A Face Recognition Algorithm Based on Improved Contourlet Transform and Principle Component Analysis
Abstract: As the internet
keeping developing, face recognition has become a research hotspot in the field
of biometrics. This paper proposes an improved face recognition algorithm that
reduces the influence of illumination and posture variations. First, face
images are transformed by using the improved contourlet transform method to get
low frequency sub-band images and high frequency sub-band images. Then this paper
uses the principal component analysis to extract main features. Finally,
combines these statistic features together as feature vector and recognize face
images. Analysis, experiment and proof on the ORL face database and the Yale
face database show that this algorithm is better able to recognize faces, reduce
the influence of illumination and posture variations and increase the
efficiency of face recognition.
Author: Jinhua Zhang, Daniel
Scholten
Journal Code: jptkomputergg160051
