Combining SIFT and individual entropy correlation coefficient for image registration

Gan Liu*, Shengyong Chen, Xiaolong Zhou, Xiaoyan Wang, Qiu Guan, Hui Yu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

156 Downloads (Pure)

Abstract

Image registration is an important topic in many fields including industrial image analysis systems, medical and remote sensing. To improve the registration accuracy, an image registration method that combines scale invariant feature transform and individual entropy correlation coefficient (SIFTIECC) is proposed in this paper. First, scale invariant feature transform algorithm is applied to extract feature points to construct a transformation model. Then, a rough registration image is obtained according to the transformation model. The individual entropy correlation coefficient is used as the similarity measure to refine the rough registration image. Finally, the experimental results show the superior performance of the proposed SIFT-IECC registration method by comparing with the state-of-the-art methods.

Original languageEnglish
Title of host publicationPattern Recognition - 6th Chinese Conference, CCPR 2014, Proceedings, Part II
EditorsShutao Li, Chenglin Liu, Yaonan Wang
PublisherSpringer Verlag
Pages128-137
Number of pages10
Volume484
ISBN (Electronic)978-3662456422
DOIs
Publication statusPublished - Nov 2014
Event6th Chinese Conference on Pattern Recognition - Changsha, China
Duration: 17 Nov 201419 Nov 2014

Publication series

NameCommunications in Computer and Information Science
Volume484
ISSN (Print)1865-0929

Conference

Conference6th Chinese Conference on Pattern Recognition
Abbreviated titleCCPR 2014
Country/TerritoryChina
CityChangsha
Period17/11/1419/11/14

Keywords

  • image registration
  • individual entropy correlation coefficient
  • scale invariant feature transform

Fingerprint

Dive into the research topics of 'Combining SIFT and individual entropy correlation coefficient for image registration'. Together they form a unique fingerprint.

Cite this