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.
Keywords: contourlet transform, principal component analysis, face recognition
Author: Jinhua Zhang, Daniel Scholten
Journal Code: jptkomputergg160051

Artikel Terkait :