Using linear Kernel entropy component analysis as a feature extraction method in face recognition in video surveillance systems

Sepehr Damavandinejadmonfared*, Sina Ashooritootkaboni, Taha Bahraminezhad Jooneghani

*Corresponding author for this work

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

Abstract

Kernel Entropy Component Analysis (KECA) is one of the latest improvements on Principal Component Analysis (PCA) and also Kernel Principal Component Analysis (KPCA). As KECA is actually an extend of KPCA, different types of KPCA can be used in this method. In this paper the performance of four different types of Kernel Entropy Component Analysis (Linear, Polynomial, Gaussian, and Sigmoid) on Surveillance Camera Face database and also Head Pose Image database is observed in order to prove that Linear Kernel Entropy Component Analysis is the most appropriate method in terms of video surveillance.

Original languageEnglish
Title of host publicationProceedings of the 2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
Pages1163-1166
Number of pages4
Volume2
Publication statusPublished - 2012
Externally publishedYes
Event2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012 - Las Vegas, NV, United States
Duration: 16 Jul 201219 Jul 2012

Other

Other2012 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2012
CountryUnited States
CityLas Vegas, NV
Period16/07/1219/07/12

Keywords

  • Biometrics
  • Face recognition
  • Kernel Principal Component Analysis (KPCA)
  • Pattern recognition
  • Video surveillance systems

Fingerprint Dive into the research topics of 'Using linear Kernel entropy component analysis as a feature extraction method in face recognition in video surveillance systems'. Together they form a unique fingerprint.

Cite this