出版方 ： Academic Press Inc., 6277 Sea Harbor Drive, Orlando, FL 32887-4900, United States

作　　者： ;

机构地区： 中国科学院

出　　处： 《可视通信与图像显示杂志》

摘　　要： 在这份报纸，我们在场一条途径基于概率的潜伏的语义分析(PLSA ) 到完成自动图象注解和检索的任务。以便精确为训练数据建模，每幅图象作为一包视觉词被代表。然后，一个概率的框架被设计分别地从视觉、文本的形式捕获语义方面。而且，一个适应不对称的学习算法被建议熔化这些方面。为每个图象文件，不同形式的方面分布被乘不同重量熔化，它由图象的视觉代表是坚定的。因而，因为它适当地联系视觉、文本的形式，概率的框架能为未看见的图象精确预言语义注解。我们把我们的途径与标准 Corel 数据集的几条最先进的途径作比较。试验性的结果证明我们的途径更有效地并且精确地表现。 In this paper, we present an approach based on probabilistic latent semantic analysis (PLSA) to achieve the task of automatic image annotation and retrieval. In order to model training data precisely, each image is represented as a bag of visual words. Then a probabilistic framework is designed to capture semantic aspects from visual and textual modalities, respectively. Furthermore, an adaptive asymmetric learning algorithm is proposed to fuse these aspects. For each image document, the aspect distributions of different modalities are fused by multiplying different weights, which are determined by the visual representations of images. Consequently, the probabilistic framework can predict semantic annotation precisely for unseen images because it associates visual and textual modalities properly. We compare our approach with several state-of-the-art approaches on a standard Corel dataset. The experimental results show that our approach performs more effectively and accurately. © 2010 Elsevier Inc. All rights reserved.

关 键 词： 自动图象注解 潜伏的方面模型 适应不对称的学习 图象检索 语义差距 视觉特征 文本的词

分 类 号： [TN91]