Accelerating the 3D Random Walker Image Segmentation Algorithm by Image Graph Reduction and GPU Computing
In this paper the problem of image segmentation using the random walker algorithm was considered. When applied to the segmentation of 3D images the method requires an extreme amount of memory and time resources in order to represent the corresponding enormous image graph and to solve the resulting sparse linear system. Having in mind these limitations the optimization of the random walker approach is proposed. In particular, certain techniques for the graph size reduction and method parallelization are proposed. The results of applying the introduced improvements to the segmentation of 3D CT datasets are presented and discussed. The analysis of results shows that the modified method can be successfully applied to the segmentation of volumetric images and on a single PC provides results in a reasonable time.
Unable to display preview. Download preview PDF.
- 1.Felzenschwalb, P., Huttenlocher, F., Efficient, D.P.: graph-based image segmentation. International Journal of Computer Vision 59, 1–25 (2004)Google Scholar
- 3.Intel Sparse matrix storage formats (2013), http://software.intel.com/sites/products/documentation/hpc/mkl/mklman/GUID-9FCEB1C4-670D-4738-81D2-F378013412B0.htm
- 4.Ion, A., Kropatsch, W.G., van Haxhimusa, Y.: Considerations Regarding the Minimum Spanning Tree Pyramid Segmentation Method. In: Yeung, D.-Y., Kwok, J.T., Fred, A., Roli, F., de Ridder, D. (eds.) SSPR&SPR 2006. LNCS, vol. 4109, pp. 182–190. Springer, Heidelberg (2006)Google Scholar
- 5.Labatut, V., Cherifi, H.: Accuracy Measures for the Comparison of Classifiers (2012), http://arxiv.org/ftp/arxiv/papers/1207/1207.3790.pdf
- 6.Nvidia Corporation Cuda Toolkit Documentation (2013), http://docs.nvidia.com/cuda/index.html
- 7.Nvidia Corporation Thrust Quick Start Guide (2013), http://docs.nvidia.com/cuda/pdf/Thrust_Quick_Start_Guide.pdf
- 9.Vineet, V., Harish, P., Suryakant, P.: Fast Minimum Spanning Tree for Large Graphs on the GPU. In: Proceedings of the Conference on High Performance Graphics, pp. 167–171 (2009)Google Scholar