• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection
【24h】

Learning Compositional Shape Models of Multiple Distance Metrics by Information Projection

机译：通过信息投影学习多距离度量的合成形状模型

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

This paper presents a novel compositional contour-based shape model by incorporating multiple distance metrics to account for varying shape distortions or deformations. Our approach contains two key steps: 1) contour feature generation and 2) generative model pursuit. For each category, we first densely sample an ensemble of local prototype contour segments from a few positive shape examples and describe each segment using three different types of distance metrics. These metrics are diverse and complementary with each other to capture various shape deformations. We regard the parameterized contour segment plus an additive residual ε as a basic subspace, namely, ε-ball, in the sense that it represents local shape variance under the certain distance metric. Using these ε-balls as features, we then propose a generative learning algorithm to pursue the compositional shape model, which greedily selects the most representative features under the information projection principle. In experiments, we evaluate our model on several public challenging data sets, and demonstrate that the integration of multiple shape distance metrics is capable of dealing various shape deformations, articulations, and background clutter, hence boosting system performance.
机译：本文提出了一种新颖的基于成分轮廓的形状模型，该模型通过合并多个距离量度来解决形状变化或变形的问题。我们的方法包含两个关键步骤：1）轮廓特征生成和2）生成模型追求。对于每个类别，我们首先从一些正形状示例中密集采样一组局部原型轮廓线段，然后使用三种不同类型的距离度量来描述每个线段。这些度量是多种多样的并且彼此互补以捕获各种形状变形。我们认为参数化轮廓线段加上一个加法残差ε作为基本子空间，即ε球，从某种意义上说，它表示在一定距离度量下的局部形状变化。以这些ε球为特征，我们提出了一种生成学习算法来追踪构图形状模型，该模型根据信息投影原理贪婪地选择了最具代表性的特征。在实验中，我们在几个公开的具有挑战性的数据集上评估了我们的模型，并证明了多个形状距离度量的集成能够处理各种形状变形，清晰度和背景混乱，从而提高了系统性能。

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