Character Region Extraction Algorithm from Scenery Images by Local and Parallel Processing

Satohi Iwakata, Masafumi Hagiwara, Yoshiaki Ajioka

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, we propose an algorithm extracting character domains from scenery images. This algorithm works under a severe constraint: each pixel in a processed image must be derived from only information of the neighboring pixels. This constraint is very important for a low cost device such as a mobile camera, because it makes possible to process each pixel in parallel. The proposed algorithm deals with color information based on physiological knowledge, and uses size of regions for judging whether a region is characters or not. The proposed algorithm is represented by local and parallel image processing and has been tested using 100 scenery images. The result shows that the proposed algorithm can extract character regions in a rate of more than 90%.

Original languageEnglish
Pages (from-to)959-965
Number of pages7
JournalIEEJ Transactions on Electronics, Information and Systems
Volume124
Issue number4
DOIs
Publication statusPublished - 2004

Fingerprint

Processing
Pixels
Image processing
Cameras
Color
Costs

Keywords

  • character extraction
  • local and parallel image processing
  • scenery image
  • support for sight-restricted people

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Character Region Extraction Algorithm from Scenery Images by Local and Parallel Processing. / Iwakata, Satohi; Hagiwara, Masafumi; Ajioka, Yoshiaki.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 124, No. 4, 2004, p. 959-965.

Research output: Contribution to journalArticle

@article{6cd1faba3d7240dcb934372ad3388526,
title = "Character Region Extraction Algorithm from Scenery Images by Local and Parallel Processing",
abstract = "In this paper, we propose an algorithm extracting character domains from scenery images. This algorithm works under a severe constraint: each pixel in a processed image must be derived from only information of the neighboring pixels. This constraint is very important for a low cost device such as a mobile camera, because it makes possible to process each pixel in parallel. The proposed algorithm deals with color information based on physiological knowledge, and uses size of regions for judging whether a region is characters or not. The proposed algorithm is represented by local and parallel image processing and has been tested using 100 scenery images. The result shows that the proposed algorithm can extract character regions in a rate of more than 90{\%}.",
keywords = "character extraction, local and parallel image processing, scenery image, support for sight-restricted people",
author = "Satohi Iwakata and Masafumi Hagiwara and Yoshiaki Ajioka",
year = "2004",
doi = "10.1541/ieejeiss.124.959",
language = "English",
volume = "124",
pages = "959--965",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "4",

}

TY - JOUR

T1 - Character Region Extraction Algorithm from Scenery Images by Local and Parallel Processing

AU - Iwakata, Satohi

AU - Hagiwara, Masafumi

AU - Ajioka, Yoshiaki

PY - 2004

Y1 - 2004

N2 - In this paper, we propose an algorithm extracting character domains from scenery images. This algorithm works under a severe constraint: each pixel in a processed image must be derived from only information of the neighboring pixels. This constraint is very important for a low cost device such as a mobile camera, because it makes possible to process each pixel in parallel. The proposed algorithm deals with color information based on physiological knowledge, and uses size of regions for judging whether a region is characters or not. The proposed algorithm is represented by local and parallel image processing and has been tested using 100 scenery images. The result shows that the proposed algorithm can extract character regions in a rate of more than 90%.

AB - In this paper, we propose an algorithm extracting character domains from scenery images. This algorithm works under a severe constraint: each pixel in a processed image must be derived from only information of the neighboring pixels. This constraint is very important for a low cost device such as a mobile camera, because it makes possible to process each pixel in parallel. The proposed algorithm deals with color information based on physiological knowledge, and uses size of regions for judging whether a region is characters or not. The proposed algorithm is represented by local and parallel image processing and has been tested using 100 scenery images. The result shows that the proposed algorithm can extract character regions in a rate of more than 90%.

KW - character extraction

KW - local and parallel image processing

KW - scenery image

KW - support for sight-restricted people

UR - http://www.scopus.com/inward/record.url?scp=21444455620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21444455620&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.124.959

DO - 10.1541/ieejeiss.124.959

M3 - Article

AN - SCOPUS:21444455620

VL - 124

SP - 959

EP - 965

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 4

ER -