Abstract
This work describes a novel quadratic formulation for solving the normalized cuts-based clustering problem as an alternative to spectral clustering approaches. Such formulation is done by establishing simple and suitable constraints, which are further relaxed in order to write a quadratic functional with linear constraints. As a meaningful result of this work, we accomplish a deterministic solution instead of using a heuristic search. Our method reaches comparable performance against conventional spectral methods, but spending significantly lower processing time.
Chapter PDF
Similar content being viewed by others
Keywords
- Linear Constraint
- Spectral Cluster
- Quadratic Problem
- Quadratic Programming Algorithm
- Lower Processing Time
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Dhillon, I.S., Guan, Y., Kulis, B.: Kernel k-means, spectral clustering and normalized cuts (2004)
Stella, Y., Jianbo, S.: Multiclass spectral clustering. In: ICCV 2003: Proceedings of the Ninth IEEE International Conference on Computer Vision, p. 313. IEEE Computer Society, Washington, DC (2003)
Tung, F., Wong, A., Clausi, D.A.: Enabling scalable spectral clustering for image segmentation. Pattern Recognition 43(12), 4069–4076 (2010)
Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1943–1950. IEEE (2010)
Peluffo-Ordonez, D.H., Castro-Ospina, A.E., Chavez-Chamorro, D., Acosta-Medina, C.D., Castellanos-Dominguez, G.: Normalized cuts clustering with prior knowledge and a pre-clustering stage
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 888–905 (2000)
Zelnik-manor, L., Perona, P.: Self-tuning spectral clustering. In: Advances in Neural Information Processing Systems, vol. 17, pp. 1601–1608. MIT Press (2004)
Alzate, C., Suykens, J.A.K.: Multiway spectral clustering with out-of-sample extensions through weighted kernel pca. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(2), 335–347 (2010)
Peluffo-Ordonez, D.H., Alzate, C., Suykens, J.A.K., Castellanos-Dominguez, G.: Optimal data projection for kernel spectral clustering
Molina-Giraldo, S., Álvarez-Meza, A., Peluffo-Ordoñez, D., Castellanos-Domínguez, G.: Image segmentation based on multi-kernel learning and feature relevance analysis. In: Advances in Artificial Intelligence–IBERAMIA 2012, pp. 501–510 (2012)
Peluffo-Ordóñez, D.H., García-Vega, S., Álvarez-Meza, A.M., Castellanos-Domínguez, C.G.: Kernel spectral clustering for dynamic data. In: Ruiz-Shulcloper, J., Sanniti di Baja, G. (eds.) CIARP 2013, Part I. LNCS, vol. 8258, pp. 238–245. Springer, Heidelberg (2013)
Dhillon, I.S., Guan, Y., Kulis, B.: Weighted graph cuts without eigenvectors a multilevel approach. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(11), 1944–1957 (2007)
Xu, L., Li, W., Schuurmans, D.: Fast normalized cut with linear constraints. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 2866–2873. IEEE (2009)
Peluffo, D., Acosta, C.D., Castellanos, G.: An improved multi-class spectral clustering based on normalized cuts. In: XVII Iberoamerican Congress on Pattern Recognition CIARP (2012)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th Int’l Conf. Computer Vision, vol. 2, pp. 416–423 (July 2001)
Pate, T.H.: Extending the hölder type inequality of blakley and roy to non-symmetric non-square matrices. Trans. Amer. Math. Soc 364, 4267–4281 (2012)
Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(6), 929–944 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Peluffo-Ordóñez, D.H., Castro-Hoyos, C., Acosta-Medina, C.D., Castellanos-Domínguez, G. (2014). Quadratic Problem Formulation with Linear Constraints for Normalized Cut Clustering. In: Bayro-Corrochano, E., Hancock, E. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2014. Lecture Notes in Computer Science, vol 8827. Springer, Cham. https://doi.org/10.1007/978-3-319-12568-8_50
Download citation
DOI: https://doi.org/10.1007/978-3-319-12568-8_50
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12567-1
Online ISBN: 978-3-319-12568-8
eBook Packages: Computer ScienceComputer Science (R0)