Enhancement of SURF performance through masked grey world approach

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved the SURF matching performance. The algorithm can be implemented as the tracking input to the system that requires robust observation between the frames.

Original languageEnglish
Pages (from-to)3911-3919
Number of pages9
JournalJournal of Computational Information Systems
Volume8
Issue number9
Publication statusPublished - 1 May 2012

Fingerprint

Detectors
Lighting
Color

Keywords

  • Colour constancy
  • Gaussian modelling
  • Key-point detector
  • Masked grey world
  • Neyman-pearson hypothesis testing
  • SURF

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

@article{a2c07e235d91420ea80a49d7acc0ae5d,
title = "Enhancement of SURF performance through masked grey world approach",
abstract = "Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved the SURF matching performance. The algorithm can be implemented as the tracking input to the system that requires robust observation between the frames.",
keywords = "Colour constancy, Gaussian modelling, Key-point detector, Masked grey world, Neyman-pearson hypothesis testing, SURF",
author = "Zulkifley, {Mohd Asyraf} and {Wan Zaki}, {Wan Mimi Diyana} and Aini Hussain and Mustafa, {Mohd. Marzuki}",
year = "2012",
month = "5",
day = "1",
language = "English",
volume = "8",
pages = "3911--3919",
journal = "Journal of Computational Information Systems",
issn = "1553-9105",
publisher = "Binary Information Press",
number = "9",

}

TY - JOUR

T1 - Enhancement of SURF performance through masked grey world approach

AU - Zulkifley, Mohd Asyraf

AU - Wan Zaki, Wan Mimi Diyana

AU - Hussain, Aini

AU - Mustafa, Mohd. Marzuki

PY - 2012/5/1

Y1 - 2012/5/1

N2 - Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved the SURF matching performance. The algorithm can be implemented as the tracking input to the system that requires robust observation between the frames.

AB - Colour constancy concerns about the transformation of input image into a canonical form. We approach the constancy issue by applying masked grey world algorithm to the SURF detector. The aim is to produce a robust feature detector that is invariant to sudden as well as gradual illumination change. We have analyzed the algorithm with various types of object surfaces, including minimal, dielectric, metallic specularity and fluorescent surface. The results show that regardless of the surface type, masked grey world have improved the SURF matching performance. The algorithm can be implemented as the tracking input to the system that requires robust observation between the frames.

KW - Colour constancy

KW - Gaussian modelling

KW - Key-point detector

KW - Masked grey world

KW - Neyman-pearson hypothesis testing

KW - SURF

UR - http://www.scopus.com/inward/record.url?scp=84862645533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862645533&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84862645533

VL - 8

SP - 3911

EP - 3919

JO - Journal of Computational Information Systems

JF - Journal of Computational Information Systems

SN - 1553-9105

IS - 9

ER -