Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes

Han Wang, Zhihuo Xu, Hanseok Ko

Research output: Contribution to journalArticle

Abstract

This paper presents a new feature descriptor that is suitable for image matching under nonlinear intensity changes. The proposed approach consists of the following three steps. First, a binary local patch clustering transform response is employed as the transform space. The value of the new space exhibits a high similarity after changes in intensity. Then, a random binary pattern coding method extracts raw feature histograms from the new space. Finally, the discrimination of the proposed feature descriptor is enhanced by using a multiple spatial support region-based binning method. Experimental results show that the proposed method is able to provide a more robust image matching performance under nonlinear intensity changes.

Original languageEnglish
Article number6360741
JournalMathematical Problems in Engineering
Volume2018
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Image matching
Image Matching
Patch
Mathematical transformations
Clustering
Transform
Binary
Descriptors
Binning
Histogram
Discrimination
Coding
Experimental Results

ASJC Scopus subject areas

  • Mathematics(all)
  • Engineering(all)

Cite this

Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes. / Wang, Han; Xu, Zhihuo; Ko, Hanseok.

In: Mathematical Problems in Engineering, Vol. 2018, 6360741, 01.01.2018.

Research output: Contribution to journalArticle

@article{9ec0402f8a894749a624ae03ca59e255,
title = "Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes",
abstract = "This paper presents a new feature descriptor that is suitable for image matching under nonlinear intensity changes. The proposed approach consists of the following three steps. First, a binary local patch clustering transform response is employed as the transform space. The value of the new space exhibits a high similarity after changes in intensity. Then, a random binary pattern coding method extracts raw feature histograms from the new space. Finally, the discrimination of the proposed feature descriptor is enhanced by using a multiple spatial support region-based binning method. Experimental results show that the proposed method is able to provide a more robust image matching performance under nonlinear intensity changes.",
author = "Han Wang and Zhihuo Xu and Hanseok Ko",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/6360741",
language = "English",
volume = "2018",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes

AU - Wang, Han

AU - Xu, Zhihuo

AU - Ko, Hanseok

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper presents a new feature descriptor that is suitable for image matching under nonlinear intensity changes. The proposed approach consists of the following three steps. First, a binary local patch clustering transform response is employed as the transform space. The value of the new space exhibits a high similarity after changes in intensity. Then, a random binary pattern coding method extracts raw feature histograms from the new space. Finally, the discrimination of the proposed feature descriptor is enhanced by using a multiple spatial support region-based binning method. Experimental results show that the proposed method is able to provide a more robust image matching performance under nonlinear intensity changes.

AB - This paper presents a new feature descriptor that is suitable for image matching under nonlinear intensity changes. The proposed approach consists of the following three steps. First, a binary local patch clustering transform response is employed as the transform space. The value of the new space exhibits a high similarity after changes in intensity. Then, a random binary pattern coding method extracts raw feature histograms from the new space. Finally, the discrimination of the proposed feature descriptor is enhanced by using a multiple spatial support region-based binning method. Experimental results show that the proposed method is able to provide a more robust image matching performance under nonlinear intensity changes.

UR - http://www.scopus.com/inward/record.url?scp=85054360474&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054360474&partnerID=8YFLogxK

U2 - 10.1155/2018/6360741

DO - 10.1155/2018/6360741

M3 - Article

AN - SCOPUS:85054360474

VL - 2018

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 6360741

ER -