...
首页> 外文期刊>IEEE Transactions on Signal Processing >Unsupervised statistical neural networks for model-based object recognition
【24h】

Unsupervised statistical neural networks for model-based object recognition

机译:无监督统计神经网络用于基于模型的对象识别

获取原文
获取原文并翻译 | 示例
           

摘要

Statistical neural networks executing soft-decision algorithms have been shown to be very effective in many classification problems. A neural network architecture is developed here that can perform unsupervised joint segmentation and labeling of objects in images. We propose the semi-parametric hierarchical mixture density (HMD) model as a tool for capturing the diversity of real world images and pose the object recognition problem as a maximum likelihood (ML) estimation of the HMD parameters. We apply the expectation-maximization (EM) algorithm for this purpose and utilize ideas and techniques from statistical physics to cast the problem as the minimization of a free energy function. We then proceed to regularize the solution thus obtained by adding smoothing terms to the objective function. The resulting recursive scheme for estimating the posterior probabilities of an object's presence in an image corresponds to an unsupervised feedback neural network architecture. We present here the results of experiments involving recognition of traffic signs in natural scenes using this technique.
机译:执行软决策算法的统计神经网络已被证明在许多分类问题中非常有效。这里开发了一种神经网络体系结构,可以执行无监督的关节分割和图像中对象的标记。我们提出了半参数分层混合密度(HMD)模型,作为捕获现实世界图像多样性的工具,并将对象识别问题作为HMD参数的最大似然(ML)估计提出。为此,我们应用了期望最大化(EM)算法,并利用统计物理学的思想和技术将问题归结为自由能函数的最小化。然后,我们通过对目标函数添加平滑项来规范化由此获得的解决方案。用于估计图像中对象存在的后验概率的所得递归方案对应于无监督反馈神经网络体系结构。我们在此介绍使用此技术在自然场景中识别交通标志的实验结果。

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