Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images
In this paper we provide an efficient parallel algorithm for reconstruction from markers, and multi-scale analysis through differential morphological profiles, which are top-hat scale spaces based on openings and closings by reconstruction. The new algorithms provide speed gain in two ways: (i) through parallelism, and (ii) through more efficient re-use of previously computed data. The best version of the algorithm provided a 17× speed-up on 24 cores, over computation of the same algorithm on a single core. Compared to the basic method of repeated reconstructions by a sequential algorithm, a speed gain of 25.1 times was obtained.
KeywordsReconstruction Phase Marker Image Single Thread Level Root Speed Gain
Unable to display preview. Download preview PDF.
- 2.Pesaresi, M., Benediktsson, J.A.: Image segmentation based on the derivative of the morphological profile. In: Goutsias, J., Vincent, L., Bloomberg, D. (eds.) Mathematical Morphology and its Applications to Image and Signal Processing. Computational Imaging And Vision, vol. 18, pp. 179–188. Kluwer Academic Publishers, Boston (2000)CrossRefGoogle Scholar
- 6.Vaz, M.S., Kiraly, A.P., Mersereau, R.M.: Multi-level decomposition of Euclidean spheres. In: Proc. Int. Symp. Math. Morphology (ISMM) 2007, pp. 461–472 (2007)Google Scholar
- 9.Wilkinson, M.H.F., Soille, P., Ouzounis, G.K.: Concurrent computation of differential morphological profiles for remote sensing. In: Köthe, U., Montanvert, A., Soille, P. (eds.) Proc. of WADGMM ICPR Workshop, pp. 67–71. IAPR, Istanbul (2010)Google Scholar