Image Color Registration for Illumination-Robust Pattern Recognition

Ukil Yang, Minsung Kang, Jongin Son, Kwanghoon Sohn

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Image-based pattern recognition techniques have attracted much attention in vision-based applications. Color-based methods have shown several benefits. However, due to color variations resulting from illumination changes, many color-based techniques have yet to demonstrate stable performance. For illumination-robust pattern recognition, we propose an image color registration method based on an image acquisition model. Since the image acquisition model is created using the variables related to an illumination condition, camera characteristics, and an object’s surface reflectance, the proposed method normalizes the image’s color by taking into account both the illumination and camera characteristics. To evaluate the performance of the proposed method in terms of illumination-robust pattern recognition, we perform both an image similarity test and a feature similarity test between images acquired under different illumination conditions. Through the experiments, the superiority and the usefulness of the proposed method was validated.

Original languageEnglish
Pages (from-to)3839-3860
Number of pages22
JournalCircuits, Systems, and Signal Processing
Volume33
Issue number12
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Color Image
Registration
Pattern Recognition
Pattern recognition
Illumination
Lighting
Color
Image Acquisition
Image acquisition
Camera
Cameras
Normalize
Reflectance
Evaluate
Model
Demonstrate
Experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Applied Mathematics

Cite this

Yang, Ukil ; Kang, Minsung ; Son, Jongin ; Sohn, Kwanghoon. / Image Color Registration for Illumination-Robust Pattern Recognition. In: Circuits, Systems, and Signal Processing. 2014 ; Vol. 33, No. 12. pp. 3839-3860.
@article{ed96f2004fbe48b2a77177f79aa04a5c,
title = "Image Color Registration for Illumination-Robust Pattern Recognition",
abstract = "Image-based pattern recognition techniques have attracted much attention in vision-based applications. Color-based methods have shown several benefits. However, due to color variations resulting from illumination changes, many color-based techniques have yet to demonstrate stable performance. For illumination-robust pattern recognition, we propose an image color registration method based on an image acquisition model. Since the image acquisition model is created using the variables related to an illumination condition, camera characteristics, and an object’s surface reflectance, the proposed method normalizes the image’s color by taking into account both the illumination and camera characteristics. To evaluate the performance of the proposed method in terms of illumination-robust pattern recognition, we perform both an image similarity test and a feature similarity test between images acquired under different illumination conditions. Through the experiments, the superiority and the usefulness of the proposed method was validated.",
author = "Ukil Yang and Minsung Kang and Jongin Son and Kwanghoon Sohn",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s00034-014-9819-0",
language = "English",
volume = "33",
pages = "3839--3860",
journal = "Circuits, Systems, and Signal Processing",
issn = "0278-081X",
publisher = "Birkhause Boston",
number = "12",

}

Image Color Registration for Illumination-Robust Pattern Recognition. / Yang, Ukil; Kang, Minsung; Son, Jongin; Sohn, Kwanghoon.

In: Circuits, Systems, and Signal Processing, Vol. 33, No. 12, 01.01.2014, p. 3839-3860.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Image Color Registration for Illumination-Robust Pattern Recognition

AU - Yang, Ukil

AU - Kang, Minsung

AU - Son, Jongin

AU - Sohn, Kwanghoon

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Image-based pattern recognition techniques have attracted much attention in vision-based applications. Color-based methods have shown several benefits. However, due to color variations resulting from illumination changes, many color-based techniques have yet to demonstrate stable performance. For illumination-robust pattern recognition, we propose an image color registration method based on an image acquisition model. Since the image acquisition model is created using the variables related to an illumination condition, camera characteristics, and an object’s surface reflectance, the proposed method normalizes the image’s color by taking into account both the illumination and camera characteristics. To evaluate the performance of the proposed method in terms of illumination-robust pattern recognition, we perform both an image similarity test and a feature similarity test between images acquired under different illumination conditions. Through the experiments, the superiority and the usefulness of the proposed method was validated.

AB - Image-based pattern recognition techniques have attracted much attention in vision-based applications. Color-based methods have shown several benefits. However, due to color variations resulting from illumination changes, many color-based techniques have yet to demonstrate stable performance. For illumination-robust pattern recognition, we propose an image color registration method based on an image acquisition model. Since the image acquisition model is created using the variables related to an illumination condition, camera characteristics, and an object’s surface reflectance, the proposed method normalizes the image’s color by taking into account both the illumination and camera characteristics. To evaluate the performance of the proposed method in terms of illumination-robust pattern recognition, we perform both an image similarity test and a feature similarity test between images acquired under different illumination conditions. Through the experiments, the superiority and the usefulness of the proposed method was validated.

UR - http://www.scopus.com/inward/record.url?scp=84920945880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920945880&partnerID=8YFLogxK

U2 - 10.1007/s00034-014-9819-0

DO - 10.1007/s00034-014-9819-0

M3 - Article

VL - 33

SP - 3839

EP - 3860

JO - Circuits, Systems, and Signal Processing

JF - Circuits, Systems, and Signal Processing

SN - 0278-081X

IS - 12

ER -