Logo recognition system using angular radial transform descriptors

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Problem statement: The shape-based logo recognition systems have been developed to automate the logo registration process. The logo recognition operation faces many challenges such as having to recognize logos that might be scaled, rotated, translated and added with noises. Different types of logo's shapes further add to the complex nature of this problem. Approach: We developed a logo recognition system that comprises of three phases: Preprocessing, feature extraction and features matching. For feature extraction, we adopted a region-based Angular Radial Transform (ART) to extract the features from logo's shapes. We used the Euclidian Distance (ED) as a similarity measure parameter for the features matching. Results: We tested the system that used the ART as feature extraction method on a large logo database of 2730 images to investigate the effect of several deformations and noise on recognition performance. The experimental results showed the system that use the ART features was robust against the size changing, had an excellent discrimination power against different types of noises and good immunity to rotations. The performance evaluation results showed that ART technique perform better than Zernike moments and Invariant moment's techniques. Conclusion: The proposed ART descriptor was very effective to describe all types of logo's shapes independent on different types of deformations and noise. It also represented the logo's shapes in concise manner without information redundancy.

Original languageEnglish
Pages (from-to)1416-1422
Number of pages7
JournalJournal of Computer Science
Volume7
Issue number9
DOIs
Publication statusPublished - 2011

Fingerprint

Mathematical transformations
Feature extraction
Redundancy

Keywords

  • Affine moment invariant (AMI)
  • Angular Radial Transform (ART)
  • Complex-mark
  • Contour-based techniques
  • Device-mark
  • Euclidian Distance (ED)
  • Invariant moment (IM)
  • Logo recognition system
  • Region-based
  • Rotation angle
  • Zernike moments (ZM)

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Logo recognition system using angular radial transform descriptors. / Wahdan, Omar Mohammed; Omar, Khairuddin; Nasrudin, Mohammad Faidzul.

In: Journal of Computer Science, Vol. 7, No. 9, 2011, p. 1416-1422.

Research output: Contribution to journalArticle

@article{c747393b9244456ba2dc364b3a68b828,
title = "Logo recognition system using angular radial transform descriptors",
abstract = "Problem statement: The shape-based logo recognition systems have been developed to automate the logo registration process. The logo recognition operation faces many challenges such as having to recognize logos that might be scaled, rotated, translated and added with noises. Different types of logo's shapes further add to the complex nature of this problem. Approach: We developed a logo recognition system that comprises of three phases: Preprocessing, feature extraction and features matching. For feature extraction, we adopted a region-based Angular Radial Transform (ART) to extract the features from logo's shapes. We used the Euclidian Distance (ED) as a similarity measure parameter for the features matching. Results: We tested the system that used the ART as feature extraction method on a large logo database of 2730 images to investigate the effect of several deformations and noise on recognition performance. The experimental results showed the system that use the ART features was robust against the size changing, had an excellent discrimination power against different types of noises and good immunity to rotations. The performance evaluation results showed that ART technique perform better than Zernike moments and Invariant moment's techniques. Conclusion: The proposed ART descriptor was very effective to describe all types of logo's shapes independent on different types of deformations and noise. It also represented the logo's shapes in concise manner without information redundancy.",
keywords = "Affine moment invariant (AMI), Angular Radial Transform (ART), Complex-mark, Contour-based techniques, Device-mark, Euclidian Distance (ED), Invariant moment (IM), Logo recognition system, Region-based, Rotation angle, Zernike moments (ZM)",
author = "Wahdan, {Omar Mohammed} and Khairuddin Omar and Nasrudin, {Mohammad Faidzul}",
year = "2011",
doi = "10.3844/jcssp.2011.1416.1422",
language = "English",
volume = "7",
pages = "1416--1422",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "9",

}

TY - JOUR

T1 - Logo recognition system using angular radial transform descriptors

AU - Wahdan, Omar Mohammed

AU - Omar, Khairuddin

AU - Nasrudin, Mohammad Faidzul

PY - 2011

Y1 - 2011

N2 - Problem statement: The shape-based logo recognition systems have been developed to automate the logo registration process. The logo recognition operation faces many challenges such as having to recognize logos that might be scaled, rotated, translated and added with noises. Different types of logo's shapes further add to the complex nature of this problem. Approach: We developed a logo recognition system that comprises of three phases: Preprocessing, feature extraction and features matching. For feature extraction, we adopted a region-based Angular Radial Transform (ART) to extract the features from logo's shapes. We used the Euclidian Distance (ED) as a similarity measure parameter for the features matching. Results: We tested the system that used the ART as feature extraction method on a large logo database of 2730 images to investigate the effect of several deformations and noise on recognition performance. The experimental results showed the system that use the ART features was robust against the size changing, had an excellent discrimination power against different types of noises and good immunity to rotations. The performance evaluation results showed that ART technique perform better than Zernike moments and Invariant moment's techniques. Conclusion: The proposed ART descriptor was very effective to describe all types of logo's shapes independent on different types of deformations and noise. It also represented the logo's shapes in concise manner without information redundancy.

AB - Problem statement: The shape-based logo recognition systems have been developed to automate the logo registration process. The logo recognition operation faces many challenges such as having to recognize logos that might be scaled, rotated, translated and added with noises. Different types of logo's shapes further add to the complex nature of this problem. Approach: We developed a logo recognition system that comprises of three phases: Preprocessing, feature extraction and features matching. For feature extraction, we adopted a region-based Angular Radial Transform (ART) to extract the features from logo's shapes. We used the Euclidian Distance (ED) as a similarity measure parameter for the features matching. Results: We tested the system that used the ART as feature extraction method on a large logo database of 2730 images to investigate the effect of several deformations and noise on recognition performance. The experimental results showed the system that use the ART features was robust against the size changing, had an excellent discrimination power against different types of noises and good immunity to rotations. The performance evaluation results showed that ART technique perform better than Zernike moments and Invariant moment's techniques. Conclusion: The proposed ART descriptor was very effective to describe all types of logo's shapes independent on different types of deformations and noise. It also represented the logo's shapes in concise manner without information redundancy.

KW - Affine moment invariant (AMI)

KW - Angular Radial Transform (ART)

KW - Complex-mark

KW - Contour-based techniques

KW - Device-mark

KW - Euclidian Distance (ED)

KW - Invariant moment (IM)

KW - Logo recognition system

KW - Region-based

KW - Rotation angle

KW - Zernike moments (ZM)

UR - http://www.scopus.com/inward/record.url?scp=80053178970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053178970&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2011.1416.1422

DO - 10.3844/jcssp.2011.1416.1422

M3 - Article

AN - SCOPUS:80053178970

VL - 7

SP - 1416

EP - 1422

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 9

ER -