Iterative Multiplicative Filters for Data Labeling
Based on an idea in Åström et al. (J Math ImagingVis, doi: 10.1007/s10851-016-0702-4, 2017) we propose a new iterative multiplicative filtering algorithm for label assignment matrices which can be used for the supervised partitioning of data. Starting with a row-normalized matrix containing the averaged distances between prior features and observed ones, the method assigns in a very efficient way labels to the data. We interpret the algorithm as a gradient ascent method with respect to a certain function on the product manifold of positive numbers followed by a reprojection onto a subset of the probability simplex consisting of vectors whose components are bounded away from zero by a small constant. While such boundedness away from zero is necessary to avoid an arithmetic underflow, our convergence results imply that they are also necessary for theoretical reasons. Numerical examples show that the proposed simple and fast algorithm leads to very good results. In particular we apply the method for the partitioning of manifold-valued images.
KeywordsLabeling Supervised partitioning Multiplicative filter Partitioning Manifold-valued images
We are grateful to Ch. Schnörr (University of Heidelberg) for stimulating discussions. Many thanks to R. Hielscher (University of Chemnitz) for supporting the work on EBSD data. We thank the referees for requesting a discussion of condition (PI). Funding by the German Research Foundation (DFG) within the Project STE 571/13-1 & BE 5888/2-1 and within the Research Training Group 1932 “Stochastic Models for Innovations in the Engineering Sciences”, project area P3, is gratefully acknowledged. Furthermore, G. Steidl acknowledges the support by the German Federal Ministry of Education and Research (BMBF) through Grant 05M13UKA (AniS).
- Åström, F., Petra, S., Schmitzer, B., & Schnörr, C. (2016a). A geometric approach to image labeling. In Proceedings of the ECCV.Google Scholar
- Åström, F., Petra, S., Schmitzer, B., & Schnörr, C. (2016b). The Assignment Manifold: A smooth model for image labeling. In Proceedings of the 2nd international workshop on differential geometry in computer vision and machine learning.Google Scholar
- Åström, F., Petra, S., Schmitzer, B., & Schnörr, C. (2017). Image labeling by assignment. Journal of Mathematical Imaging and Vision. doi: 10.1007/s10851-016-0702-4.
- Bachmann, F., & Hielscher, R. (2005–2016). MTEX—MATLAB toolbox for quantitative texture analysis. http://mtex-toolbox.github.io/.
- Burger, M., Sawatzky, A., & Steidl, G. (2016). First order algorithms in variational image processing. In R. Glowinski, S. Osher, & W. Yin (Eds.), Operator splittings and alternating direction methods. Berlin: Springer.Google Scholar
- Cook, P. A., Bai, Y., Nedjati-Gilani, S., Seunarine, K. K., Hall, M. G., Parker, G. J., & Alexander, D. C. (2006)(2006) Camino: Open-source diffusion-MRI reconstruction and processing. In 14th Scientific meeting of the international society for magnetic resonance in medicine (p. 2759). Seattle, WA.Google Scholar
- Frobenius, G. F. (1912). Über Matrizen aus nichtnegativen Elementen. Königliche Akademie der Wissenschaften.Google Scholar
- Laus, F., Persch, J., & Steidl, G. (2016). A nonlocal denoising algorithm for manifold-valued images using second order statistics. SIAM Journal on Imaging Sciences. ArXiv, Preprint arXiv:1607.08481.
- Moakher, M., & Batchelor, P. G. (2006). Symmetric positive-definite matrices: From geometry to applications and visualization. In Visualization and processing of tensor fields (pp. 285–298). Berlin: Springer.Google Scholar
- Nolze, G., & Hielscher, R. (2016). IPF coloring of crystal orientation data. Preprint Technische Universität Chemnitz.Google Scholar
- Peyré, G. (2015). Entropic Wasserstein gradient flows. ArXiv Preprint arXiv:1502.06216v3.
- Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., et al. (2008). A comparative study of energy minimizing methods for Markov random fields with smoothness-based priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(6), 1068–1080.CrossRefGoogle Scholar
- Tomasi, C., & Manduchi, R. (1998). Bilateral filtering for gray and color images. In Proceedings of the sixth international conference on computer vision (pp. 839–846). Bombay. Narosa Publishing House.Google Scholar
- Tuzel, O., Porikli, F., & Meer, P. (2006). Region covariance: A fast descriptor for detection and classification. In European conference on computer vision (pp. 589–600). Berlin: Springer.Google Scholar