Automatic text recognition in natural scene using neural network classifier with dynamic-group-based hybrid particle swarm optimization

Tang Kuang-Hui, Chuan-Kuei Huang, Lin Cheng-Jian

Research output: Contribution to journalArticle

Abstract

This paper presents a two-stage algorithm for automatic text detection and recognition. In the first stage, using a stroke width transform and an improved connected component, an edge analysis method detects a candidate character region. Subsequently, a text region is located by filtering and linking characters with similar font sizes and colors. For the second stage, a histogram of oriented gradient is employed as a feature descriptor, and a neural network classifier is built with dynamic-group-based hybrid particle swarm optimization (DGHPSO) for character recognition. In DGHPSO, each group's threshold value of similarity depends on the threshold values of fitness and distance. In addition, a local search algorithm is used to improve the search for a global optimum. The proposed algorithm was experimentally validated; it outperformed a number of recently published studies in terms of the text recognition rate when tested on the ICDAR 2003 database and the Street View Text database.

Original languageEnglish
Pages (from-to)555-575
Number of pages21
JournalJournal of Information Science and Engineering
Volume35
Issue number3
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

group dynamics
neural network
Particle swarm optimization (PSO)
Classifiers
Neural networks
Character recognition
stroke
fitness
Color
candidacy
Group

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Library and Information Sciences
  • Computational Theory and Mathematics

Cite this

@article{ebcc11eeaffa46e5a5c2c87dc1b3d5a5,
title = "Automatic text recognition in natural scene using neural network classifier with dynamic-group-based hybrid particle swarm optimization",
abstract = "This paper presents a two-stage algorithm for automatic text detection and recognition. In the first stage, using a stroke width transform and an improved connected component, an edge analysis method detects a candidate character region. Subsequently, a text region is located by filtering and linking characters with similar font sizes and colors. For the second stage, a histogram of oriented gradient is employed as a feature descriptor, and a neural network classifier is built with dynamic-group-based hybrid particle swarm optimization (DGHPSO) for character recognition. In DGHPSO, each group's threshold value of similarity depends on the threshold values of fitness and distance. In addition, a local search algorithm is used to improve the search for a global optimum. The proposed algorithm was experimentally validated; it outperformed a number of recently published studies in terms of the text recognition rate when tested on the ICDAR 2003 database and the Street View Text database.",
author = "Tang Kuang-Hui and Chuan-Kuei Huang and Lin Cheng-Jian",
year = "2019",
month = "1",
day = "1",
doi = "10.6688/JISE.201905_35(3).0005",
language = "English",
volume = "35",
pages = "555--575",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "3",

}

Automatic text recognition in natural scene using neural network classifier with dynamic-group-based hybrid particle swarm optimization. / Kuang-Hui, Tang; Huang, Chuan-Kuei; Cheng-Jian, Lin.

In: Journal of Information Science and Engineering, Vol. 35, No. 3, 01.01.2019, p. 555-575.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic text recognition in natural scene using neural network classifier with dynamic-group-based hybrid particle swarm optimization

AU - Kuang-Hui, Tang

AU - Huang, Chuan-Kuei

AU - Cheng-Jian, Lin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper presents a two-stage algorithm for automatic text detection and recognition. In the first stage, using a stroke width transform and an improved connected component, an edge analysis method detects a candidate character region. Subsequently, a text region is located by filtering and linking characters with similar font sizes and colors. For the second stage, a histogram of oriented gradient is employed as a feature descriptor, and a neural network classifier is built with dynamic-group-based hybrid particle swarm optimization (DGHPSO) for character recognition. In DGHPSO, each group's threshold value of similarity depends on the threshold values of fitness and distance. In addition, a local search algorithm is used to improve the search for a global optimum. The proposed algorithm was experimentally validated; it outperformed a number of recently published studies in terms of the text recognition rate when tested on the ICDAR 2003 database and the Street View Text database.

AB - This paper presents a two-stage algorithm for automatic text detection and recognition. In the first stage, using a stroke width transform and an improved connected component, an edge analysis method detects a candidate character region. Subsequently, a text region is located by filtering and linking characters with similar font sizes and colors. For the second stage, a histogram of oriented gradient is employed as a feature descriptor, and a neural network classifier is built with dynamic-group-based hybrid particle swarm optimization (DGHPSO) for character recognition. In DGHPSO, each group's threshold value of similarity depends on the threshold values of fitness and distance. In addition, a local search algorithm is used to improve the search for a global optimum. The proposed algorithm was experimentally validated; it outperformed a number of recently published studies in terms of the text recognition rate when tested on the ICDAR 2003 database and the Street View Text database.

UR - http://www.scopus.com/inward/record.url?scp=85065637423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065637423&partnerID=8YFLogxK

U2 - 10.6688/JISE.201905_35(3).0005

DO - 10.6688/JISE.201905_35(3).0005

M3 - Article

VL - 35

SP - 555

EP - 575

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 3

ER -