Ölçeklendirme Yaklaşımlı GPU Tabanlı Seviye Kümesi Yöntemi Kullanan Görüntü Bölütleme

Bu çalışmada görüntü bölütleme için kullanılan seviye kümesi yöntemi ölçeklendirme yaklaşımı ile GPUüzerinde çalıştırılmıştır. Seviye kümeleri yaklaşımı ağırlıklı olarak kısmi diferansiyel denklemlerin çözümünedayanmaktadır. Sunulan yöntem kısmi diferansiyel çözümüne gerek duymaz. Temel geometrik dönüşümlerdenolan ölçeklendirme yaklaşımını kullanır. Böylece çözüm için gerekli olan hesaplama yükünü hafifletir. GPUüzerinde CUDA programlama kullanılarak performans ve harcanan zaman bakımından avantaj sağlanmış ve çokdaha hızlı sonuçlar elde edilmiştir. GPU kullanılması ile gerçek zamanlı işlem yapmaya da olanak sağlamıştır.Bu çalışmada geliştirilen uygulama beyin tümörleri üzerine uygulanmıştır.

Image segmentation using GPU-based Level Set Method with Scaling Approach

In this study, a scaling approach for image segmentation using level sets is carried out by the GPU programmingtechniques. Approach to level sets is mainly based on the solution of partial differential equations. The proposedmethod does not require the solution of partial differential. Scaling approach, which uses basic geometrictransformations, is used. Thus, the computational cost required to work lighter. The use of the CUDAprogramming on the GPU has taken advantage of classic programming as spending time and performance. Thusbetter results are obtained quickly. The use of the GPU has provided to enable real-time processing. Thedeveloped application in this study was applied to brain tumors.

PDF

___

1. Osher,S.,Paragios,N. (2003)Geometric Level Set Methods in Imaging, Vision and Graphics, Springer-Verlag New York, Secaucus, NJ, USA, 513s. 2. Shattuck,D. W., Prasad, G., Mirza, M., Narr, K. L., Toga, A. W. (2009) Online resource for validation of brain segmentation methods, Neuro Imaging, 45, 431-439. 3. Osher, S., Sethian, J. (1988) Fronts propagating with curvature dependent speed: Algorithims based on Hamilton Jakobi formulation, J. Comput. Phys., 79 no:1, 12-49. 4. Fetkiw, R. (2002) Simulating Natural Phenomena for Computer Graphics, In Imaging, Vision and Graphics, 461-479. 5. Adalsteinsson, D., Sethian, J. (1995) A Fast Level Set Method for Propagating Interfaces, Journal of Computational Physics, 118 no:2, 269-277. 6. Whitaker, R. (1998) A Level-Set Approach to 3D Reconstruction from Range Data, International Journal of Computer Vision, 29 no:3, 203-232. 7. http://en.wikipedia.org/wiki/CUDA, CUDA, 8 Mayıs 2013. 8. Sanders, J., Kandrot, E. (2011), CUDA By Example: An Introduction to General-Purpose GPU Programming, Addison-Wesley, NVIDIA Cooporation, 290s. 9. NVIDIA: CUDA C Programming Guide v5.0, 2012.http://docs.nvidia.com/cuda/pdf/CUDA_C_ Programming_Guide.pdf. 10. Kirk, D. B., Hwu, W. W. (2010), Programming Massively Parallel Processors, Elsevier, Morgan Kaufmann, 514s. 11. Rumpf, M., Strzodka, R. (2001), Level Set Segmentation in Graphics Hardware, IEEE International Conference on Image Processing (ICIP01), 3, 1103-1106. 12. Lefohn, A., Whitaker, R. (2002), A GPU-Based Three-Dimensional Level Set Solver with Curvature Flow, Technical Report UUCS-02- 017, University of Utah, Scholl of Computing. 13. Lefohn, A., Kniss, J. M., Hansen, C. D., Whitaker, R. T. (2004), A Streaming Narrow- Band Algorithm: Interactive Computation and Visualization of Level Sets, IEEE Transactions on Visualization and Computer Graphics, 10, 422-433. 14. The Insight Toolkit (ITK) 2003, http://www.itk.org, 8 Mayıs 2013. 15. Klar, O. (2007), Interactive GPU-based Segmentation of Large Medical Volume Data with Level-Sets, 11th Central European Siminar on Computer Graphics (CESCG07). 16. Hagan, A. Zhao, Y. (2009), Parallel 3D Image Segmentation of Large Data Sets on a GPU Cluster, 5th International Symposium on Visual Computing, 960-969. 17. Roberts, M., Packer, J., Sousa, M. C., Mitchell, J. R. (2010), A Work-Efficient GPU Algorithm for Level Set Segmentation, High Performance Graphics (HGP 10), 123-132. 18. Jalba, A.C., van der Laan, W.J., Roerdink, J. B. T. M. (2013), Fast Sparse Level Sets on Graphics Hardware, Visualization and Computer Graphics, 19 no:1, 30-44. 19. http://radiopaedia.org, 9 Mayıs 2013.