Skip to main navigation Skip to search Skip to main content

Improved maximum average correlation height filter with adaptive log base selection for object recognition

  • Sara Tehsin
  • , Saad Rehman
  • , Ahmad B. Awan
  • , Qaiser Chaudry
  • , Muhammad Abbas
  • , Rupert Young
  • , Afia Asif
  • National University of Sciences and Technology Pakistan
  • University of Sussex
  • Istanbul Sehir University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

23 Scopus citations

Abstract

Sensitivity to the variations in the reference image is a major concern when recognizing target objects. A combinational framework of correlation filters and logarithmic transformation has been previously reported to resolve this issue alongside catering for scale and rotation changes of the object in the presence of distortion and noise. In this paper, we have extended the work to include the influence of different logarithmic bases on the resultant correlation plane. The meaningful changes in correlation parameters along with contraction/expansion in the correlation plane peak have been identified under different scenarios. Based on our research, we propose some specific log bases to be used in logarithmically transformed correlation filters for achieving suitable tolerance to different variations. The study is based upon testing a range of logarithmic bases for different situations and finding an optimal logarithmic base for each particular set of distortions. Our results show improved correlation and target detection accuracies.

Original languageEnglish
Title of host publicationOptical Pattern Recognition XXVII
EditorsDavid Casasent, Mohammad S. Alam
PublisherSPIE
ISBN (Electronic)9781510600867
DOIs
StatePublished - 2016
Externally publishedYes
EventOptical Pattern Recognition XXVII - Baltimore, United States
Duration: 20 Apr 201621 Apr 2016

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9845
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceOptical Pattern Recognition XXVII
Country/TerritoryUnited States
CityBaltimore
Period20/04/1621/04/16

Keywords

  • Logarithmic mapping
  • correlation pattern recognition
  • maximum average correlation height
  • target detection

Fingerprint

Dive into the research topics of 'Improved maximum average correlation height filter with adaptive log base selection for object recognition'. Together they form a unique fingerprint.

Cite this