Two-Phase Image Segmentation with Nonlocal Mean Filter and Kernel Evolutionary Clustering in Local Learning

Abstract:

In this study, a novel two-phase image segmentation algorithm (TPIS) by using nonlocal mean filter and kernel evolutionary clustering in local learning is proposed. Currently, the difficulties for image segmentation lie in its vast pixels with overlapping characteristic and the noise in the different process of imaging. Here, we want to use nonlocal mean filter to remove different types of noise in the image, and then, two kernel clustering indices are designed in evolutionary optimization. Besides, the local learning strategy is designed using local coefficient of variation of each local pixels or image patch is employed to update the quality of the local segments. The new algorithm is used to solve different image segmentation tasks. The experimental results show that TPIS is competent for segmenting majority of the test images with high quality.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 172-175
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.172
• Online since: April 2014
• Authors: Bing Chen, Dong Dong Yang*, Gang Lu, Hong Xiao Feng
• Keywords: Image Recognition, Image Segmentation, Local Learning, Nonlocal Mean Filter

References

[1] S. Krinidis, and V. Chatzis: IEEE Trans. on Image Processing, vol. 19, no. 5, pp.1328-1337, (2010).

[2] X. R Zhang, L.C. Jiao, F. Liu, and M. G Gong: IEEE Trans. on Geoscience and Remote Sensing, vol. 46, no. 7, p.2126–2136, (2008).

[3] C. Lemarechal, R. Fjortoft, P. Marthon, E. Cubero-Castan, A. Lopes, in: Proceeding of the SPIE, vol. 3497, 1998, p.111–121.

DOI: 10.1117/12.331343

[4] D.D. Yang, L.C. Jiao, M.G. Gong, and F. Liu: Information Sciences, vol. 181, no. 13, pp.2797-2812, (2011).

[5] M. G. Gong, Y. Liang, J. Shi, W. P Ma, and J.J. Ma: IEEE Trans. on Image Processing, vol. 22, no. 2, pp.573-584, (2013).

[6] A. Buades, B. Coll, J.M. Morel: Multiscale Modeling and Simulation, vol. 4, no. 2, p.490–530, (2005).