GPGPU를 이용한 Fuzzy C-Means 알고리즘의 구현 및 성능분석
Implementation and Performance Analysis of Fuzzy C-Means Algorithm Using GPGPU
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
영상 분할은 의료 영상 처리에서 중요한 역할을 수행하지만 영상 분할 알고리즘의 많은 연산량은 실생활에서의 사용을 제약하는 요인이 된다. 따라서 본 논문에서는 본 논문에서는 고해상도 의료 영상 분할 알고리즘의 실시간 처리를 위해 GPGPU(general purpose graphics processing unit)상에서 영상 분할 알고리즘인 Fuzzy C-Means(FCM)의 병렬구현 방법을 제안한다. 본 논문에서는 GPU상에서 FCM 알고리즘의 고속화를 위해 대상 영상을 재구성하고, 단일 쉐이더 코어에서 필요한 레지스터 개수를 바탕으로 FCM 알고리즘을 위한 최적의 쓰레드(thread)와 블록(block)의 크기를 계산한다. 성능 평가를 위해 본 논문에서는 총 5가지 크기의 의료 영상(64×64, 128×128, 256×256, 512×512, 1,024×1,024)을 이용하여 단일 CPU대비 향상된 실행 시간을 측정하였고, 모의실험 결과 64x64 영상을 제외한 나머지 영상에서 단일 CPU 보다 약 4배 높은 실행 시간의 향상을 나타내었다.
Abstract
Image segmentation plays a crucial role in numerous biomedical imaging applications. However, its high computational complexities require substantial amount of time and have limited its use in real applications. With this reason, this paper implements a fuzzy c-means (FCM) clustering algorithm on general purpose graphics processing unit (GPGPU) in order to run it in real time. This paper first reconfigures a target medical image for real-time processing of FCM, and calculates optimal sizes of threads and blocks for FCM based on the number of registers required by a shader core. To evaluate the proposed approach on GPGPU, this paper measures execution times to complete FCM on GPGPU by utilizing medical images at different resolutions (64×64, 128×128, 256×256, 512×512, 1,024×1,024). Experimental results indicate that execution times on GPGPU are approximately 4-fold faster than those on a single CPU for all of medical images except an 64×64 medical image.
참고문헌 (24)
- M. F. Santarelli, "Real- Time Multimodal Medical Image Processing: A Dynamic Volume-Rendering Application", IEEE Transaction on Information Technology in Biomedicine, 1(3), pp.171~178 (1997)
- M. Smelyanskiy, "Mapping High-Fidelity Volume Rendering for Medical Imaging to CPU, GPU and Many-Core Architectures", IEEE Transaction on Visualization and Computer Graphics, 15(6) (2009)
- S. Krinidis, "A Robust Fuzzy Local Information C-Mans Clustering Algorithm", IEEE Transactions on Image Processing, 19(5), pp.1328~1337 (2010)
- N. Venu, "A Novel Multiplekernel Based Fuzzy c-means Algorithm with Spatial Information for Medical Image Segmentation", International Journal of Image Processing, 7(3) (2013)
- D. L. Pham, "A Survey of Current Methods in Medical Image Segmentation", Annual Review of Biomedical Engineering, 2, pp.315~337 (2000)
- J. C. Bezdek, "FCM: The Fuzzy C-means Clustering Algorithm", Computers and Geosciencs, 10(2), pp.191~203 (1984)
- P. K. Sahoo, "A Survey of thresholding techniques", Computer Vision, Graphics, and Image Processing, 41(2), pp.233~260 (1988)
- R. Dass, "Image segmentation techniques", International Journal of Electronics and Communication Technology, 3(1) (2012)
- J. C. Bezdek, "Review of MR image segmentation techniques using pattern recognition", Medical Physics, 20(4), pp.1033~1048 (1993)
- Y. Tan, "An Explicit Shape-constrained MRF-based Contour Evolution Method for 2D Medical Image Segmentation", IEEE Journal of Biomedical and Health Informatics, (99) (2013)
- J. Bezdek, "Pattern Recognition With Fuzzy Objective Function Algorithm" (1981), Plenum
- D. Pham, "An Adaptive Fuzzy C-Means Algorithm for Image Segmentation in The Presenece of Intensity Inhomogeneities", Pattern Recognition Letters, 20, pp.57~68 (1999)
- J. D.Owens, "GPU computing", Proceedings of IEEE, 96, pp.879~899 (2008)
- 윤민, "GPU를 이용한 Salsa20 스트림 암호의 병렬화", 한국차세대컴퓨팅학회 논문지, 5(1), pp.53~62 (2009), 한국차세대컴퓨팅학회
- 최홍준, "워프 스케쥴링 기법에 따른 GPU 성능 분석", 한국차세대컴퓨팅학회 논문지, 9(2), pp.54~66 (2013), 한국차세대컴퓨팅학회
- 쟌 느앗-프엉, "Cache Conscious Parallel Pattern Matching for Aho-Corasick Algorithm on a GPU", 한국차세대컴퓨팅학회 논문지, 8(1), pp.64~75 (2012), 한국차세대컴퓨팅학회
- B. Jang, "Exploiting Memory Access Patterns to Improve Memory Performance in Data-Parallel Architectures", IEEE Transactions on Parallel and Distributed System, 22(1) (2011)
- S. A. A. Shalom, "Graphics Hardware based Efficient and Scalable Fuzzy C-Means Clustering", Proceeding of 7th Australasian Data Mining Conference, 87, pp.87~ (2008)
- J. E. Stone, "OpenCL : A Parallel Programming Standard for Heterogeneous Computing Systems", Computing in Science and Engineering, 12(3), pp.66~73 (2010)
- "CUDA Programming Guide"[URL]
- Nyland, Lars, "Fast n-body simulation with cuda", GPU gems, 3, pp.677~695 (2007)
- A. Pangborn, "Scalable Data Clustering Using GPU Cluster", Concurrency Computation Practice and Experience, pp.1~24 (2011)
- "CUDA ZONE"[URL]
- Y. Zhang, "A Hybrid Image Segmentation Approach Using Watershed Transform and FCM", Fuzzy Systems and Knowledge Discovery, 4, pp.24~27 (2007)