Abstract
An approach to dimensionality reduction using 2DPCA is presented for colored images. This research also investigates the mechanism of reducing computational complexity for computer vision applications. Since high dimensional data poses various problems like increased computational complexity and increased processing time, there is a dire need of incorporating dimensionality reduction as a preprocessing step in various applications to reduce these factors, which becomes worst for color image processing.
In the first part of this research, key frames are extracted from long video sequences using entropy difference between frames. Afterwards RGB image representing each frame is converted to indexed image and 2DPCA is applied on that image to get its basis vectors. Comparison of uniform quantization and minimum variance quantization techniques for color map approximation from RGB to indexed conversion is presented. Analysis of results obtained by using uniform quantization as a color map approximation technique will be presented in terms of PSNR. Major reduction in overall image dimensions is observed using proposed technique, hence reducing the overall complexity of the required algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ebied, H.: Feature extraction using PCA and kernel-PCA for face recognition. In: 2012 8th International Conference on Informatics and Systems (INFOS), p. MM-72. IEEE (2012)
Mudrova, M., Prochazka, A.: Principal component analysis in image processing. In: Proceedings of the MATLAB Technical Computing Conference, Prague (2005)
Yu, H., Bennamoun, M.: 1D-PCA 2D-PCA to nD-PCA. In: 18th International Conference on Pattern Recognition, 2006, ICPR 2006, vol. 4, pp. 181–184. IEEE (2006)
Dwivedi, A., Tolambiya, A., Kandula, P., Bose, N., Kumar, A. Kalra, P.: Color image compression using 2-dimensional principal component analysis (2DPCA). In: 9th International Conference on Asian Symposium on Information Display, 2006, ASID 2006, vol. 2, p. 1 (2006)
Yang, J., Zhang, D., Frangi, A., Yang, J.: Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 131–137 (2004)
Zhang, D., Zhou, Z.-H.: (2D) 2PCA: Two-directional two-dimensional PCA for efficient face representation and recognition. Neurocomputing 69(1), 224–231 (2005)
Buchanan, A., Fitzgibbon, A.: Interactive feature tracking using kd trees and dynamic programming. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 626–633. IEEE (2006)
Kwatra, V., Han, M.: Fast covariance computation and dimensionality reduction for sub-window features in images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 156–169. Springer, Heidelberg (2010)
Mentzelopoulos, M., Psarrou, A.: Key-frame extraction algorithm using entropy difference. In: Proceedings of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval, pp. 39–45. ACM (2004)
Acknowledgment
We would like to thank Dr. Fahim Arif, Dr. Imran Tauqeer and Dr. Adil Masood Siddique of Military College of Signals, for their continuous support and valuable suggestions throughout this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Javaid, S., Rao, N. (2014). Dimensionality Reduction of Colored Images Using 2DPCA. In: Shaikh, F., Chowdhry, B., Zeadally, S., Hussain, D., Memon, A., Uqaili, M. (eds) Communication Technologies, Information Security and Sustainable Development. IMTIC 2013. Communications in Computer and Information Science, vol 414. Springer, Cham. https://doi.org/10.1007/978-3-319-10987-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-10987-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10986-2
Online ISBN: 978-3-319-10987-9
eBook Packages: Computer ScienceComputer Science (R0)