AUTHORS: Roumiana Kountcheva, Roumen Kountchev

Download as PDF

ABSTRACT: The famous method Principal Components Analysis (PCA) is the basic approach for decomposition of 3D tensor images (for example, multi- and hyper-spectral, multi-view, computer tomography, video, etc.). As a result of the processing, their information redundancy is significantly reduced. This is of high importance for the efficient compression and for the reduction of the features space needed, when object recognition or search is performed. The basic obstacle for the wide application of PCA is the high computational complexity. One of the approaches to overcome the problem is to use algorithms, based on the recursive PCA. The well-known methods for recursive PCA are aimed at the processing of sequences of images, represented as non-overlapping groups of vectors. In this work is proposed new method, called Sliding Recursive Hierarchical Adaptive PCA, based on image sequence processing in a sliding window. The new method decreases the number of calculations needed, and permits parallel implementation. The results obtained from the algorithm simulation, confirm its efficiency. The lower computational complexity of the new method facilitates its application in the real-time processing of 3D tensor images.

KEYWORDS: Hierarchical Adaptive PCA, Sliding Recursive PCA, 3D tensor image decomposition

REFERENCES:

[1] T. Kolda, B. Bader, Tensor decompositions and applications, SIAM Review, Vol. 51, No 3, 2009, pp. 455-500.

[2] M. Torun, A. Akansu, An Efficient Method to Derive Explicit KLT Kernel for First-Order Discrete Autoregressive Process, IEEE Transactions on Signal Processing, Vol. 61, No 15, 2013, pp. 3944-3953.

[3] H. Abdi, L. Williams, Principal Component Analysis, Wiley Interdisciplinary Reviews: Computational Statistics, Vol. 2, Iss. 4, 2010, pp. 433-459.

[4] R. Gonzales, R. Woods, Digital Image Processing, 3rd ed., Prentice Hall, 2008.

[5] S. Orfanidis, SVD, PCA, KLT, CCA, and all that, Rutgers University Electrical & Computer Engineering Department, Optimum Signal Processing, 2007, pp. 1-77.

[6] I. Jolliffe, Principal Component Analysis, 2nd ed., Springer, NY, 2002.

[7] C. Maccone, A simple introduction to the KLT (Karhunen-Loève Transform), Deep Space Flight and Communications, C. Maccone (Ed.), Springer, 2009, pp. 151-179.

[8] M. Hanafi, A. Kohler, E. Qannari, Shedding new light on Hierarchical Principal Component Analysis, Journal of Chemometrics, Vol. 24, Iss. 11-12, 2010, pp. 703-709.

[9] I. Blanes, J. Sagristà, M. Marcellin, J. Rapesta, Divide-and-conquer strategies for hyperspectral image processing, IEEE Signal Processing Magazine, Vol. 29, No 3, 2012, pp. 71-81.

[10] R. Kountchev, R. Kountcheva, Decorrelation of Multispectral Images, Based on Hierarchical Adaptive PCA, Intern. Journal WSEAS Trans. on Signal Processing, Iss. 3, No 9, July 2013, pp. 120-137.

[11] W. Li, H. Yue, S. Cervantes, S. Qin, Recursive PCA for adaptive process monitoring, Journal of Process Control, Vol.10, No 5, October 2000, pp. 471-486.

[12] D. Erdogmus, Y. Rao, H. Peddaneni, A. Hegde, J. Principe, Recursive Principal Components Analysis using Eigenvector Matrix Perturbation, EURASIP Journal on Advances in Signal Processing, Vol. 13, Dec. 2004:13, pp. 2034- 2041.

[13] A. Amar, A. Leshem, M. Gastpar, Recursive Implementation of the Distributed KarhunenLoève Transform, IEEE Trans. on Signal Processing, Vol. 58, No 10, 2010, pp. 5320- 5330.

[14] Z. Wei, X. Liu, F. Li, S. Shang, X. Du, J. Wen, Matrix Sketching Over Sliding Windows, Proc. of the Intern. Conf. on Management of Data (SIGMOD’16), June 26-July 01, San Francisco, USA, 2016, pp. 1465-1480.

[15] S. Zhou, N. Vinh, J. Bailey, Y. Jia, I. Davidson, Accelerating Online CP Decompositions for Higher Order Tensors, Proc. of the 22nd ACM SIGKDD Intern. Conf. on Knowledge Discovery and Data Mining (KDD’16), August 13-17, San Francisco, USA, 2016, pp. 1375-1384.

[16] J. Faires, R. Burden, Numerical Methods, 4th ed, Brooks/Cole, Boston MA, USA, 2013.

[17] P. Ivanov, R. Kountchev, Hierarchical Principal Component Analysis based Transformation of Multispectral Images, Intern. Journal of Reasoning-Based Intelligent Systems (IJRIS), Vol. 5, No 4, 2013, pp. 260-273.

[18] S. Arora, B. Barak, Computational Complexity: A Modern Approach, Cambridge University Press, NY, USA, 2009.