Application of cascading two-dimensional canonical correlation analysis to image matching

• Autorzy: Forczmański P. , Kukharev G. , Kamenskaya E.
• Języki publikacji: EN

Abstrakty

EN

The paper presents a novel approach to Canonical Correlation Analysis (CCA) applied to visible and thermal infrared spectrum facial images. In the typical CCA framework biometrical information is transformed from original feature space into the space of canonical variates, and further processing takes place in this space. Extracted features are maximally correlated in canonical variates space, making it possible to expose, investigate and model latent relationships between measured variables. In the paper the CCA is implemented along two directions (along rows and columns of pixel matrix of dimension M x N) using a cascade scheme. The first stage of transformation proceeds along rows of data matrices. Its results are reorganized by transposition. These reorganized matrices are inputs to the second processing stage, namely basic CCA procedure performed along the rows of reorganized matrices, resulting in fact in proceeding along the columns of input data matrix. The so called cascading 2DCCA method also solves the Small Sample Size problem, because instead of the images of size MxN pixels in fact we are using N images of size M x 1 pixels and M images of size 1 x N pixels. In the paper several numerical experiments performed on FERET and Equinox databases are presented.

Słowa kluczowe

EN

canonical correlation analysis; image matching; face recognition

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2011
• Tom: Vol. 40, no 3
• Strony: 833--848
• Opis fizyczny: Bibliogr. 22 poz., il.

Twórcy

autor

Forczmański P.

autor

Kukharev G.

autor

Kamenskaya E.

• 1West Pomeranian University of Technology, Faculty of Computer Science and Information Technology Żołnierska 49, 71-210 Szczecin, Poland,

Bibliografia

• Borga,M. (2001) Canonical correlation - a tutorial. See http://www.imt.liu.se/magnus/cca/tutorial/tutorial.pdf.
• Cai-rong, Z., Ning, S. and Zhen-shai, J. (2007) 2DCCA: A novel metod for small sample size face recognition. In: IEEE Workshop on Application of Computer Vision, WACV’07. IEEE Computer Society Press, Los Alamos, CA, 43-47.
• Donner, R., Reiter, M., Langs, G., Peloschek, P. and Bischof, H. (2006) Fast active appearance model search using canonical correlation analysis. IEEE Transaction on PAMI, 28 (10), 1960-1964
• Equinox Corporation (2009) Human Identification at a Distance: The Equinox database. see http://www.equinoxsensors.com/products/HID.html.
• Hotelling, H. (1936) Relations between two sets of variates. Biometrika 28 (3-4), 321-377.
• ISO/IEC (2009) JTC 1/SC 37 N 506: Biometric data interchange formats, part 5: Face image data. see http://www.icao.int/mrtd/download/technical.cfm
• Kamenskaya, E., Borawski, M. and Szaber, M. (2009) Visible and infrared recognition using canonical variables. Polish Journal of Environmental Studies 18 (3B), 39-43.
• Kompanets, L. et al. (2002) Biometrical method of personal identification based on information about asymmetry and mimics (in Polish). In: Proceedings of the 6-th Intern. Conference IT Forum Secure 2002, 2, NASK and Multicopy Press, Warszawa, 31-40.
• Kukharev, G. and Kuzminski, A. (2003) Biometric techniques. Part I. The Methods of Face Recognition (in Polish). Pracownia Poligraficzna WI PS, Szczecin (Poland).
• Kukharev, G. and Kamenskaya, E. (2009) Two-dimensional canonical correlation analysis for face image processing and recognition. Metody Informatyki Stosowanej 18 (3), 103-112.
• Lanitis, A., Taylor, Ch.J. and Cootes, T.F. (1997) Automatic interpretation and coding of face images using flexible models. IEEE Trans. PAMI 17 (7), 73-755.
• Lee, S.H. and Choi, S. (2007) Two-dimensional CCA. IEEE Signal Processing Letters 14 (10), 735-738.
• Pentland, A. and Choudbury, T. (2000) Face recognition for smart environments. IEEE Computer 1, 50-55.
• Phillips, P.J., Wechler, H., Huang J. and Rauss, P.J. (1998) The FERET database and evaluation procedure for face recognition algorithms. Image and Vision Computing 16 (5), 295-306.
• Phillips, P.J. , Moon, H., Rauss, P.J. and Rizvi, S. (2000) The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (10), 1090-1104.
• Scheenstra, A., Ruifrok, A., Veltkamp, R. (2005) A Survey of 3D Face Recognition Methods. In: Audio- and Video-Based Biometric Person Authentication. LNCS 3546, Springer, 325-345.
• Socolinsky, D. and Selinger, A. (2002) A comparative analysis of face recognition performance with visible and thermal infrared imagery. In: Proceedings of the 16th International Conference on Pattern Recognition. IEEE Computer Society Press, Los Alamos, CA, 217-222
• Tistarelli, M. and Grosso, E. (1997) Active face recognition with a hybryd approach. Pattern Recognition Letters 18, 933-946.
• Turk M., Pentland, A. (1991) Eigenfaces for Recognition. Journal of Cognitive Neurosicence 3, 1, 71-86
• Yi,D., Liu,R., Chu,R., Lei, Z. and Li, S.Z. (2007) Face matching between near infrared and visible light images. LNCS 4642, Springer, 523-530.
• Zhao, W., Chellappa, R., Rosenfeld, A. and Phillips, P. (2000) Face recognition: A literature survey. ACM Computing Surveys 35 (4), 399-458.
• Zuo, W., Wang, K. and Zhang, H. (2009) Subspace Methods for Face Recognition: Singularity, Regularization, and Robustness. State of the Art. in Face Recognition. InTech, Vienna, Austria.