Local Autoencoding for Parameter Estimation in a Hidden Potts-Markov Random Field
Song SM(宋三明); Si BL(斯白露); Herrmann, J. Michael; Feng XS(封锡盛)
刊名IEEE Transactions on Image Processing
2016
卷号25期号:5页码:2324-2336
关键词Markov Random Field Gibbs Distribution Parameters Estimation Local Autoencoding Potts Model
ISSN号1057-7149
产权排序1
英文摘要

A local-autoencoding (LAE) method is proposed for the parameter estimation in a Hidden Potts-Markov random field model. Due to sampling cost, Markov chain Monte Carlo methods are rarely used in real-time applications. Like other heuristic methods, LAE is based on a conditional independence assumption. It adapts, however, the parameters in a block-by-block style with a simple Hebbian learning rule. Experiments with given label fields show that the LAE is able to converge in far less time than required for a scan. It is also possible to derive an estimate for LAE based on a Cramer-Rao bound that is similar to the classical maximum pseudolikelihood method. As a general algorithm, LAE can be used to estimate the parameters in anisotropic label fields. Furthermore, LAE is not limited to the classical Potts model and can be applied to other types of Potts models by simple label field transformations and straightforward learning rule extensions. Experimental results on image segmentations demonstrate the efficiency and generality of the LAE algorithm.

WOS关键词IMAGE SEGMENTATION ; EM PROCEDURES ; MODEL ; ALGORITHM ; SONAR ; LIKELIHOOD ; NETWORKS ; CHAINS
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000374551200008
资助机构National Natural Science Foundation of China under Grant 41506121, in part by the China Post-Doctoral Science Foundation under Grant 2014M561266, in part by the Jiang Xinsong Innovation Fund under Grant Y4FC012901, in part by the State Key Laboratory of Robotics under Grant Y5A1203901, in part by the Distinguished Young Scholar Project of the Talents Program of China under Grant Y5A1370101, in part by the Doctoral Scientific Research Foundation of Liaoning Province under Grant 201501035, and in part by the Project Research and Development Center for Underwater Construction Robotics within the Ministry of Ocean and Fisheries through the Korea Institute of Marine Science and Technology Promotion, Korea, under Grant PJT200539.
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/18625]  
专题沈阳自动化研究所_水下机器人研究室
通讯作者Song SM(宋三明); Si BL(斯白露); Feng XS(封锡盛)
作者单位1.Institute of Perception, Action and Behavior, University of Edinburgh, Edinburgh, United Kingdom
2.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式
GB/T 7714
Song SM,Si BL,Herrmann, J. Michael,et al. Local Autoencoding for Parameter Estimation in a Hidden Potts-Markov Random Field[J]. IEEE Transactions on Image Processing,2016,25(5):2324-2336.
APA Song SM,Si BL,Herrmann, J. Michael,&Feng XS.(2016).Local Autoencoding for Parameter Estimation in a Hidden Potts-Markov Random Field.IEEE Transactions on Image Processing,25(5),2324-2336.
MLA Song SM,et al."Local Autoencoding for Parameter Estimation in a Hidden Potts-Markov Random Field".IEEE Transactions on Image Processing 25.5(2016):2324-2336.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace