作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2020, Vol. 46 ›› Issue (4): 220-227. doi: 10.19678/j.issn.1000-3428.0054582

• 图形图像处理 • 上一篇    下一篇

面向图像先验建模的可扩展高斯混合模型

张墨华1,2, 彭建华1   

  1. 1. 国家数字交换系统工程技术研究中心, 郑州 450002;
    2. 河南财经政法大学 计算机与信息工程学院, 郑州 450002
  • 收稿日期:2019-04-11 修回日期:2019-05-12 出版日期:2020-04-15 发布日期:2020-04-07
  • 作者简介:张墨华(1979-),男,副教授、博士,主研方向为图像处理、机器学习、智能信息处理;彭建华,教授。
  • 基金资助:
    国家自然科学基金(61841702);河南省科技攻关计划(1521002210087,202102210371);河南省教育厅科学技术研究重点项目(14A520040)。

Extensible Gaussian Mixture Model for Image Prior Modeling

ZHANG Mohua1,2, PENG Jianhua1   

  1. 1. National Digital Switching System Engineering and Technological Research Center, Zhengzhou 450000, China;
    2. College of Computer and Information Engineering, Henan University of Economics and Law, Zhengzhou 450000, China
  • Received:2019-04-11 Revised:2019-05-12 Online:2020-04-15 Published:2020-04-07

摘要: 针对使用高斯混合模型的图像先验建模中分量数目难以扩展的问题,构建基于狄利克雷过程的可扩展高斯混合模型。通过聚类分量的新增及归并机制,使模型复杂度根据数据规模自适应变化,从而增强先验模型结构的紧密度,以提升其可解释性。此外,对高斯混合模型的推理过程进行优化,给出一种基于批次处理方式的可扩展变分推理算法,求解图像去噪中所有隐变量的变分后验分布,实现先验学习。实验结果表明,该模型在图像去噪任务中较EPLL等传统去噪模型能够取得更高的峰值信噪比,去噪效果更佳,验证了该模型的有效性。

关键词: 先验建模, 高斯混合模型, 狄利克雷过程, 图像去噪, 批次处理

Abstract: To address the inextensible fixed number of components in image prior modeling based on Gaussian Mixture Model(GMM),this paper proposes an extensible GMM model based on Dirichlet Process(DP).Through the addition and merging mechanism of cluster components,the model complexity can adaptively vary with data scaling,making the structure of the learnt prior model more compact to improve its interpretability.Also,to improve the inference of the proposed model,a scalable variational inference algorithm using batch processing is proposed to solve the variational distribution of all hidden variables for prior learning.Experimental results demonstrates that the proposed model has better denoising performance than EPLL and other traditional models with a higher Peak Signal-to-Noise Ratio(PSNR) in image denoising tasks,which proves its effectiveness.

Key words: prior modeling, Gaussian Mixture Model(GMM), Dirichlet Process(DP), image denoising, batch processing

中图分类号: