Performance Evaluation of Different Feature Extractors and Classifiers for Recognition of Human Faces with Low Resolution Images

Performance Evaluation of Different Feature Extractors and Classifiers for Recognition of Human Faces with Low Resolution Images

Journal

Subject and more

  • LCC Subject Category: Engineering, Nanotechnology
  • Publisher's keywords: Face recognition, Feature Extraction, Classification, Interpolation, Dimensionality Reduction
  • Language of fulltext: english
  • Full-text formats available: PDF
  • Time From Submission to Publication: 4

AUTHORS

    Soodeh Nikan*| ECE, University of Windsor, Windsor, ON – N9B 3P4, Canada, Majid Ahmadi| ECE, University of Windsor, Windsor, ON – N9B 3P4, Canada

FULL TEXT

To download PDF files Login to your Account.

ABSTRACT

Face recognition is an effective biometric identification technique used in many applications such as law enforcement, document validation and video surveillance. In this paper the effect of low resolution images which are captured in real world applications, on the performance of different feature extraction techniques combined with a variety of classification approaches is evaluated. Gabor features and its combination with local phase quantization histogram (GLPQH) are dimensionality reduced by principal component analysis (PCA), linear discriminant analysis (LDA), locally sensitive discriminant analysis (LSDA) and neighbourhood preserving embedding (NPE) to extract discriminant image characteristics and the class label is attributed using the extreme learning machine (ELM), sparse classifier (SC), fuzzy nearest neighbour (FNN) or regularized discriminant classifier (RDC). ORL and AR databases are utilized and the results show that ELM and RDC have better performance and stability against resolution reduction, especially on Gabor-PCA and Gabor-LDA techniques. Among the interpolation approaches that we employed to enhance the image resolution, nearest neighbour outperforms other methods.

About Europub

EuroPub is a comprehensive, multipurpose database covering scholarly literature, with indexed records from active, authoritative journals, and indexes articles from journals all over the world. The result is an exhaustive database that assists research in every field. Easy access to a vast database at one place, reduces searching and data reviewing time considerably and helps authors in preparing new articles to a great extent. EuroPub aims at increasing the visibility of open access scholarly journals, thereby promoting their increased usage and impact.