Modular Human Face Recognition Method based on Principal Component Analysis and Mahalanobis Distance

Document Type : Original Article

Authors

1 Assistant Professor, Imam Hossein University (AS), Tehran, Iran

2 Researcher, Imam Hossein University .Tehran, Iran

Abstract

The principal component analysis (PCA) method is one of the well-known dimensional reduction methods, The PCA has many applications in big data analysis from various fields. PCA is an essential method for image processing that is used directly or after several stages of preprocessing and in combination with other methods. Face recognition methods based on principal component analysis have many applications in face detection and recognition. In this paper, we present a cost-effective algorithm for human face
recognition based on principal component analysis, which combines the Mahalanobis distance with the PCA method, the ability to detect faces in the shortest possible time for low-quality and black and white images. The architect of this method is modular, and every part of it can be hybridized with other methods. The proposed method is expressed and discussed in terms of parameters for determining the complexity and computational efficiency. Overall, it can be said that the method presented compared to other methods can process images with very low resolution and color depth, is able to recognize the face based on the B&W images, has no need for robust and costly computer systems, has a modular structure, and customizable based on distance (For example, a 30 percent increase of recognition rate from 49 % to 79 % in some
implementations).
 

Keywords

Smiley face

https://creativecommons.org/licenses/by/4.0/

References

   [1]      Weinberger, K. Q.; Saul, L. K. “An Introduction to Nonlinear Dimensionality Reduction by Maximum Variance Unfolding”; American Association for Artificial Intelligence, 2006.
   [2]      Yazdani, H. R.; Shahrezaee, M.; Shojaeifard, A. R. “Introduction to Data Science, Big Data, and Intelligent Learnings”; Tafresh University in cooperation with Shar Publication. 2022, ISBN: 978-600-91089-0-9 (In Persian). 
   [3]      Rama, A; Tarres, D; Onofrio, D; Tubaro, S. “Mixed 2D-3D information for pose estimation and face recognition”; International Conference on Acoustic, Speech and Signal Processing (ICASSP); 2006, 361-364.
   [4]      Riccio, D.; Dugelay, J. L. “Geometric invariants for 2D/3D face recognition”; Pattern Recognition Letters; 2007, 1907-1914.
   [5]      Yang, W.; Lei, Z.; Sang, J. “2D-3D face matching using CCA method”; International Conference on Automatic Face and Gesture Recognition”; Beijing, 2008, 1-6.
   [6]      Ravi, K., and M. Kttswamy. "Face recognition using PCA and eigenface approach." Int J Mag Eng Manag Res 1.10, 2014.
   [7]      Meenpal, T., Aarti Goyal, and Ankita Meenpal. "Face recognition system based on principal components analysis and distance measures." Int. J. Eng. Technol 7.2, 2018, 15-19.
   [8]      Mulyono, Ibnu Utomo Wahyu, et al. "Performance Analysis of Face Recognition using Eigenface Approach." 2019 International Seminar on Application for Technology of Information and Communication (iSemantic), IEEE, 2019.
   [9]      Maheswari, Vannya, Christy Atika Sari, and Eko Hari Rachmawanto. "Study Analysis of Human Face Recognition using Principal Component Analysis." 2020 International Seminar on Application for Technology of Information and Communication (iSemantic). IEEE, 2020.
[10]      Fu, Y.; “Manifold Learning Theory and Applications”; London, CRC Press, Taylor Francis, 2012.
[11]      Maesschalck, R. De; Jouan-Rimbaud, D.; Massart, D.L. “The Mahalanobis distance”, Chemometrics and Intelligent Laboratory Systems, 50 (1), 2000, 1-18.
[12]      Myung, G. K.; “Multivariate outliers and decompositions of Mahalanobis distance”, Communications in Statistics - Theory and Methods, 29(7), 2000, 1511-1526.
[13]      Searcóid, M. Ó.; “Metric Spaces”, Springer, 2006.
[14]      Shojaeifard, A. R.; Shahrezaee, M.; Yazdani, H. R.; “Fixing security defects of video authentication systems with face recognition based on 3D structure and shape evaluation”; Scientific Journal of electronic and cyber defense; Onilne Published: ECDJ-2109-1327, 2022.
[15]      Xiao, H.; Huang, M.; Zhu, X. “From One Point to A Manifold: Knowledge Graph Embedding for Precise Link Prediction”, arXiv:1512.04792v5, 2017.

Files

History

  • Receive Date: 05 July 2023
  • Revise Date: 05 December 2023
  • Accept Date: 18 December 2023
  • Publish Date: 18 January 2024

Share

How to cite

Statistics