition dictionary. First, it extracts keywords composed of characters that are regularly aligned in the image by matching the word dictionary to the candidate character set. It then uses the user-input keywords in performing image search. We assume that the principal use of this technology is to retrieve images from data sets held by the user. The proposed technology has the feature that it can extract character strings even if they consist of shaded, three-dimensional characters, lie on a complex background, and are inclined, etc., attributes that cannot be offered by existing character recognition schemes for scene images. To overcome the problem of the background triggering the erroneous recognition of characters, we estimate the transformation angles of the candidate character from angular distributions of the gradient vector of pertinent areas, and add it to the limiting conditions used in determining the arrangement of character strings in the matching against the word dictionary process. Experiments on keyword extraction and image retrieval show that the proposed technology has practical performance in the application assumed, and that its estimation of the transformation angle of candidate characters is effective in decreasing keyword extraction errors.

Original languageEnglish
Pages (from-to)386-398
Number of pages13
JournalJournal of the Institute of Image Electronics Engineers of Japan
Volume39
Issue number4
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

Character sets
Glossaries
Character recognition
Angular distribution
Image retrieval
Scanning
Experiments

Keywords

  • character recognition in scene image
  • estimation of transformation angles
  • image retrieval
  • word dictionary

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

Keyword Extraction and Search Technique Using Transformation Angle Estimation to Candidate Character Set in Scene Image. / Suzuki, Akira; Ando, Shingo; Shimada, Satoshi; Yonemura, Shunichi.

In: Journal of the Institute of Image Electronics Engineers of Japan, Vol. 39, No. 4, 2010, p. 386-398.

Research output: Contribution to journalArticle

@article{ff7a9633e58f488ebbdb0c0c125f4fda,
title = "Keyword Extraction and Search Technique Using Transformation Angle Estimation to Candidate Character Set in Scene Image",
abstract = "This paper proposes an image search technology that processes character candidate sets by scanning scene images containing character strings such as signboard messages with a recognition dictionary. First, it extracts keywords composed of characters that are regularly aligned in the image by matching the word dictionary to the candidate character set. It then uses the user-input keywords in performing image search. We assume that the principal use of this technology is to retrieve images from data sets held by the user. The proposed technology has the feature that it can extract character strings even if they consist of shaded, three-dimensional characters, lie on a complex background, and are inclined, etc., attributes that cannot be offered by existing character recognition schemes for scene images. To overcome the problem of the background triggering the erroneous recognition of characters, we estimate the transformation angles of the candidate character from angular distributions of the gradient vector of pertinent areas, and add it to the limiting conditions used in determining the arrangement of character strings in the matching against the word dictionary process. Experiments on keyword extraction and image retrieval show that the proposed technology has practical performance in the application assumed, and that its estimation of the transformation angle of candidate characters is effective in decreasing keyword extraction errors.",
keywords = "character recognition in scene image, estimation of transformation angles, image retrieval, word dictionary",
author = "Akira Suzuki and Shingo Ando and Satoshi Shimada and Shunichi Yonemura",
year = "2010",
doi = "10.11371/iieej.39.386",
language = "English",
volume = "39",
pages = "386--398",
journal = "Journal of the Institute of Image Electronics Engineers of Japan",
issn = "0285-9831",
publisher = "Institute of Image Electronics Engineers of Japan",
number = "4",

}

TY - JOUR

T1 - Keyword Extraction and Search Technique Using Transformation Angle Estimation to Candidate Character Set in Scene Image

AU - Suzuki, Akira

AU - Ando, Shingo

AU - Shimada, Satoshi

AU - Yonemura, Shunichi

PY - 2010

Y1 - 2010

N2 - This paper proposes an image search technology that processes character candidate sets by scanning scene images containing character strings such as signboard messages with a recognition dictionary. First, it extracts keywords composed of characters that are regularly aligned in the image by matching the word dictionary to the candidate character set. It then uses the user-input keywords in performing image search. We assume that the principal use of this technology is to retrieve images from data sets held by the user. The proposed technology has the feature that it can extract character strings even if they consist of shaded, three-dimensional characters, lie on a complex background, and are inclined, etc., attributes that cannot be offered by existing character recognition schemes for scene images. To overcome the problem of the background triggering the erroneous recognition of characters, we estimate the transformation angles of the candidate character from angular distributions of the gradient vector of pertinent areas, and add it to the limiting conditions used in determining the arrangement of character strings in the matching against the word dictionary process. Experiments on keyword extraction and image retrieval show that the proposed technology has practical performance in the application assumed, and that its estimation of the transformation angle of candidate characters is effective in decreasing keyword extraction errors.

AB - This paper proposes an image search technology that processes character candidate sets by scanning scene images containing character strings such as signboard messages with a recognition dictionary. First, it extracts keywords composed of characters that are regularly aligned in the image by matching the word dictionary to the candidate character set. It then uses the user-input keywords in performing image search. We assume that the principal use of this technology is to retrieve images from data sets held by the user. The proposed technology has the feature that it can extract character strings even if they consist of shaded, three-dimensional characters, lie on a complex background, and are inclined, etc., attributes that cannot be offered by existing character recognition schemes for scene images. To overcome the problem of the background triggering the erroneous recognition of characters, we estimate the transformation angles of the candidate character from angular distributions of the gradient vector of pertinent areas, and add it to the limiting conditions used in determining the arrangement of character strings in the matching against the word dictionary process. Experiments on keyword extraction and image retrieval show that the proposed technology has practical performance in the application assumed, and that its estimation of the transformation angle of candidate characters is effective in decreasing keyword extraction errors.

KW - character recognition in scene image

KW - estimation of transformation angles

KW - image retrieval

KW - word dictionary

UR - http://www.scopus.com/inward/record.url?scp=85024726874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024726874&partnerID=8YFLogxK

U2 - 10.11371/iieej.39.386

DO - 10.11371/iieej.39.386

M3 - Article

AN - SCOPUS:85024726874

VL - 39

SP - 386

EP - 398

JO - Journal of the Institute of Image Electronics Engineers of Japan

JF - Journal of the Institute of Image Electronics Engineers of Japan

SN - 0285-9831

IS - 4

ER -