文章基本信息

标题：Image Hierarchical Representations Models based on Latent Dirichlet Allocation
本地全文：下载
作者：WANG, Fushun ; LI, Yan ; SUN, Xiaohua 等
期刊名称：Journal of Multimedia
印刷版ISSN：1796-2048
出版年度：2013
卷号：8
期号：4
页码：358-364
DOI：10.4304/jmm.8.4.358-364
语种：English
出版社：Academy Publisher
摘要：Existing image layer representations methods are very feed-forward, and then not able to deal with small ambiguities. A probabilistic model is proposed, and it learns and deduces each layer in that hierarchy together. Therefore, we consider a recursive probabilistic decomposition process, and derive a new yielded method based on recursive Latent Dirichlet Allocation. We show 2 significant properties of the novel probabilistic method: 1) pulsing another hierarchical to represent the enhanced results on that smooth method; 2) an entire Bayesian method beats a feed-forward running of the novel method. The method can be evaluated on a criterion recognition dataset. It takes the probability of recursive decomposition process into account, and obtains multilayer structure pyramid LDA derived model through the derivation. Experiments demonstrate that the novel technique beats existing hierarchical approaches, and present better performance
关键词：Image Hierarchical Representation;Feed-forward;Probabilistic Model;Latent Dirichlet Allocation (LDA)