Expectation-maximization algorithm with local adaptivity

Shing-Yu Leung Gang Liang Knut Solna Hongkai Zhao

Statistics Theory and Methods mathscidoc:1912.43190

IAM J. Imaging Sci., 2, (3), 834-857, 2009.7
We develop an expectation-maximization algorithm with local adaptivity for image segmentation and classification. The key idea of our approach is to combine global statistics extracted from the Gaussian mixture model or other proper statistical models with local statistics and geometrical information, such as local probability distribution, orientation, and anisotropy. The combined information is used to design an adaptive local classification strategy that improves the robustness of the algorithm and also keeps fine features in the image. The proposed methodology is flexible and can be easily generalized to deal with other inferred information/quantities and statistical methods/models.
No keywords uploaded!
[ Download ] [ 2019-12-21 11:28:35 uploaded by Shing_Yu_Leung ] [ 519 downloads ] [ 0 comments ]
  title={Expectation-maximization algorithm with local adaptivity},
  author={Shing-Yu Leung, Gang Liang, Knut Solna, and Hongkai Zhao},
  booktitle={IAM J. Imaging Sci.},
Shing-Yu Leung, Gang Liang, Knut Solna, and Hongkai Zhao. Expectation-maximization algorithm with local adaptivity. 2009. Vol. 2. In IAM J. Imaging Sci.. pp.834-857. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20191221112835393184750.
Please log in for comment!
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved