Media Lab., MIT, Cambridge, MA.
IEEE Trans Image Process. 1997;6(2):268-84. doi: 10.1109/83.551697.
We develop, analyze, and apply a specific form of mixture modeling for density estimation within the context of image and texture processing. The technique captures much of the higher order, nonlinear statistical relationships present among vector elements by combining aspects of kernel estimation and cluster analysis. Experimental results are presented in the following applications: image restoration, image and texture compression, and texture classification.
我们开发、分析并应用了一种特定形式的混合模型，用于在图像处理和纹理处理的背景下进行密度估计。该技术通过结合核估计和聚类分析的方面，捕捉到了向量元素之间存在的许多高阶非线性统计关系。在以下应用中给出了实验结果：图像恢复、图像和纹理压缩以及纹理分类。
