A feature descriptor based on the local patch clustering distribution for illumination-robust image matching

Han Wang, Sang Min Yoon, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This paper proposes a feature descriptor based on the local patch clustering distribution (LPCD), which preserves the salient features of a given image following changes in illumination. To mitigate the effects of illumination change, the proposed LPCD methodology consists of two steps. First, a local patch clustering assignment map is constructed by pairing the source image with a reference image. To resolve the quantization problem caused by an illumination change, a dual-codebook clustering method is employed so that an effective local patch clustering feature space can be constructed. Second, in the feature encoding process, the impact of the informative local patches that contain textural information is enhanced when using a saliency detection response as a method of weighting every local patch when the histogram feature is extracted. Experimental results show that the proposed local patch clustering space is more robust than the conventional intensity order-based space in response to changes in illumination.

Original languageEnglish
Pages (from-to)46-54
Number of pages9
JournalPattern Recognition Letters
Volume94
DOIs
Publication statusPublished - 2017 Jul 15

Fingerprint

Image matching
Lighting

Keywords

  • Feature descriptor illumination change
  • Image matching
  • Local patch clustering distribution

ASJC Scopus subject areas

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

Cite this

A feature descriptor based on the local patch clustering distribution for illumination-robust image matching. / Wang, Han; Yoon, Sang Min; Han, David K.; Ko, Hanseok.

In: Pattern Recognition Letters, Vol. 94, 15.07.2017, p. 46-54.

Research output: Contribution to journalArticle

@article{f484eb3205f9418b9bf8cf8bf9727628,
title = "A feature descriptor based on the local patch clustering distribution for illumination-robust image matching",
abstract = "This paper proposes a feature descriptor based on the local patch clustering distribution (LPCD), which preserves the salient features of a given image following changes in illumination. To mitigate the effects of illumination change, the proposed LPCD methodology consists of two steps. First, a local patch clustering assignment map is constructed by pairing the source image with a reference image. To resolve the quantization problem caused by an illumination change, a dual-codebook clustering method is employed so that an effective local patch clustering feature space can be constructed. Second, in the feature encoding process, the impact of the informative local patches that contain textural information is enhanced when using a saliency detection response as a method of weighting every local patch when the histogram feature is extracted. Experimental results show that the proposed local patch clustering space is more robust than the conventional intensity order-based space in response to changes in illumination.",
keywords = "Feature descriptor illumination change, Image matching, Local patch clustering distribution",
author = "Han Wang and Yoon, {Sang Min} and Han, {David K.} and Hanseok Ko",
year = "2017",
month = "7",
day = "15",
doi = "10.1016/j.patrec.2017.05.010",
language = "English",
volume = "94",
pages = "46--54",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - A feature descriptor based on the local patch clustering distribution for illumination-robust image matching

AU - Wang, Han

AU - Yoon, Sang Min

AU - Han, David K.

AU - Ko, Hanseok

PY - 2017/7/15

Y1 - 2017/7/15

N2 - This paper proposes a feature descriptor based on the local patch clustering distribution (LPCD), which preserves the salient features of a given image following changes in illumination. To mitigate the effects of illumination change, the proposed LPCD methodology consists of two steps. First, a local patch clustering assignment map is constructed by pairing the source image with a reference image. To resolve the quantization problem caused by an illumination change, a dual-codebook clustering method is employed so that an effective local patch clustering feature space can be constructed. Second, in the feature encoding process, the impact of the informative local patches that contain textural information is enhanced when using a saliency detection response as a method of weighting every local patch when the histogram feature is extracted. Experimental results show that the proposed local patch clustering space is more robust than the conventional intensity order-based space in response to changes in illumination.

AB - This paper proposes a feature descriptor based on the local patch clustering distribution (LPCD), which preserves the salient features of a given image following changes in illumination. To mitigate the effects of illumination change, the proposed LPCD methodology consists of two steps. First, a local patch clustering assignment map is constructed by pairing the source image with a reference image. To resolve the quantization problem caused by an illumination change, a dual-codebook clustering method is employed so that an effective local patch clustering feature space can be constructed. Second, in the feature encoding process, the impact of the informative local patches that contain textural information is enhanced when using a saliency detection response as a method of weighting every local patch when the histogram feature is extracted. Experimental results show that the proposed local patch clustering space is more robust than the conventional intensity order-based space in response to changes in illumination.

KW - Feature descriptor illumination change

KW - Image matching

KW - Local patch clustering distribution

UR - http://www.scopus.com/inward/record.url?scp=85019749898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019749898&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2017.05.010

DO - 10.1016/j.patrec.2017.05.010

M3 - Article

AN - SCOPUS:85019749898

VL - 94

SP - 46

EP - 54

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -