Abstract
This paper presents a parallel image segmentation method based on self-organizing map (SOM) neural network by extending the authors’ former work from serial computation to parallel processing in order to accelerate the computation process. The parallel algorithm is composed of a group of parallel sub-algorithms for implementing the entire segmentation process, including parallel classification of the image into edge/non-edge pattern vectors, parallel training of an SOM network, and parallelly segmenting the image by using the trained SOM model with vector quantization approach. In the paper, the parallel algorithm is implemented on GPU with OpenCL program language and applied to segmenting the human brain MRI images. The experimental results obtained in the work showed that, compared with the original serial algorithm, the parallel algorithm can achieve a significant improvement on the computation efficiency with a speedup ratio of 64.72.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Gao, X.L., Wang, Z.L., Liu, J.W.: Algorithm for Image Segmentation using Statistical Models based on Intensity Features. Acta Optica Sinica 31(1), 1–6 (2011)
Zhao, J., Shao, F.Q., Zhang, X.D.: Vector-valued Images Segmentation based on Improved Variational GAC Model. Control and Decision 26(6), 909–915 (2011)
Wu, Y., Xiao, P., Wang, C.M.: Segmentation Algorithm for SAR Images based on the Persistence and Clustering in the Contourlet Domain. Acta Optica Sinica 30(7), 1977–1983 (2010)
Veksler, O.: Image Segmentation by Nested Cuts. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 339–344. IEEE Press (2000)
Wang, S., Lu, H.H., Yang, F.: Superpixel Tracking. In: Proc. of IEEE International Conference on Computer Vision, pp. 1323–1330. IEEE Press (2011)
De, A., Guo, C.: A Vector Quantization Approach for Image Segmentation Based on SOM Neural Network. In: Guo, C., Hou, Z.-G., Zeng, Z. (eds.) ISNN 2013, Part I. LNCS, vol. 7951, pp. 612–619. Springer, Heidelberg (2013)
Fitzgerald, D.F., Wills, D.S., Wills, L.M.: Real-time, parallel segmentation of high-resolution images on multi-core platforms. Journal of Real-Time Image Processing (May 31, 2014)
Farias, R., Farias, R., Marroquim, R., Clua, E.: Parallel Image Segmentation Using Reduction-Sweeps on Multicore Processors and GPUs. In: 2013 XXVI Conference on Graphics, Patterns and Images, Arequipa, Peru, pp. 139–146 (August 2013)
Dessai, V.S., Arakeri, M.P., Ram Mohana Reddy, G.: A parallel segmentation of brain tumor from magnetic resonance images. In: 2012 Third International Conference on Computing, Communication and Networking Technologies, Coimbatore, India (July 2012)
Luo, Z.Z., Shen, H.X.: Hermite Interpolation-based Wavelet Transform Modulus Maxima Reconstruction Algorithm’s Application to EMG De-noising. Journal of Electronics & Information Technology 31(4), 857–860 (2009)
Liu, B., Huang, L.J.: Multi-scale Fusion of Well Logging Data Based on Wavelet Modulus Maximum. Journal of China Coal Society 35(4), 645–649 (2010)
Gaster, B.R., Howes, L., et al.: Heterogeneous Computing with OpenCL. Elsevier(Inc.) (2012)
Munshi, A., Gaster, B.R., et al.: OpenCL Programming Guide. Pearson Education, Inc. (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
De, A., Zhang, Y., Guo, C. (2014). A Parallel Image Segmentation Method Based on SOM and GPU with Application to MRI Image Processing. In: Zeng, Z., Li, Y., King, I. (eds) Advances in Neural Networks – ISNN 2014. ISNN 2014. Lecture Notes in Computer Science(), vol 8866. Springer, Cham. https://doi.org/10.1007/978-3-319-12436-0_71
Download citation
DOI: https://doi.org/10.1007/978-3-319-12436-0_71
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12435-3
Online ISBN: 978-3-319-12436-0
eBook Packages: Computer ScienceComputer Science (R0)