Exact order based feature descriptor for illumination robust image matching

Bongjoe Kim, Hunjae Yoo, Kwanghoon Sohn

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

We present a novel method for a feature descriptor called an exact order based descriptor (EOD). The proposed method consists of three steps. First, to resolve ordering ambiguity for pixels of the same intensity, an exact order image is created by changing the discrete intensity into a k-dimensional continuous value. Second, exact order based features are generated globally and locally. Finally, the EOD is constructed by combining the global and local exact order features using the discrete cosine transform. Experimental results show that the proposed method outperforms other state-of-the-art descriptors over a number of images.

Original languageEnglish
Pages (from-to)3268-3278
Number of pages11
JournalPattern Recognition
Volume46
Issue number12
DOIs
Publication statusPublished - 2013 Dec 1

Fingerprint

Image matching
Discrete cosine transforms
Lighting
Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Kim, Bongjoe ; Yoo, Hunjae ; Sohn, Kwanghoon. / Exact order based feature descriptor for illumination robust image matching. In: Pattern Recognition. 2013 ; Vol. 46, No. 12. pp. 3268-3278.
@article{7280a48edfc743f9a42a8de402090e80,
title = "Exact order based feature descriptor for illumination robust image matching",
abstract = "We present a novel method for a feature descriptor called an exact order based descriptor (EOD). The proposed method consists of three steps. First, to resolve ordering ambiguity for pixels of the same intensity, an exact order image is created by changing the discrete intensity into a k-dimensional continuous value. Second, exact order based features are generated globally and locally. Finally, the EOD is constructed by combining the global and local exact order features using the discrete cosine transform. Experimental results show that the proposed method outperforms other state-of-the-art descriptors over a number of images.",
author = "Bongjoe Kim and Hunjae Yoo and Kwanghoon Sohn",
year = "2013",
month = "12",
day = "1",
doi = "10.1016/j.patcog.2013.04.015",
language = "English",
volume = "46",
pages = "3268--3278",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "12",

}

Exact order based feature descriptor for illumination robust image matching. / Kim, Bongjoe; Yoo, Hunjae; Sohn, Kwanghoon.

In: Pattern Recognition, Vol. 46, No. 12, 01.12.2013, p. 3268-3278.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exact order based feature descriptor for illumination robust image matching

AU - Kim, Bongjoe

AU - Yoo, Hunjae

AU - Sohn, Kwanghoon

PY - 2013/12/1

Y1 - 2013/12/1

N2 - We present a novel method for a feature descriptor called an exact order based descriptor (EOD). The proposed method consists of three steps. First, to resolve ordering ambiguity for pixels of the same intensity, an exact order image is created by changing the discrete intensity into a k-dimensional continuous value. Second, exact order based features are generated globally and locally. Finally, the EOD is constructed by combining the global and local exact order features using the discrete cosine transform. Experimental results show that the proposed method outperforms other state-of-the-art descriptors over a number of images.

AB - We present a novel method for a feature descriptor called an exact order based descriptor (EOD). The proposed method consists of three steps. First, to resolve ordering ambiguity for pixels of the same intensity, an exact order image is created by changing the discrete intensity into a k-dimensional continuous value. Second, exact order based features are generated globally and locally. Finally, the EOD is constructed by combining the global and local exact order features using the discrete cosine transform. Experimental results show that the proposed method outperforms other state-of-the-art descriptors over a number of images.

UR - http://www.scopus.com/inward/record.url?scp=84881055611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881055611&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2013.04.015

DO - 10.1016/j.patcog.2013.04.015

M3 - Article

VL - 46

SP - 3268

EP - 3278

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 12

ER -