DCT-based unique faces for face recognition using Mahalanobis distance

ABSTRACT

In this paper, we propose a technique to generate DCT based unique normalized face using Principal Component Analysis (PCA). The idea of the PCA is to decompose face images into a small set of characteristic feature images. In the proposed technique we generate feature image by finding the peak values in the absolute DCT matrix followed by normalization. This maximizes the scatter between training dataset to give more discriminating power. The feature images so generated are called unique normalized faces as each image is different and unique from all other training faces. They have high recognition performance since they capture the global features onto a low dimensional linear "face space" extracted from the individual face of training dataset. We use Mahalanobis distance to measure the recognition between original face and the test face. The algorithm is tested on ORL face datasets. In the proposed technique we improved face recognition rate as compared to Eigenface, DCT-normalization and Wavelet-Denoising.

References

1. Brian H. Russell and Laurence R. Lines, 2003. Mahalanobis clustering, with applications to AVO classification and seismic reservoir parameter estimation. In CREWES Research Report, Volume 15, 1--23
2. C. Podilchuk, Xiao Zhang, 1996. Face recognition using DCT-based feature vectors. In Proceedings of the Acoustics, Speech, and Signal Processing, ICASSP'96, IEEE, 2144-2147. ISBN:0-7803-3192-3, DOI= 10.1109/ICASSP.1996.545740
3. Chellappa, R.; Wilson, C. L.; Sirohey, S.; 1995. Human and machine recognition of faces: a survey. In Proceedings of the IEEE, Volume 83, Issue 5, 705--741. DOI= 10.1109/5.381842
4. Chen, W.; Meng Joo Er; Shiqian Wu, 2006. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithmic domain. In IEEE Transactions on Systems, Man and Cybernetics, part B: Cybernetics, Volume 36, Issue 2, 458--466. DOI= 10.1109/TSMCB.2005.857353
5. Chichizola, F.; De Giusti, L.; De Giusti, A.; Naiouf, M., 2005. Face Recognition: Reduced Image Eigenfaces Method. In ELMAR, 2005. 47th International Symposium, Zadar, Croatia, 159--162. DOI= 10.1109/ELMAR.2005.193666
6. Haris Supic, 2008. Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning. In Proceedings of the World Congress on Engineering, WCE 2008, Volume 1, London, U. K. ISBN: 978-988-98671-9-5.
7. Joanna Jaworska, Tom Aldenberg, Nina Nikolova, 2005. Review of methods for QSAR applicability domain estimation by the training set. In The European Commission - Joint Research Centre, Institute for Health & Consumer Protection -- ECVAM, Ispra (VA), Italy, 1--39.
8. M. Turk and A. Pentland., 1991. Eigenfaces for recognition. In Journal of Cognitive Neuroscience, Volume 3(1). 71--86. DOI= 10.1162/jocn.1991.3.1.71
9. M. Wolfel, H. K. Ekenel. 2005. Feature weighted Mahalanobis distance: Improved robustness for gaussian classifiers, 2005, In Proceedings of 13th European Signal Processing Conference EUSIPCO '05, Antalya, Turkey.
10. Michelle M., Juliana G. Denipote, Ricardo A. S. Fernandes, Maria Stela V. Paiva. Illumination Normalization Methods for Face Recognition, In Escola de Engenharia de São Carlos -- EESC. Universidade de São Paulo - USP, 1--2.
11. R. Brunelli,; T. Poggio, 1993. Face recognition: features versus templates. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 15, No. 10, 1042--1052. DOI=10.1109/34.254061
12. R. Gonzalez and R. E. Woods, 1992. In Digital Image Processing. Addison-Wesley. Prentice Hall, second edition.
13. R. Gross and V. Brajovic, 2003. An image pre-processing algorithm for illumination invariant face recognition. In Proceedings of 4th International Conference on Audio- and Video-Based Biometric Person Authentication, AVBPA'03, LNCS 2688, 10--18.
14. Ramanathan, N.; Chellappa, R.; Roy Chowdhury, A. K.; 2004. Facial similarity across age, disguise, illumination and pose. In Proceedings of the International Conference on Image Processing ICIP '04, 1999--2002. DOI=10.1109/ICIP.2004.1421474
15. S. Srisuk and W. Kurutach, 2003, Face Recognition using a New Texture Representation of Face Images, In Proceedings of Electrical Engineering Conference, Chaam, Thailand, 1097--1102.
16. Shiming Xiang, Feiping Nie, Changshui Zhang, 2008. Learning a Mahalanobis distance for distance clustering and classification. In Journal of Pattern recognition, Volume 41, Issue 12, 3600--3612.
17. Short, J.; Kittler, J.; Messer, K., 2004. A comparison of photometric normalization algorithm for face verification, In Proceedings of Sixth IEEE International conference on Automatic Face and Gesture Recognition, 2004.AFGR'04, 254--259.DOI= 10.1109/AFGR.2004.1301540
18. V. Štruc and N Pavešić. Performance Evaluation of Photometric Normalization Techniques for Illumination Invariant Face Recognition", In: Y. J. Zhang (Ed.), Advances in Face Image Analysis: Techniques and Technologies. IGI Global.

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

  • Computer graphics

  • Machine learning

    • Machine learning algorithms