Robust representations for face recognition: The power of averages
Robust representations for face recognition: The power of averages
复制标题
DOI：
10.1016/j.cogpsych.2005.06.003
复制
发表时间：
2005-11-01
影响因子：
2.6
通讯作者：
White, D
中科院分区：
文献类型：
--
作者：
Burton, AM;Jenkins, R;White, D
我们能够在图像质量变化很大的情况下轻松识别熟悉的面孔，尽管我们匹配不熟悉面孔的能力非常差。在这里，我们要问的是，当我们熟悉一张脸时，它的表征是如何变化的，我们使用一种简单的图像平均技术来获得已知面孔的抽象表征。使用主成分分析，我们表明，基于这些平均值的计算系统始终优于基于实例集合的系统。此外，平均值的质量会随着使用更多图像而提高。这些模拟是用著名的面孔进行的，我们无法控制这些面孔的表面图像特征。然后，我们提出了三个实验的数据表明，图像平均也可以提高人类观察者的识别。最后，我们描述了如何PCA图像平均值出现保存身份特定的人脸信息，同时消除非诊断的图片信息。因此，我们认为这是一个很好的候选人，一个强大的人脸表示。(c)2005年爱思唯尔公司All rights reserved.
We are able to recognise familiar faces easily across large variations in image quality, though our ability to match unfamiliar faces is strikingly poor. Here we ask how the representation of a face changes as we become familiar with it. We use a simple image-averaging technique to derive abstract representations of known faces. Using Principal Components Analysis, we show that computational systems based on these averages consistently outperform systems based on collections of instances. Furthermore, the quality of the average improves as more images are used to derive it. These simulations are carried out with famous faces, over which we had no control of superficial image characteristics. We then present data from three experiments demonstrating that image averaging can also improve recognition by human observers. Finally, we describe how PCA on image averages appears to preserve identity-specific face information, while eliminating non-diagnostic pictorial information. We therefore suggest that this is a good candidate for a robust face representation. (c) 2005 Elsevier Inc. All rights reserved.