Application of DCT blocks with principal component analysis for face recognition

  • Authors:
  • Maha Sharkas

  • Affiliations:
  • Electronics & Communication Eng. Dept., Arab Academy for Science & Technology, Alexandria, Egypt

  • Venue:
  • SSIP'05 Proceedings of the 5th WSEAS international conference on Signal, speech and image processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Security is becoming one of the main human concerns nowadays. The need for an identity that cannot be destroyed, forgotten or stolen is greatly recommended in a world that is directed more and more toward automation. Hence, Biometrics is taking an important role in personal identification systems. A technique for automatic face recognition based on 2D Discrete Cosine Transform (2D-DCT) together with Principal Component Analysis (PCA) is suggested and tested. The achieved recognition rate varied according to the chosen threshold based on the security level of the application. The best achieved recognition result is 96.5%.