用于图像分割的局部区域一致性流形约束MRF模型
|
摘要
针对区域马尔可夫随机场(MRF)模型难以有效描述图像复杂先验知识的问题,提出一种基于局部区域一致性流形约束MRF(LRCMC-MRF)模型.首先,所提模型利用高维数据的低维流形分布表征图像局部区域的复杂几何结构先验,建立图像局部区域的流形先验约束;其次,基于Pairwise MRF模型,建立一种包含更多图像局部信息的局部空间自适应MRF模型;最后,基于贝叶斯理论,将复杂局部区域几何结构先验和局部空间自适应统计特征融合,利用Gibbs采样算法对所提出模型进行优化.实验结果表明,与基于常规区域的MRF模型相比,所提出的分割算法具有较好的分割效果.
Region-based Markov random fields(MRF) is usually difficult to effectively describe the prior knowledge of complex natural images. To solve this problem, a local region consistency manifold constrained MRF(RCMC-MRF)model is proposed. Firstly, the proposed model uses low-dimensional manifold distribution of high-dimensional data to characterize complex geometry structure prior in local region of images, and builds a localized manifold prior constraints term for the image segmentation model. Then, the proposed model utilizes more local region information of images to construct a local spatial adaptive MRF based on the pairwise MRF. Finally, the complex geometry structure prior and local spatial adaptive statistical feature in the local region are incorporated according to the Bayesian theory. The Gibbs sample algorithm is used for optimization. Compared with the conventional region-based MRF model, experimental result shows that the proposed model can provide a better segmentation result.
Region-based Markov random fields(MRF) is usually difficult to effectively describe the prior knowledge of complex natural images. To solve this problem, a local region consistency manifold constrained MRF(RCMC-MRF)model is proposed. Firstly, the proposed model uses low-dimensional manifold distribution of high-dimensional data to characterize complex geometry structure prior in local region of images, and builds a localized manifold prior constraints term for the image segmentation model. Then, the proposed model utilizes more local region information of images to construct a local spatial adaptive MRF based on the pairwise MRF. Finally, the complex geometry structure prior and local spatial adaptive statistical feature in the local region are incorporated according to the Bayesian theory. The Gibbs sample algorithm is used for optimization. Compared with the conventional region-based MRF model, experimental result shows that the proposed model can provide a better segmentation result.
引文
[1] Kohli P, Kumar M P, Torr P H S. P3&beyond:Move making algorithms for solving higher order functions[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2009, 31(9):1645-1656.
[2]余淼,胡占义.高阶马尔科夫随机场及其在场景理解中的应用[J].自动化学报, 2015, 41(7):1213-1234.(Yu M, Hu Z Y. Higher-order Markov random fields and their applications in scene understanding[J]. Acta Automatica Sinica, 2015, 41(7):1213-1234.)
[3] Diplaros A, Vlassis N, Gevers T. A spatially constrained generative model and an EM algorithm for image segmentation[J]. IEEE Trans on Neural Networks, 2007,18(3):798-808.
[4]宋艳涛,纪则轩,孙权森.基于图像片马尔科夫随机场的脑MR图像分割算法[J].自动化学报, 2014(8):1754-1763.(Song Y T, Ji Z X, Sun Q S. Brain MR image segmentation algorithm based on Markov random field with image patch[J]. Acta Automatica Sinica, 2014(8):1754-1763.)
[5]徐胜军,韩九强,刘光辉,等.基于局部空间自适应MRF模型的图像分割[J].控制与决策, 2013, 28(6):889-893.(Xu S J, Han J Q, Liu G H, et al. Image segmentation based on local spatial adaptive markov random field model[J].Control and Decision, 2013, 28(6):889-893.)
[6] Yan S C, Xu D, Zhang B Y, et al. Graph embedding and extensions:A general framework for dimensionality reduction[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(1):40-51.
[7] He X F, Cai D, Shao Y L, et al. Laplacian regularized gaussian mixture model for data clustering[J]. IEEE Trans on Knowledge&Data Engineering, 2011, 23(9):1406-1418.
[8] Liu J, Cai D, He X. Gaussian mixture model with local consistency[C]. The 24th AAAI Conf on Artificial Intelligence. Atlanta:AAAI Press, 2010:512-517.
[9] Fisher J, Lin D. Manifold guided composite of Markov random fields for image modeling[C]. 2012 IEEE Computer Vision and Pattern Recognition. Providence:IEEE Press, 2012:2176-2183.
[10] Chung F R K. Spectral graph theory, CBMS regional conference series in mathematics[M]. Providence RI:AMS, 1997:1-21.
[11]张震,汪斌强,李向涛,等.基于近邻传播学习的半监督流量分类方法[J].自动化学报, 2013, 39(7):1100-1109.(Zhang Z, Wang B Q, Li X T, et al. Semi-supervised traffic identification based on affinity propagation[J]. Acta Automatica Sinica, 2013, 39(7):1100-1109.)
[12] Li S Z. Markov random field modeling in computer vision[M]. New York:Springer-Verlag, 2001:13-16.
[2]余淼,胡占义.高阶马尔科夫随机场及其在场景理解中的应用[J].自动化学报, 2015, 41(7):1213-1234.(Yu M, Hu Z Y. Higher-order Markov random fields and their applications in scene understanding[J]. Acta Automatica Sinica, 2015, 41(7):1213-1234.)
[3] Diplaros A, Vlassis N, Gevers T. A spatially constrained generative model and an EM algorithm for image segmentation[J]. IEEE Trans on Neural Networks, 2007,18(3):798-808.
[4]宋艳涛,纪则轩,孙权森.基于图像片马尔科夫随机场的脑MR图像分割算法[J].自动化学报, 2014(8):1754-1763.(Song Y T, Ji Z X, Sun Q S. Brain MR image segmentation algorithm based on Markov random field with image patch[J]. Acta Automatica Sinica, 2014(8):1754-1763.)
[5]徐胜军,韩九强,刘光辉,等.基于局部空间自适应MRF模型的图像分割[J].控制与决策, 2013, 28(6):889-893.(Xu S J, Han J Q, Liu G H, et al. Image segmentation based on local spatial adaptive markov random field model[J].Control and Decision, 2013, 28(6):889-893.)
[6] Yan S C, Xu D, Zhang B Y, et al. Graph embedding and extensions:A general framework for dimensionality reduction[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(1):40-51.
[7] He X F, Cai D, Shao Y L, et al. Laplacian regularized gaussian mixture model for data clustering[J]. IEEE Trans on Knowledge&Data Engineering, 2011, 23(9):1406-1418.
[8] Liu J, Cai D, He X. Gaussian mixture model with local consistency[C]. The 24th AAAI Conf on Artificial Intelligence. Atlanta:AAAI Press, 2010:512-517.
[9] Fisher J, Lin D. Manifold guided composite of Markov random fields for image modeling[C]. 2012 IEEE Computer Vision and Pattern Recognition. Providence:IEEE Press, 2012:2176-2183.
[10] Chung F R K. Spectral graph theory, CBMS regional conference series in mathematics[M]. Providence RI:AMS, 1997:1-21.
[11]张震,汪斌强,李向涛,等.基于近邻传播学习的半监督流量分类方法[J].自动化学报, 2013, 39(7):1100-1109.(Zhang Z, Wang B Q, Li X T, et al. Semi-supervised traffic identification based on affinity propagation[J]. Acta Automatica Sinica, 2013, 39(7):1100-1109.)
[12] Li S Z. Markov random field modeling in computer vision[M]. New York:Springer-Verlag, 2001:13-16.