• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on >Evidence-Driven Image Interpretation by Combining Implicit and Explicit Knowledge in a Bayesian Network
【24h】

Evidence-Driven Image Interpretation by Combining Implicit and Explicit Knowledge in a Bayesian Network

机译：贝叶斯网络中内隐与外显知识相结合的证据驱动图像解释

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Computer vision techniques have made considerable progress in recognizing object categories by learning models that normally rely on a set of discriminative features. However, in contrast to human perception that makes extensive use of logic-based rules, these models fail to benefit from knowledge that is explicitly provided. In this paper, we propose a framework that can perform knowledge-assisted analysis of visual content. We use ontologies to model the domain knowledge and a set of conditional probabilities to model the application context. Then, a Bayesian network is used for integrating statistical and explicit knowledge and performing hypothesis testing using evidence-driven probabilistic inference. In addition, we propose the use of a focus-of-attention (FoA) mechanism that is based on the mutual information between concepts. This mechanism selects the most prominent hypotheses to be verified/tested by the BN, hence removing the need to exhaustively test all possible combinations of the hypotheses set. We experimentally evaluate our framework using content from three domains and for the following three tasks: 1) image categorization; 2) localized region labeling; and 3) weak annotation of video shot keyframes. The results obtained demonstrate the improvement in performance compared to a set of baseline concept classifiers that are not aware of any context or domain knowledge. Finally, we also demonstrate the ability of the proposed FoA mechanism to significantly reduce the computational cost of visual inference while obtaining results comparable to the exhaustive case.
机译：通过学习通常依赖于一组区分特征的模型，计算机视觉技术在识别对象类别方面取得了长足的进步。但是，与广泛使用基于逻辑的规则的人类感知相反，这些模型无法从明确提供的知识中受益。在本文中，我们提出了一个可以执行视觉内容的知识辅助分析的框架。我们使用本体对领域知识建模，并使用一组条件概率来对应用程序上下文进行建模。然后，将贝叶斯网络用于整合统计知识和显式知识，并使用循证驱动的概率推断进行假设检验。此外，我们建议使用基于概念之间相互信息的关注焦点（FoA）机制。这种机制选择了要由国阵验证/检验的最突出的假设，因此无需彻底测试假设集的所有可能组合。我们使用来自三个领域的内容以及以下三个任务，对我们的框架进行实验性评估：1）图像分类； 2）局部区域标签；和3）视频镜头关键帧的弱注释。与一组不了解任何上下文或领域知识的基线概念分类器相比，所获得的结果证明了性能的提高。最后，我们还证明了所提出的FoA机制能够显着降低视觉推理的计算成本，同时获得与详尽案例相当的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号