摘要
针对传统EM算法存在估计参数不具有最优性,以及在参数估计中需要人工参与等问题,提出一种基于高斯混合模型的改进EM算法。采用无人工参与的无监督思想,获取高斯混合模型对直方图拟合的最优参数组合。实验表明,该算法不仅能够快速地估计模型参量,而且能够给出最优参数,并在图像增强中使细节更明显,对比度更适中。
In order to solve the disadvantages of traditional expectation maximization (EM) a gorithm which lacks parameters optimization and needs human operation when estimating pa- rameters, an improved EM algorithm based on Gaussian mixture model was proposed. The un- supervised theory was used to calculate optimal Gaussian mixture model parameters. The sub- jective and objective indices of experiments show that the algorithm can not only estimate pa- rameters quickly but also figure out the optimal parameters, making the detail more obvious and the contrast more moderate in image enhancement application.
出处
《应用光学》
CAS
CSCD
北大核心
2013年第6期985-989,共5页
Journal of Applied Optics
关键词
EM算法
高斯混合模型
图像增强
EM algorithm
Gaussian mixture model
image enhancement