Weighted and robust learning of subspace representations
Weighted and robust learning of subspace representations
复制标题
DOI：
10.1016/j.patcog.2006.09.019
复制
发表时间：
2007-05-01
影响因子：
8
通讯作者：
Bischof, Horst
中科院分区：
文献类型：
--
作者：
Skocaj, Danijel;Leonardis, Ales;Bischof, Horst
一个可靠的视觉学习和识别系统应该能够有选择地处理输入数据的各个部分，并成功地处理噪声和遮挡。这些要求不能令人满意地满足时，视觉学习接近基于外观的建模的对象和场景，使用传统的PCA方法。在本文中，我们扩展了标准PCA方法来克服这些缺点。首先，我们提出了一个加权版本的PCA，这与标准的方法，认为个别像素和图像选择性，根据相应的权重。然后，我们提出了一个强大的PCA方法，以获得一致的子空间表示在训练图像中的离群像素的存在。该方法是基于EM算法估计的主子空间中存在的缺失数据。我们证明了所提出的方法在一些实验的效率。(c)2006模式识别学会。由爱思唯尔有限公司出版。保留所有权利。
A reliable system for visual learning and recognition should enable a selective treatment of individual parts of input data and should successfully deal with noise and occlusions. These requirements are not satisfactorily met when visual learning is approached by appearance-based modeling of objects and scenes using the traditional PCA approach. In this paper we extend standard PCA approach to overcome these shortcomings. We first present a weighted version of PCA, which, unlike the standard approach, considers individual pixels and images selectively, depending on the corresponding weights. Then we propose a robust PCA method for obtaining a consistent subspace representation in the presence of outlying pixels in the training images. The method is based on the EM algorithm for estimation of principal subspaces in the presence of missing data. We demonstrate the efficiency of the proposed methods in a number of experiments. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.