PriMera Scientific Engineering (ISSN: 2834-2550)

Research Article

Volume 2 Issue 4

An Improved Principal Component Analysis (PCA) Face Recognition Technique using Modular Approach

Liu Aofan* and Tan Qianqian

March 24, 2023

DOI : 10.56831/PSEN-02-044

View PDF

Abstract

Face recognition is an important application in computer vision and biometrics. In this paper, we propose a novel approach to face recognition based on modular PCA (Principal Component Analysis). The proposed method improves the accuracy and efficiency of face recognition by dividing the face image into multiple overlapping sub-blocks, and then applying PCA to each sub-block independently. The resulting sub-block eigenfaces are then combined to form a composite face feature vector, which is used for face identification. Experimental results on several standard face recognition datasets demonstrate that our approach outperforms other state-of-the-art methods in terms of recognition accuracy and computational efficiency. The proposed method is also shown to be robust to variations in lighting, facial expressions, and occlusion.

Keywords: modular Analysis; principal component analysis; face recognition; modular PCA; pattern recognition

References

  1. Abdi H. “The interpretation of principal component analysis”. In S. Kotz, N. Balakrishnan, & C. Read (Eds.), Encyclopedia of statistical sciences, Wiley 8 (2007): 1-16.
  2. Comrey AL and Lee HB. A first course in factor analysis (2nd ed.). Erlbaum (1992).
  3. Gorsuch RL. Factor analysis (2nd ed.). Erlbaum (1983).
  4. Hotelling H. “Analysis of a complex of statistical variables into principal components”. Journal of Educational Psychology 24.6 (1933): 417-441.
  5. International Organization for Standardization and Commission Internationale de l'Eclairage. (2019). ISO/CIE 11664-1:2019(E) colorimetry -- Part 1: CIE standard colorimetric observers. ISO. Geneva, Switzerland.
  6. Jackson JE. “A user's guide to principal components”. Wiley (1991).
  7. Jolliffe IT. Principal component analysis (2nd ed.). Springer (2011).
  8. Johnson RA and Wichern DW. Applied multivariate statistical analysis (2007).
  9. O'Connor BP. “SPSS and SAS programs for determining the number of components using parallel analysis and Velicer's MAP test”. Behavior Research Methods, Instruments, & Computers 32.3 (2000): 396-402.
  10. Otsu N. “A threshold selection method from gray-level histograms”. IEEE Transactions on Systems, Man, and Cybernetics 9.1 (1979): 62-66.
  11. Pearson K. “On lines and planes of closest fit to systems of points in space”. Philosophical Magazine 2.11 (1901): 559-572.
  12. Rencher AC. Methods of multivariate analysis (2nd ed.). Wiley (2002).
  13. Shlens J. A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100 (2009).
  14. Tabachnick BG and Fidell LS. Using multivariate statistics (6th ed.). Pearson (2013).
  15. Mardia KV, Kent JT and Bibby JM. “Multivariate analysis”. Academic Press (1979).
  16. Velicer WF. “Determining the number of components from the matrix of partial correlations”. Psychometrika 41.3 (1976): 321-327.