Fusion of Dimension Reduction Methods and Application to Face Recognition

  • Byungjun Son
  • Sungsoo Yoon
  • Yillbyung Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

As dimensionality reduction is an important problem in pattern recognition, it is necessary to reduce the dimensionality of the feature space for efficient face recognition. In this paper, we suggest the fusion of Discrete Wavelet Transform(DWT) and Direct Linear Discriminant Analysis (DLDA) for the efficient dimension reduction. The Support Vector Machines (SVM) and nearest mean classifier (NM) approaches are applied to compare the similarity between the similar and different face data. In the experiments, we show that the proposed method is an efficient way of representing face patterns as well as reducing dimension of multidimensional feature.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Watanabe, H., et al.: Discriminative Metric Design for Robust Pattern Recognition. IEEE Trans. On Signal Processing 45, 2655–2662 (1997)CrossRefGoogle Scholar
  2. 2.
    Jollife, I.T.: Principal Component Analysis. Springer, New York (1986)Google Scholar
  3. 3.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification and Scene Analysis. Wiley Interscience, Hoboken (2000)Google Scholar
  4. 4.
    Poston, W.L.: Recursive Dimensionality Reduction Using Fisher’s Linear Discriminant. Pattern Recognition 31(7), 881–888 (1988)CrossRefGoogle Scholar
  5. 5.
    Yang, J., Yu, H.: A Direct LDA Algorithm for High-Dimensional Data – with Application to Face Recognition. Pattern Recognition 34(10), 2067–2070 (2001)MATHCrossRefGoogle Scholar
  6. 6.
    Swets, D., Weng, J.: Using discriminant eigenfeatures for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(8), 831–836 (1996)CrossRefGoogle Scholar
  7. 7.
    Tefas, A., Kotropoulos, C., Pitas, I.: Using support vector machines to enhance the performance of elastic graph matching for frontal face authentication. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(7) (2001)Google Scholar
  8. 8.
    Laboratories of Intelligent Systems, Institute of Information Science. The IIS Face Database, http://smart.iis.sinica.edu.tw/index.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Byungjun Son
    • 1
  • Sungsoo Yoon
    • 1
  • Yillbyung Lee
    • 1
  1. 1.Division of Computer and Information EngineeringYonsei UniversitySeoulKorea

Personalised recommendations