具有聚类结构相似性的非参数贝叶斯字典学习算法  

A Nonparametric Bayesian Dictionary Learning Algorithm with Clustering Structure Similarity

作　　者：董道广 芮国胜 田文飚 张洋 刘歌 DONG Daoguang;RUI Guosheng;TIAN Wenbiao;ZHANG Yang;LIU Ge(Signal and Information Processing Key Laboratory in Shandong,Navy Aviation University,Yantai 264001,China)

机构地区：[1]海军航空大学信号与信息处理山东省重点实验室,烟台264001

出　　处：《电子与信息学报》2020年第11期2765-2772,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(41606117,41476089,61671016)。

摘　　要：利用图像结构信息是字典学习的难点,针对传统非参数贝叶斯算法对图像结构信息利用不充分,以及算法运行效率低下的问题,该文提出一种结构相似性聚类beta过程因子分析(SSC-BPFA)字典学习算法。该算法通过Markov随机场和分层Dirichlet过程实现对图像局部结构相似性和全局聚类差异性的兼顾,利用变分贝叶斯推断完成对概率模型的高效学习,在确保算法收敛性的同时具有聚类的自适应性。实验表明,相比目前非参数贝叶斯字典学习方面的主流算法,该文算法在图像去噪和插值修复应用中具有更高的表示精度、结构相似性测度和运行效率。Making use of image structure information is a difficult problem in dictionary learning,the traditional nonparametric Bayesian algorithms lack the ability to make full use of image structure information,and faces problem of inefficiency.To this end,a dictionary learning algorithm called Structure Similarity Clustering-Beta Process Factor Analysis(SSC-BPFA)is proposed in this paper,which completes efficient learning of the probabilistic model via variational Bayesian inference and ensures the convergence and selfadaptability of the algorithm.Image denoising and inpainting experiments show that this algorithm has significant advantages in representation accuracy,structure similarity index and running efficiency compared with the existing nonparametric Bayesian dictionary learning algorithms.

关 键 词：变分贝叶斯 MARKOV随机场 字典学习 去噪 修复 

分 类 号：TN911.73[电子电信—通信与信息系统] TP301.6[电子电信—信息与通信工程]