A robust classifier combined with an auto-associative network for completing partly occluded images
A robust classifier combined with an auto-associative network for completing partly occluded images
复制标题
DOI：
10.1016/j.neunet.2005.03.011
复制
发表时间：
2005-09
期刊：
影响因子：
--
通讯作者：
Takashi Takahashi;Takio Kurita
中科院分区：
文献类型：
--
作者：
Takashi Takahashi;Takio Kurita
本文描述了一种构造不受图像遮挡影响的分类器的方法。我们提出了一种将自关联网络集成到简单分类器中的方法。由于自关联网络可以从部分遮挡的输入图像中召回原始图像，我们可以利用它来检测遮挡区域，并通过用召回的像素替换这些区域来完成输入图像。通过对该重建过程的迭代，该网络能够对有遮挡的目标进行鲁棒分类。为了验证该方法的有效性，我们进行了人脸图像分类实验。结果表明，即使约30%的人脸图像被遮挡，分类性能也不会下降。
This paper describes an approach for constructing a classifier which is unaffected by occlusions in images. We propose a method for integrating an auto-associative network into a simple classifier. As the auto-associative network can recall the original image from a partly occluded input image, we can employ it to detect occluded regions and complete the input image by replacing those regions with recalled pixels. By iterating this reconstruction process, the integrated network is able to classify target objects with occlusions robustly. To confirm the effectiveness of this method, we performed experiments involving face image classification. It is shown that the classification performance is not decreased, even if about 30% of the face image is occluded.