Gaussian-Mixture-Model-Based Spatial Neighborhood Relationships for Pixel Labeling Problem
Gaussian-Mixture-Model-Based Spatial Neighborhood Relationships for Pixel Labeling Problem
复制标题
DOI：
10.1109/tsmcb.2011.2161284
复制
发表时间：
2012-02
期刊：
影响因子：
--
通讯作者：
T. Nguyen;Q. M. J. Wu
中科院分区：
文献类型：
--
作者：
T. Nguyen;Q. M. J. Wu
提出了一种新的基于标准高斯混合模型(GMM)的像素标记和图像分割算法。与标准GMM不同，标准GMM认为像素本身是相互独立的，不考虑相邻像素之间的空间关系，而是将这种空间关系融入标准GMM中。此外，与基于马尔可夫随机场的模型相比，该模型需要的参数更少。为了从观测值估计模型参数，我们不使用期望最大化算法，而是使用梯度法最小化数据负对数似然的上界。将该模型与基于标准GMM和马尔可夫随机场的方法进行了比较，证明了该方法的稳健性、准确性和有效性。
In this paper, we present a new algorithm for pixel labeling and image segmentation based on the standard Gaussian mixture model (GMM). Unlike the standard GMM where pixels themselves are considered independent of each other and the spatial relationship between neighboring pixels is not taken into account, the proposed method incorporates this spatial relationship into the standard GMM. Moreover, the proposed model requires fewer parameters compared with the models based on Markov random fields. In order to estimate model parameters from observations, instead of utilizing an expectation-maximization algorithm, we employ gradient method to minimize a higher bound on the data negative log-likelihood. The performance of the proposed model is compared with methods based on both standard GMM and Markov random fields, demonstrating the robustness, accuracy, and effectiveness of our method.