The lattice Boltzmann (LB) model has advantages of simple programming and faster operation, but for images with low contrast and noise, segmentation may fail. This paper proposes a novel LB model using local statistical region information. As the method can enhance contrast of the object and background, and reduce noise, it provides improved delineation accuracy. To verify effectiveness of the model, comparison experiments among the existing LB model, level set models and the proposed model are made, using real magnetic resonance (MR) images. Dice coefficient and Hausdorf distance are used as the measurement index. The results show that the proposed model produces segmentation results with precision 10 times better than the existing LB method. In addition, the computing speed is 3 times faster than level set models.
WEN Jun-ling, YAN Zhuang-zhi, JIANG Jie-hui
. A Lattice Boltzmann Model with Statistic Region Information for Image Segmentation[J]. Journal of Applied Sciences, 2016
, 34(1)
: 49
-57
.
DOI: 10.3969/j.issn.0255-8297.2016.01.006
[1] Bhansali B, Tiwari S, Agrawal S. Hybrid method for image segmentation[J]. International Journal of Computer Science and Information Technologies, 2015, 6(1):514-518.
[2] Chen J, Chai Z, Shi B, Zhang W. Lattice Boltzmann method for filtering and contour detection of the natural images[J]. Computers & Mathematics with Applications, 2014, 68(3):257-268.
[3] Chen Y, Navarro L, Wang Y. Segmentation of the thrombus of giant intracranial aneurysms from CT angiography scans with lattice Boltzmann method[J]. Medical Image Analysis, 2014, 18(1):1-8.
[4] Wen J, Yan Z, Jiang J. Novel lattice Boltzmann method based on integrated edge and region information for medical image segmentation[J]. Bio-medical Materials and Engineering, 2014, 24(1):1247-1252.
[5] Shi B, Deng B, Du R. A new scheme for source term in LBGK model for convection diffusion equation[J]. Computers & Mathematics with Applications, 2008, 55(7):1568-1575.
[6] Hagan A, Zhao Y. Parallel 3D image segmentation of large data sets on a GPU cluster[C]//Springer Proceedings of the 5th International Symposium on Advances in Visual Computing:Part II, 2009:960-969.
[7] Wang Z, Yan Z, Chen G. Lattice Boltzmann method of active contour for image segmentation[C]//Sixth International Conference on Image and Graphics, 2011:338-343.
[8] Balla-Arabe S, Gao X, Wang B. A fast and robust level set method for image segmentation using fuzzy clustering and lattice Boltzmann method[J]. IEEE Transactions on Systems Man & Cybernetics, 2013, 43(3):910-920.
[9] Yan Z, Sun Y, Jiang J, Wen J. Novel explanation, modeling and realization of lattice Boltzmann methods for image processing[J]. Multidimensional Systems and Signal Processing, 2015, 26(3):645-663.
[10] 郭照立,郑楚光. 格子Boltzmann方法的原理及应用[M]. 北京:科学出版社,2009.
[11] Zhu S, Yuille A. Region competition:unifying snakes, region growing, and Bayes/MDL for multiband image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(9):884-900.
[12] Zhang K, Zhang L, Zhang S. A variational multiphase level set approach to simultaneous segmentation and bias correction[C]//17th IEEE International Conference on Image Processing (ICIP), 2010:4105-4108.
[13] Li C, Huang R, Ding Z. A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI[J]. IEEE Transactions on Image Processing, 2011, 20(7):2007-2016.
[14] Frisch U, D'humieres D, Hasslacher B. Lattice gas hydrodynamics in two and three dimensions[J]. Complex Systems, 1987, 1(4):649-707.
