eISSN:2278-5299

International Journal of Latest Research in Science and Technology

DOI:10.29111/ijlrst   ISRA Impact Factor:3.35

A News Letter Sign UP!
FAST PARALLEL CONNECTED COMPONENT LABELING ALGORITHMS USING CUDA BASED ON 8-DIRECTIONAL LABEL SELECTION

Research Paper Open Access

International Journal of Latest Research in Science and Technology Vol.3 Issue 2, pp 187-190,Year 2014

FAST PARALLEL CONNECTED COMPONENT LABELING ALGORITHMS USING CUDA BASED ON 8-DIRECTIONAL LABEL SELECTION

Youngsung Soh, Hadi Ashraf, Yongsuk Hae, Intaek Kim

Correspondence should be addressed to :

Received : 25 April 2014; Accepted : 28 April 2014 ; Published : 30 April 2014

Share
Download 125
View 177
Article No. 10301
Abstract

Connected component labeling (CCL) is a key step in image segmentation where foreground pixels are extracted and labeled. Sequential CCL is a computationally expensive operation and thus is often done within parallel processing framework to reduce execution time. Various parallel CCL methods have been proposed in the literature. Among them NSZ label equivalence (NSZ-LE) method seemed to perform best. In this paper we propose two new parallel CCL algorithms based on 8-directional label selection and show that they run 3 to 10 times faster than NSZ-LE depending on the characteristics of images.

Key Words   
Connected Component labeling, CUDA, GPU, Parallel
Copyright
References
  1. Wu, E. Otoo, and K. Suzuki, “Optimizing two-pass connected-component labeling algorithms,” Pattern Analysis & Applications, vol. 2, pp. 117-135, 2009.
  2. Suzuki, I. Horiba, and N. Sugie, “Linear-time connected-component labeling based on sequential local operations,” Computer Vision and Image Understanding, vol. 1, pp.1–23, 2003.
  3. Rosenfeld and A. Kak, Digital Picture Processing, Academic Press, Orlando, 1982.
  4. Farber, CUDA Application Design and Development, Elsevier, Waltham, 2011
  5. Kalentev, A. Rai, S. Kemnitz, and R. Schneider, “Connected component labeling on a 2D grid using CUDA,” J. Parallel Distributed Computing, pp. 615-620, 2011.
  6. Chang, C. Chen, and C. Lu, “A linear-time Component-labeling algorithm using contour tracing technique,” Computer Vision Image Understanding, vol. 2, pp. 206-220, 2004.
  7. Hawick, A. Leist, and D. Playne, “Parallel graph component labeling with GPUs and CUDA,” Parallel Computing, vol. 12, pp. 655-678, 2010.
To cite this article

Youngsung Soh, Hadi Ashraf, Yongsuk Hae, Intaek Kim , " Fast Parallel Connected Component Labeling Algorithms Using Cuda Based On 8-directional Label Selection ", International Journal of Latest Research in Science and Technology . Vol. 3, Issue 2, pp 187-190 , 2014


Responsive image

MNK Publication was founded in 2012 to upholder revolutionary ideas that would advance the research and practice of business and management. Today, we comply with to advance fresh thinking in latest scientific fields where we think we can make a real difference and growth now also including medical and social care, education,management and engineering.

Responsive image

We offers several opportunities for partnership and tie-up with individual, corporate and organizational level. We are working on the open access platform. Editors, authors, readers, librarians and conference organizer can work together. We are giving open opportunities to all. Our team is always willing to work and collaborate to promote open access publication.

Responsive image

Our Journals provide one of the strongest International open access platform for research communities. Our conference proceeding services provide conference organizers a privileged platform for publishing extended conference papers as journal publications. It is deliberated to disseminate scientific research and to establish long term International collaborations and partnerships with academic communities and conference organizers.